Best LLM for coding
Issue resolution, code generation, private mergeability tasks, long-horizon engineering tasks, webdev preference and security review contribute once each. LiveCodeBench is the stable 2025-08-01 snapshot of 454 problems dated 2024-08-01 through 2025-05-01, so it does not cover newer frontier families. Every row prints coverage and marks partial evidence.
Aldena runs these models inside your team's projects. See what each one costs.
| rank | model | vendor | composite | pricein / out | benchmarks | % | % | % | % | % | % | % | % | % | % | % | elo | elo | % | count |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra (max)openai/gpt-6-astra:max | OpenAI | 84.6 | $10.00 / $50.00 | 5 of 15 benchmarks | 73.2% | 53.3% | 76.2% | 1548 | 1767 | ||||||||||
| 2 | Claude Opus 5.5 (high)anthropic/claude-opus-5.5:high | Anthropic | 81.4 | $4.00 / $20.00 | 3 of 15 benchmarks | 54.0% | 78.9% | 1546 | ||||||||||||
| 3 | Claude Opus 5.5 (max)anthropic/claude-opus-5.5:max | Anthropic | 80.1 | $4.00 / $20.00 | 3 of 15 benchmarks | 54.4% | 71.4% | 1818 | ||||||||||||
| 4 | Claude Fable 5.1 (max)anthropic/claude-fable-5.1:max | Anthropic | 79.3 | $10.00 / $50.00 | 4 of 15 benchmarks | 50.3% | 57.1% | 1534 | 1744 | |||||||||||
| 5 | Claude Fable 5 (high)anthropic/claude-fable-5:high | Anthropic | 78.8 | $10.00 / $50.00 | 5 of 15 benchmarks | 68.6% | 52.7% | 63.9% | 1551 | 1625 | ||||||||||
| 6 | Claude Opus 5 (max)anthropic/claude-opus-5:max | Anthropic | 78.2 | $5.00 / $25.00 | 5 of 15 benchmarks | 73.7% | 48.0% | 45.7% | 1528 | 1691 | ||||||||||
| 7 | Claude Sonnet 5.5 (xhigh)anthropic/claude-sonnet-5.5:xhigh | Anthropic | 78.1 | $2.00 / $10.00 | 3 of 15 benchmarks | 52.1% | 1517 | 1773 | ||||||||||||
| 8 | Gemini 4 Carbon (high)google/gemini-4-carbon:high | 77.6 | — | 2 of 15 benchmarks | 1567 | 1768 | ||||||||||||||
| 9 | Claude Opus 5 (high)anthropic/claude-opus-5:high | Anthropic | 77.4 | $5.00 / $25.00 | 4 of 15 benchmarks | 72.8% | 48.0% | 1532 | 1656 | |||||||||||
| 10 | Claude Opus 4.6anthropic/claude-opus-4.6 | Anthropic | 76.9 | $5.00 / $25.00 | 4 of 15 benchmarks | 78.7% | 72.0% | 1547 | 1537 | |||||||||||
| 11 | Gemini 4 Argon (high)google/gemini-4-argon:high | 76.6 | $2.00 / $10.00 | 5 of 15 benchmarks | 45.9% | 58.9% | 64.8% | 1553 | 1683 | |||||||||||
| 12 | GPT-6.1 Sol (max)openai/gpt-6.1-sol:max | OpenAI | 76.5 | $2.00 / $10.00 | 4 of 15 benchmarks | 47.6% | 54.3% | 1541 | 1743 | |||||||||||
| 13 | Kimi K3 (max)moonshotai/kimi-k3:max | MoonshotAI | 75.9 | $0.192 / $16.00 | 5 of 15 benchmarks | 68.5% | 1537 | 1657 | 37.2% | 44.0 | ||||||||||
| 14 | GPT-6 Astra (xhigh)openai/gpt-6-astra:xhigh | OpenAI | 75.7 | $10.00 / $50.00 | 2 of 15 benchmarks | 74.1% | 50.6% | |||||||||||||
| 15 | GPT-6.1 Terra (max)openai/gpt-6.1-terra:max | OpenAI | 75.3 | $1.00 / $5.00 | 2 of 15 benchmarks | 78.1% | 1678 | |||||||||||||
| 16 | GPT-6 Sol (max)openai/gpt-6-sol:max | OpenAI | 74.9 | $2.00 / $10.00 | 4 of 15 benchmarks | 49.3% | 53.3% | 1519 | 1674 | |||||||||||
| 17 | Claude Opus 4.5anthropic/claude-opus-4.5 | Anthropic | 74.6 | $5.00 / $25.00 | 5 of 15 benchmarks | 76.7% | 52.6% | 70.7% | 1523 | 1469 | ||||||||||
| 18 | GPT-6 Astra (high)openai/gpt-6-astra:high | OpenAI | 74.1 | $10.00 / $50.00 | 3 of 15 benchmarks | 73.2% | 50.9% | 46.7% | ||||||||||||
| 19 | GPT-5.6 Sol (xhigh)openai/gpt-5.6-sol:xhigh | OpenAI | 73.8 | $4.00 / $20.00 | 4 of 15 benchmarks | 70.7% | 46.8% | 1533 | 1615 | |||||||||||
| 20 | Claude Fable 5.1 (high)anthropic/claude-fable-5.1:high | Anthropic | 73.7 | $10.00 / $50.00 | 2 of 15 benchmarks | 50.3% | 73.3% | |||||||||||||
| 21 | Claude Sonnet 5.5 (high)anthropic/claude-sonnet-5.5:high | Anthropic | 73.3 | $2.00 / $10.00 | 2 of 15 benchmarks | 49.4% | 1713 | |||||||||||||
| 22 | Claude Fable 5 (xhigh)anthropic/claude-fable-5:xhigh | Anthropic | 73.3 | $10.00 / $50.00 | 2 of 15 benchmarks | 69.9% | 53.5% | |||||||||||||
| 23 | Muse Spark 1.3 (max)meta/muse-spark-1.3:max | Meta | 73.3 | $1.25 / $4.25 | 2 of 15 benchmarks | 1532 | 1654 | |||||||||||||
| 24 | DeepSeek V4.1 Flash (max)deepseek/deepseek-v4.1-flash:max | DeepSeek | 73.1 | $0.051 / $0.567 | 2 of 15 benchmarks | 1525 | 1664 | |||||||||||||
| 25 | MiMo-V2.6-Proxiaomi/mimo-v2.6-pro | Xiaomi | 72.8 | $0.435 / $0.87 | 2 of 15 benchmarks | 1538 | 1624 | |||||||||||||
| 26 | Claude Opus 5 (medium)anthropic/claude-opus-5:medium | Anthropic | 71.3 | $5.00 / $25.00 | 2 of 15 benchmarks | 68.9% | 53.4% | |||||||||||||
| 27 | GPT-6 Astra (medium)openai/gpt-6-astra:medium | OpenAI | 71.2 | $10.00 / $50.00 | 2 of 15 benchmarks | 72.8% | 48.8% | |||||||||||||
| 28 | Claude Fable 5.2anthropic/claude-fable-5.2 | Anthropic | 70.6 | $8.00 / $40.00 | 1 of 15 benchmarks | 69.9% | ||||||||||||||
| 29 | Claude Fable 5.2 (max)anthropic/claude-fable-5.2:max | Anthropic | 70.6 | $8.00 / $40.00 | 1 of 15 benchmarks | 90.5% | ||||||||||||||
| 30 | Claude Opus 5.5 (medium)anthropic/claude-opus-5.5:medium | Anthropic | 70.6 | $4.00 / $20.00 | 1 of 15 benchmarks | 54.6% | ||||||||||||||
| 31 | o4 Mini Highopenai/o4-mini-high | OpenAI | 70.6 | — | 1 of 15 benchmarks | 80.2% | ||||||||||||||
| 32 | GPT 5.5 Pre Release (xhigh)openai/gpt-5.5-pre-release:xhigh | OpenAI | 70.2 | — | 1 of 15 benchmarks | 80.6% | ||||||||||||||
| 33 | Muse Wonder (max)meta/muse-wonder:max | Meta | 70.0 | $4.00 / $20.00 | 3 of 15 benchmarks | 31.4% | 1546 | 1650 | ||||||||||||
| 34 | Claude Opus 4.7anthropic/claude-opus-4.7 | Anthropic | 69.8 | $5.00 / $25.00 | 2 of 15 benchmarks | 1546 | 1555 | |||||||||||||
| 35 | Claude Fable 5 (max)anthropic/claude-fable-5:max | Anthropic | 69.8 | $10.00 / $50.00 | 3 of 15 benchmarks | 69.7% | 51.6% | 39.5% | ||||||||||||
| 36 | Claude Opus 4.5 (medium)anthropic/claude-opus-4.5:medium | Anthropic | 69.5 | $5.00 / $25.00 | 1 of 15 benchmarks | 79.2% | ||||||||||||||
| 37 | MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash | Xiaomi | 69.3 | $0.14 / $0.28 | 2 of 15 benchmarks | 1511 | 1636 | |||||||||||||
| 38 | o3 (high)openai/o3:high | OpenAI | 69.3 | $2.00 / $8.00 | 1 of 15 benchmarks | 75.8% | ||||||||||||||
| 39 | Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | 69.2 | $0.50 / $3.00 | 4 of 15 benchmarks | 75.4% | 72.7% | 1505 | 1440 | ||||||||||||
| 40 | GPT-6 Astraopenai/gpt-6-astra | OpenAI | 69.1 | $10.00 / $50.00 | 1 of 15 benchmarks | 65.5% | ||||||||||||||
| 41 | Doubao-Seed-Codebytedance/doubao-seed-code | ByteDance | 69.1 | — | 1 of 15 benchmarks | 78.8% | ||||||||||||||
| 42 | Kimi K3.1 Pro (max)moonshotai/kimi-k3.1-pro:max | MoonshotAI | 68.8 | $2.00 / $10.00 | 1 of 15 benchmarks | 1687 | ||||||||||||||
| 43 | GPT-5.6 Sol (max)openai/gpt-5.6-sol:max | OpenAI | 68.5 | $4.00 / $20.00 | 3 of 15 benchmarks | 72.7% | 47.5% | 44.8% | ||||||||||||
| 44 | Muse Spark 1.1meta/muse-spark-1.1 | Meta | 68.4 | $1.25 / $4.25 | 2 of 15 benchmarks | 1533 | 1542 | |||||||||||||
| 45 | Claude Opus 5.5 (xhigh)anthropic/claude-opus-5.5:xhigh | Anthropic | 68.3 | $4.00 / $20.00 | 1 of 15 benchmarks | 51.4% | ||||||||||||||
| 46 | o4 Mini (medium)openai/o4-mini:medium | OpenAI | 67.9 | — | 1 of 15 benchmarks | 74.2% | ||||||||||||||
| 47 | Claude Fable 5.1 (medium)anthropic/claude-fable-5.1:medium | Anthropic | 67.8 | $10.00 / $50.00 | 1 of 15 benchmarks | 50.9% | ||||||||||||||
| 48 | Muse Sparkmeta/muse-spark | Meta | 67.8 | — | 1 of 15 benchmarks | 1528 | ||||||||||||||
| 49 | GLM 5.3 (max)z-ai/glm-5.3:max | Z.ai | 67.8 | $0.0699 / $1.40 | 4 of 15 benchmarks | 69.0% | 40.1% | 1522 | 1622 | |||||||||||
| 50 | Claude Opus 5.5anthropic/claude-opus-5.5 | Anthropic | 67.7 | $4.00 / $20.00 | 1 of 15 benchmarks | 62.3% | ||||||||||||||
| 51 | Claude Opus 4.8anthropic/claude-opus-4.8 | Anthropic | 67.2 | $5.00 / $25.00 | 2 of 15 benchmarks | 1529 | 1536 | |||||||||||||
| 52 | GPT-6.1 Sol (medium)openai/gpt-6.1-sol:medium | OpenAI | 66.8 | $2.00 / $10.00 | 1 of 15 benchmarks | 50.2% | ||||||||||||||
| 53 | Claude Opus 4.5 (high)anthropic/claude-opus-4.5:high | Anthropic | 66.8 | $5.00 / $25.00 | 1 of 15 benchmarks | 76.8% | ||||||||||||||
| 54 | Grok 4.6 (high)x-ai/grok-4.6:high | SpaceXAI | 66.6 | $2.00 / $6.00 | 6 of 15 benchmarks | 65.2% | 48.0% | 1508 | 1618 | 29.1% | 38.0 | |||||||||
| 55 | SWE-2 (max)cognition/swe-2:max | Cognition | 66.6 | — | 1 of 15 benchmarks | 50.0% | ||||||||||||||
| 56 | Grok 4.7 (xhigh)x-ai/grok-4.7:xhigh | SpaceXAI | 66.4 | $2.00 / $6.00 | 3 of 15 benchmarks | 45.6% | 1492 | 1640 | ||||||||||||
| 57 | Claude Sonnet 5.5anthropic/claude-sonnet-5.5 | Anthropic | 66.2 | $2.00 / $10.00 | 1 of 15 benchmarks | 61.9% | ||||||||||||||
| 58 | Claude Fable 5.1 (low)anthropic/claude-fable-5.1:low | Anthropic | 66.2 | $10.00 / $50.00 | 1 of 15 benchmarks | 49.8% | ||||||||||||||
| 59 | Claude Opus 5 (xhigh)anthropic/claude-opus-5:xhigh | Anthropic | 66.1 | $5.00 / $25.00 | 2 of 15 benchmarks | 73.2% | 43.6% | |||||||||||||
| 60 | Qwen3.6 Max Previewqwen/qwen3.6-max-preview | Qwen | 66.1 | — | 3 of 15 benchmarks | 76.7% | 1510 | 1482 | ||||||||||||
| 61 | Grok 4.5x-ai/grok-4.5 | SpaceXAI | 65.9 | $2.00 / $6.00 | 2 of 15 benchmarks | 1514 | 1552 | |||||||||||||
| 62 | Claude Sonnet 4.6anthropic/claude-sonnet-4.6 | Anthropic | 65.6 | $3.00 / $15.00 | 5 of 15 benchmarks | 75.2% | 1528 | 1522 | 29.1% | 32.0 | ||||||||||
| 63 | Inkling 2 Smallthinkingmachines/inkling-2-small | Thinking Machines | 65.6 | — | 2 of 15 benchmarks | 1486 | 1649 | |||||||||||||
| 64 | GPT-6.1 Sol (xhigh)openai/gpt-6.1-sol:xhigh | OpenAI | 65.6 | $2.00 / $10.00 | 1 of 15 benchmarks | 49.3% | ||||||||||||||
| 65 | Hy4 previewtencent/hy4-preview | Tencent | 65.6 | $0.7506 / $2.2509 | 1 of 15 benchmarks | 1632 | ||||||||||||||
| 66 | GLM 5.1z-ai/glm-5.1 | Z.ai | 65.5 | $1.40 / $4.40 | 3 of 15 benchmarks | 74.2% | 1513 | 1508 | ||||||||||||
| 67 | Claude Fable 5 (medium)anthropic/claude-fable-5:medium | Anthropic | 65.5 | $10.00 / $50.00 | 2 of 15 benchmarks | 65.4% | 49.8% | |||||||||||||
| 68 | Claude Opus 4.5 (high 32K)anthropic/claude-opus-4.5:high-32k | Anthropic | 65.2 | $5.00 / $25.00 | 2 of 15 benchmarks | 1530 | 1493 | |||||||||||||
| 69 | DeepSeek V4 Pro 0423 (high)deepseek/deepseek-v4-pro:high | DeepSeek | 65.1 | $0.8837 / $1.7675 | 2 of 15 benchmarks | 1503 | 1581 | |||||||||||||
| 70 | Gemini 3 Flash Preview (high)google/gemini-3-flash-preview:high | 65.1 | $0.50 / $3.00 | 1 of 15 benchmarks | 75.8% | |||||||||||||||
| 71 | MiniMax M2.5 (high)minimax/minimax-m2.5:high | MiniMax | 65.1 | $0.30 / $1.20 | 1 of 15 benchmarks | 75.8% | ||||||||||||||
| 72 | GPT-5.2 Chatopenai/gpt-5.2-chat | OpenAI | 65.1 | — | 1 of 15 benchmarks | 1515 | ||||||||||||||
| 73 | Dola Seed 2.0 Probytedance/dola-seed-2.0-pro | ByteDance | 65.0 | — | 1 of 15 benchmarks | 1514 | ||||||||||||||
| 74 | DeepSeek V4 Pro 0423 (max)deepseek/deepseek-v4-pro:max | DeepSeek | 64.9 | $0.8837 / $1.7675 | 2 of 15 benchmarks | 77.6% | 62.8% | |||||||||||||
| 75 | Qwen3.8 Flash Nextqwen/qwen3.8-flash-next | Qwen | 64.9 | — | 1 of 15 benchmarks | 1624 | ||||||||||||||
| 76 | Claude Fable 5.1 (xhigh)anthropic/claude-fable-5.1:xhigh | Anthropic | 64.8 | $10.00 / $50.00 | 1 of 15 benchmarks | 48.7% | ||||||||||||||
| 77 | Gemini 4 Carbongoogle/gemini-4-carbon | 64.8 | — | 1 of 15 benchmarks | 61.2% | |||||||||||||||
| 78 | Gemini 3.7 Flash (high)google/gemini-3.7-flash:high | 64.8 | $0.75 / $3.75 | 5 of 15 benchmarks | 65.3% | 42.2% | 41.1% | 1520 | 1588 | |||||||||||
| 79 | Qwen3.8 27Bqwen/qwen3.8-27b | Qwen | 64.7 | $0.15 / $1.875 | 2 of 15 benchmarks | 1495 | 1591 | |||||||||||||
| 80 | GPT 5.5 Instantopenai/gpt-5.5-instant | OpenAI | 64.7 | — | 1 of 15 benchmarks | 1514 | ||||||||||||||
| 81 | Qwen3.5 Max Previewqwen/qwen3.5-max-preview | Qwen | 64.6 | — | 1 of 15 benchmarks | 1513 | ||||||||||||||
| 82 | GPT-6 Sol (xhigh)openai/gpt-6-sol:xhigh | OpenAI | 64.6 | $2.00 / $10.00 | 1 of 15 benchmarks | 48.5% | ||||||||||||||
| 83 | Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtools | 64.5 | $2.00 / $12.00 | 1 of 15 benchmarks | 75.6% | |||||||||||||||
| 84 | Muse Spark 1.3 (xhigh)meta/muse-spark-1.3:xhigh | Meta | 64.4 | $1.25 / $4.25 | 1 of 15 benchmarks | 1621 | ||||||||||||||
| 85 | Ernie 5.1baidu/ernie-5.1 | Baidu | 64.2 | — | 1 of 15 benchmarks | 1512 | ||||||||||||||
| 86 | Claude Opus 4.1 (thinking 16K)anthropic/claude-opus-4.1:thinking-16k | Anthropic | 64.1 | $15.00 / $75.00 | 1 of 15 benchmarks | 1511 | ||||||||||||||
| 87 | EXAONE 4.0 32Blg-ai/exaone-4.0-32b | LG AI Research | 63.9 | — | 1 of 15 benchmarks | 70.0% | ||||||||||||||
| 88 | Muse Spark 1.2 (xhigh)meta/muse-spark-1.2:xhigh | Meta | 63.6 | $1.25 / $4.25 | 3 of 15 benchmarks | 54.9% | 1543 | 1534 | ||||||||||||
| 89 | GPT-5.3-Codex (high)openai/gpt-5.3-codex:high | OpenAI | 63.4 | $1.75 / $14.00 | 1 of 15 benchmarks | 74.8% | ||||||||||||||
| 90 | Grok 4.20 Multi Agent Beta 0309x-ai/grok-4.20-multi-agent-beta-0309 | SpaceXAI | 63.4 | — | 1 of 15 benchmarks | 1508 | ||||||||||||||
| 91 | Claude Fable 5.1anthropic/claude-fable-5.1 | Anthropic | 63.3 | $10.00 / $50.00 | 1 of 15 benchmarks | 56.3% | ||||||||||||||
| 92 | GPT-5.5 (high)openai/gpt-5.5:high | OpenAI | 63.3 | $5.00 / $30.00 | 7 of 15 benchmarks | 64.4% | 40.6% | 10.0% | 1518 | 1487 | 47.7% | 72.0 | ||||||||
| 93 | GPT-6.1 Sol (high)openai/gpt-6.1-sol:high | OpenAI | 63.3 | $2.00 / $10.00 | 1 of 15 benchmarks | 48.0% | ||||||||||||||
| 94 | Grok 4.5 (high)x-ai/grok-4.5:high | SpaceXAI | 63.2 | $2.00 / $6.00 | 5 of 15 benchmarks | 53.8% | 42.4% | 32.2% | 47.7% | 55.0 | ||||||||||
| 95 | GPT-6 Sol (high)openai/gpt-6-sol:high | OpenAI | 63.1 | $2.00 / $10.00 | 1 of 15 benchmarks | 47.7% | ||||||||||||||
| 96 | Grok 4.6 (medium)x-ai/grok-4.6:medium | SpaceXAI | 63.1 | $2.00 / $6.00 | 2 of 15 benchmarks | 67.5% | 46.1% | |||||||||||||
| 97 | Kimi K2.6moonshotai/kimi-k2.6 | MoonshotAI | 63.0 | $0.65 / $3.41 | 6 of 15 benchmarks | 76.7% | 2.4% | 1516 | 1509 | 36.0% | 45.0 | |||||||||
| 98 | GPT-5openai/gpt-5 | OpenAI | 63.0 | $1.25 / $10.00 | 1 of 15 benchmarks | 74.4% | ||||||||||||||
| 99 | MiMo-V2.5-Proxiaomi/mimo-v2.5-pro | Xiaomi | 63.0 | $0.48 / $1.80 | 2 of 15 benchmarks | 1520 | 1479 | |||||||||||||
| 100 | Grok 4.7 (high)x-ai/grok-4.7:high | SpaceXAI | 62.8 | $2.00 / $6.00 | 1 of 15 benchmarks | 47.6% | ||||||||||||||
| 101 | Step 5 Previewstepfun/step-5-preview | StepFun | 62.7 | $1.00 / $2.70 | 1 of 15 benchmarks | 1505 | ||||||||||||||
| 102 | Kimi K3 (high)moonshotai/kimi-k3:high | MoonshotAI | 62.7 | $0.192 / $16.00 | 2 of 15 benchmarks | 31.4% | 41.0 | |||||||||||||
| 103 | OpenReasoning Nemotron 32Bnvidia/openreasoning-nemotron-32b | NVIDIA | 62.6 | — | 1 of 15 benchmarks | 69.8% | ||||||||||||||
| 104 | MiniMax M3.1 Flashminimax/minimax-m3.1-flash | MiniMax | 62.4 | $0.075 / $0.30 | 1 of 15 benchmarks | 1582 | ||||||||||||||
| 105 | Gemini 4 Argon (medium)google/gemini-4-argon:medium | 62.3 | $2.00 / $10.00 | 1 of 15 benchmarks | 47.5% | |||||||||||||||
| 106 | R1 0528deepseek/deepseek-r1-0528 | DeepSeek | 62.3 | $0.50 / $2.15 | 2 of 15 benchmarks | 73.1% | 1464 | |||||||||||||
| 107 | Gemini 3 Progoogle/gemini-3-pro | 62.0 | — | 3 of 15 benchmarks | 68.7% | 1517 | 1441 | |||||||||||||
| 108 | DeepSeek V4 Flash 0423 (high)deepseek/deepseek-v4-flash:high | DeepSeek | 61.9 | $0.091 / $0.182 | 2 of 15 benchmarks | 1480 | 1582 | |||||||||||||
| 109 | Gemini 4 Argongoogle/gemini-4-argon | 61.9 | $2.00 / $10.00 | 1 of 15 benchmarks | 55.0% | |||||||||||||||
| 110 | Gemini 3.8 Flash (medium)google/gemini-3.8-flash:medium | 61.9 | $0.75 / $3.75 | 2 of 15 benchmarks | 71.0% | 41.2% | ||||||||||||||
| 111 | Claude Opus 5.5 (low)anthropic/claude-opus-5.5:low | Anthropic | 61.8 | $4.00 / $20.00 | 1 of 15 benchmarks | 47.3% | ||||||||||||||
| 112 | Claude Haiku 5.5 (high)anthropic/claude-haiku-5.5:high | Anthropic | 61.5 | $0.10 / $0.50 | 3 of 15 benchmarks | 41.9% | 1490 | 1595 | ||||||||||||
| 113 | Claude Haiku 5.5 (max)anthropic/claude-haiku-5.5:max | Anthropic | 61.5 | $0.10 / $0.50 | 2 of 15 benchmarks | 46.4% | 43.8% | |||||||||||||
| 114 | Step 5 Preview (high)stepfun/step-5-preview:high | StepFun | 61.5 | $1.00 / $2.70 | 1 of 15 benchmarks | 1572 | ||||||||||||||
| 115 | SWE-2 (high)cognition/swe-2:high | Cognition | 61.4 | — | 1 of 15 benchmarks | 47.2% | ||||||||||||||
| 116 | Gemini 4 Argon (low)google/gemini-4-argon:low | 61.4 | $2.00 / $10.00 | 1 of 15 benchmarks | 47.2% | |||||||||||||||
| 117 | Qwen3.7 Maxqwen/qwen3.7-max | Qwen | 61.4 | $1.475 / $4.425 | 4 of 15 benchmarks | 77.3% | 9.5% | 1524 | 1515 | |||||||||||
| 118 | Qwen3.7 Plusqwen/qwen3.7-plus | Qwen | 61.2 | $0.32 / $1.28 | 1 of 15 benchmarks | 1500 | ||||||||||||||
| 119 | GLM 5z-ai/glm-5 | Z.ai | 61.2 | $1.00 / $3.20 | 4 of 15 benchmarks | 72.1% | 69.7% | 1498 | 1435 | |||||||||||
| 120 | Qwen3.8 Maxqwen/qwen3.8-max | Qwen | 61.2 | — | 3 of 15 benchmarks | 15.8% | 1524 | 1670 | ||||||||||||
| 121 | Gemini 3.5 Flash (medium)google/gemini-3.5-flash:medium | 61.2 | $1.50 / $9.00 | 2 of 15 benchmarks | 1506 | 1490 | ||||||||||||||
| 122 | Hy3tencent/hy3 | Tencent | 61.1 | $0.0825 / $0.33 | 2 of 15 benchmarks | 1504 | 1506 | |||||||||||||
| 123 | Claude Opus 4 (thinking 16K)anthropic/claude-opus-4:thinking-16k | Anthropic | 61.0 | — | 1 of 15 benchmarks | 1499 | ||||||||||||||
| 124 | Claude Fable 5 (low)anthropic/claude-fable-5:low | Anthropic | 60.8 | $10.00 / $50.00 | 2 of 15 benchmarks | 59.6% | 48.0% | |||||||||||||
| 125 | GPT-6 Astra (low)openai/gpt-6-astra:low | OpenAI | 60.8 | $10.00 / $50.00 | 2 of 15 benchmarks | 67.0% | 45.3% | |||||||||||||
| 126 | GPT-5.3 Chatopenai/gpt-5.3-chat | OpenAI | 60.8 | — | 1 of 15 benchmarks | 1497 | ||||||||||||||
| 127 | Gemini 3 Pro Previewgoogle/gemini-3-pro-preview | 60.7 | — | 1 of 15 benchmarks | 72.9% | |||||||||||||||
| 128 | GLM 5.3 Flashz-ai/glm-5.3-flash | Z.ai | 60.7 | $0.15 / $0.50 | 3 of 15 benchmarks | 18.1% | 1527 | 1609 | ||||||||||||
| 129 | o3openai/o3 | OpenAI | 60.6 | $2.00 / $8.00 | 3 of 15 benchmarks | 58.4% | 36.0% | 1460 | ||||||||||||
| 130 | GPT-5.6 Terra (max)openai/gpt-5.6-terra:max | OpenAI | 60.6 | $2.00 / $12.00 | 2 of 15 benchmarks | 69.6% | 41.3% | |||||||||||||
| 131 | Claude Opus 5anthropic/claude-opus-5 | Anthropic | 60.4 | $5.00 / $25.00 | 1 of 15 benchmarks | 52.0% | ||||||||||||||
| 132 | Mistral Large 4mistralai/mistral-large-4-0 | Mistral | 60.4 | $0.70 / $2.10 | 2 of 15 benchmarks | 1473 | 1563 | |||||||||||||
| 133 | GPT-5.4 (high)openai/gpt-5.4:high | OpenAI | 60.4 | $2.50 / $15.00 | 4 of 15 benchmarks | 76.9% | 15.6% | 1521 | 1462 | |||||||||||
| 134 | Claude Sonnet 5.5 (max)anthropic/claude-sonnet-5.5:max | Anthropic | 60.3 | $2.00 / $10.00 | 1 of 15 benchmarks | 46.2% | ||||||||||||||
| 135 | GLM 5 (high)z-ai/glm-5:high | Z.ai | 60.2 | $1.00 / $3.20 | 1 of 15 benchmarks | 72.8% | ||||||||||||||
| 136 | GPT-5.5openai/gpt-5.5 | OpenAI | 60.1 | $5.00 / $30.00 | 2 of 15 benchmarks | 1510 | 1455 | |||||||||||||
| 137 | Gemini 3.8 Flash (high)google/gemini-3.8-flash:high | 60.0 | $0.75 / $3.75 | 6 of 15 benchmarks | 73.8% | 38.0% | 1530 | 1584 | 22.1% | 25.0 | ||||||||||
| 138 | OpenCodeReasoning Nemotron 1.1 32Bnvidia/opencodereasoning-nemotron-1.1-32b | NVIDIA | 59.9 | — | 1 of 15 benchmarks | 66.8% | ||||||||||||||
| 139 | Grok 4.1x-ai/grok-4.1 | SpaceXAI | 59.9 | — | 1 of 15 benchmarks | 1492 | ||||||||||||||
| 140 | GPT-6 Sol (medium)openai/gpt-6-sol:medium | OpenAI | 59.8 | $2.00 / $10.00 | 1 of 15 benchmarks | 45.9% | ||||||||||||||
| 141 | Claude 3.7 Sonnetanthropic/claude-3-7-sonnet | Anthropic | 59.8 | — | 5 of 15 benchmarks | 61.0% | 51.7% | 33.8% | 31.3% | 1431 | ||||||||||
| 142 | Claude Haiku 5.5 (xhigh)anthropic/claude-haiku-5.5:xhigh | Anthropic | 59.3 | $0.10 / $0.50 | 1 of 15 benchmarks | 45.8% | ||||||||||||||
| 143 | Ernie 5.0 0110baidu/ernie-5.0-0110 | Baidu | 59.2 | — | 1 of 15 benchmarks | 1489 | ||||||||||||||
| 144 | Claude Opus 4.7 (high)anthropic/claude-opus-4.7:high | Anthropic | 59.1 | $5.00 / $25.00 | 4 of 15 benchmarks | 35.2% | 31.1% | 1551 | 1557 | |||||||||||
| 145 | GPT-5.5 (xhigh)openai/gpt-5.5:xhigh | OpenAI | 59.1 | $5.00 / $30.00 | 4 of 15 benchmarks | 67.0% | 43.0% | 34.3% | 1512 | |||||||||||
| 146 | Kimi K2.5moonshotai/kimi-k2.5 | MoonshotAI | 59.1 | $0.532 / $3.325 | 2 of 15 benchmarks | 73.8% | 67.3% | |||||||||||||
| 147 | Claude Fable 5anthropic/claude-fable-5 | Anthropic | 59.0 | $10.00 / $50.00 | 1 of 15 benchmarks | 47.0% | ||||||||||||||
| 148 | Gemini 3.7 Flash (medium)google/gemini-3.7-flash:medium | 59.0 | $0.75 / $3.75 | 2 of 15 benchmarks | 65.5% | 43.6% | ||||||||||||||
| 149 | GPT-5.6 Terra (xhigh)openai/gpt-5.6-terra:xhigh | OpenAI | 58.9 | $2.00 / $12.00 | 4 of 15 benchmarks | 60.2% | 38.8% | 1517 | 1520 | |||||||||||
| 150 | Claude Sonnet 4.5 (high)anthropic/claude-sonnet-4.5:high | Anthropic | 58.8 | $3.00 / $15.00 | 1 of 15 benchmarks | 71.4% | ||||||||||||||
| 151 | Mimo v2 Omnixiaomi/mimo-v2-omni | Xiaomi | 58.8 | — | 1 of 15 benchmarks | 1488 | ||||||||||||||
| 152 | MiniMax M3minimax/minimax-m3 | MiniMax | 58.7 | $0.30 / $1.20 | 2 of 15 benchmarks | 1494 | 1484 | |||||||||||||
| 153 | GPT-6.1 Sol (low)openai/gpt-6.1-sol:low | OpenAI | 58.6 | $2.00 / $10.00 | 1 of 15 benchmarks | 45.5% | ||||||||||||||
| 154 | GPT-5.1 (high)openai/gpt-5.1:high | OpenAI | 58.5 | $1.25 / $10.00 | 2 of 15 benchmarks | 68.0% | 1492 | |||||||||||||
| 155 | Muse Spark Open (max)meta/muse-spark-open:max | Meta | 58.5 | $1.25 / $4.25 | 1 of 15 benchmarks | 1528 | ||||||||||||||
| 156 | GPT-5.6 Luna (high)openai/gpt-5.6-luna:high | OpenAI | 58.4 | $0.20 / $1.20 | 4 of 15 benchmarks | 44.3% | 35.9% | 41.9% | 57.0 | |||||||||||
| 157 | DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | DeepSeek | 58.2 | $0.091 / $0.182 | 1 of 15 benchmarks | 1484 | ||||||||||||||
| 158 | Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | Reflection | 58.2 | $0.30 / $1.00 | 2 of 15 benchmarks | 1505 | 1438 | |||||||||||||
| 159 | GPT-6 Luna (max)openai/gpt-6-luna:max | OpenAI | 58.2 | $0.10 / $0.50 | 4 of 15 benchmarks | 42.4% | 26.7% | 1502 | 1577 | |||||||||||
| 160 | DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro | DeepSeek | 58.2 | $0.8837 / $1.7675 | 2 of 15 benchmarks | 1501 | 1448 | |||||||||||||
| 161 | Claude Sonnet 4anthropic/claude-sonnet-4 | Anthropic | 58.0 | — | 5 of 15 benchmarks | 57.0% | 58.3% | 35.6% | 47.1% | 1449 | ||||||||||
| 162 | Seed 2.1 Pro Previewbytedance/seed-2.1-pro-preview | ByteDance | 57.8 | — | 1 of 15 benchmarks | 1519 | ||||||||||||||
| 163 | Kimi K3 (none)moonshotai/kimi-k3:none | MoonshotAI | 57.8 | $0.192 / $16.00 | 1 of 15 benchmarks | 44.2% | ||||||||||||||
| 164 | GLM 5.2 (max)z-ai/glm-5.2:max | Z.ai | 57.7 | $0.006 / $6.80 | 5 of 15 benchmarks | 78.7% | 43.8% | 9.5% | 1515 | 1608 | ||||||||||
| 165 | Grok 4.6 (xhigh)x-ai/grok-4.6:xhigh | SpaceXAI | 57.7 | $2.00 / $6.00 | 3 of 15 benchmarks | 66.7% | 41.1% | 30.5% | ||||||||||||
| 166 | Kimi K2.5 (high)moonshotai/kimi-k2.5:high | MoonshotAI | 57.7 | $0.532 / $3.325 | 1 of 15 benchmarks | 70.8% | ||||||||||||||
| 167 | Claude Opus 4.7 (max)anthropic/claude-opus-4.7:max | Anthropic | 57.6 | $5.00 / $25.00 | 3 of 15 benchmarks | 83.5% | 38.5% | 19.1% | ||||||||||||
| 168 | DeepSeek V4.1 Flash (high)deepseek/deepseek-v4.1-flash:high | DeepSeek | 57.6 | $0.051 / $0.567 | 1 of 15 benchmarks | 43.9% | ||||||||||||||
| 169 | Claude Haiku 5.5anthropic/claude-haiku-5.5 | Anthropic | 57.5 | $0.10 / $0.50 | 1 of 15 benchmarks | 43.8% | ||||||||||||||
| 170 | Claude Sonnet 4.5 (high 32K)anthropic/claude-sonnet-4.5:high-32k | Anthropic | 57.4 | $3.00 / $15.00 | 2 of 15 benchmarks | 1519 | 1394 | |||||||||||||
| 171 | Kimi K2.5 (thinking)moonshotai/kimi-k2.5:thinking | MoonshotAI | 57.3 | $0.532 / $3.325 | 2 of 15 benchmarks | 1502 | 1436 | |||||||||||||
| 172 | Kimi K2 0905moonshotai/kimi-k2-0905 | MoonshotAI | 57.3 | $0.60 / $2.50 | 2 of 15 benchmarks | 71.2% | 1468 | |||||||||||||
| 173 | Claude Opus 4.8 (max)anthropic/claude-opus-4.8:max | Anthropic | 57.2 | $5.00 / $25.00 | 2 of 15 benchmarks | 46.5% | 28.6% | |||||||||||||
| 174 | DeepSeek V3.2 Exp (thinking)deepseek/deepseek-v3.2-exp:thinking | DeepSeek | 57.0 | $0.27 / $0.41 | 1 of 15 benchmarks | 1475 | ||||||||||||||
| 175 | GPT-5.2 (high)openai/gpt-5.2:high | OpenAI | 57.0 | $1.75 / $14.00 | 3 of 15 benchmarks | 73.8% | 66.7% | 1489 | ||||||||||||
| 176 | Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | 57.0 | $0.30 / $2.50 | 2 of 15 benchmarks | 1502 | 1435 | ||||||||||||||
| 177 | DeepSeek V3.2 (high)deepseek/deepseek-v3.2:high | DeepSeek | 57.0 | $0.26 / $0.38 | 1 of 15 benchmarks | 70.0% | ||||||||||||||
| 178 | Claude Sonnet 4 (thinking 32K)anthropic/claude-sonnet-4:thinking-32k | Anthropic | 56.9 | — | 1 of 15 benchmarks | 1474 | ||||||||||||||
| 179 | GPT-5.4openai/gpt-5.4 | OpenAI | 56.9 | $2.50 / $15.00 | 2 of 15 benchmarks | 1511 | 1400 | |||||||||||||
| 180 | Mimo v2 Proxiaomi/mimo-v2-pro | Xiaomi | 56.8 | — | 2 of 15 benchmarks | 1503 | 1434 | |||||||||||||
| 181 | SWE-2 (medium)cognition/swe-2:medium | Cognition | 56.8 | — | 1 of 15 benchmarks | 43.1% | ||||||||||||||
| 182 | Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b | NVIDIA | 56.8 | $0.60 / $2.40 | 1 of 15 benchmarks | 1474 | ||||||||||||||
| 183 | Qwen3 Maxqwen/qwen3-max | Qwen | 56.7 | — | 1 of 15 benchmarks | 1473 | ||||||||||||||
| 184 | o4 Mini (low)openai/o4-mini:low | OpenAI | 56.6 | — | 1 of 15 benchmarks | 65.9% | ||||||||||||||
| 185 | GPT-5.6 Luna (max)openai/gpt-5.6-luna:max | OpenAI | 56.5 | $0.20 / $1.20 | 2 of 15 benchmarks | 67.2% | 39.8% | |||||||||||||
| 186 | GPT-5.6 Sol (high)openai/gpt-5.6-sol:high | OpenAI | 56.4 | $4.00 / $20.00 | 3 of 15 benchmarks | 69.4% | 45.1% | 20.0% | ||||||||||||
| 187 | Gemini 3 Pro Preview (high)google/gemini-3-pro-preview:high | 56.4 | — | 1 of 15 benchmarks | 69.6% | |||||||||||||||
| 188 | LongCat Flash Chatmeituan/longcat-flash-chat | Meituan | 56.3 | — | 1 of 15 benchmarks | 1472 | ||||||||||||||
| 189 | Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | Qwen | 56.2 | $0.14 / $0.80 | 1 of 15 benchmarks | 1472 | ||||||||||||||
| 190 | Kimi K2.5 Instantmoonshotai/kimi-k2.5-instant | Moonshot AI | 56.2 | — | 2 of 15 benchmarks | 1505 | 1406 | |||||||||||||
| 191 | GPT-5.6 Solopenai/gpt-5.6-sol | OpenAI | 56.1 | $4.00 / $20.00 | 1 of 15 benchmarks | 32.2% | ||||||||||||||
| 192 | MiMo-V2.5xiaomi/mimo-v2.5 | Xiaomi | 56.1 | $0.40 / $2.00 | 2 of 15 benchmarks | 1491 | 1438 | |||||||||||||
| 193 | GPT-5.6 Luna (xhigh)openai/gpt-5.6-luna:xhigh | OpenAI | 56.0 | $0.20 / $1.20 | 4 of 15 benchmarks | 56.9% | 38.9% | 1502 | 1519 | |||||||||||
| 194 | Claude Sonnet 5 (high)anthropic/claude-sonnet-5:high | Anthropic | 55.9 | $2.00 / $10.00 | 4 of 15 benchmarks | 48.2% | 39.4% | 1520 | 1539 | |||||||||||
| 195 | Ernie 5.0 Preview 1203baidu/ernie-5.0-preview-1203 | Baidu | 55.8 | — | 1 of 15 benchmarks | 1471 | ||||||||||||||
| 196 | Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | 55.6 | $2.00 / $12.00 | 3 of 15 benchmarks | 14.3% | 1520 | 1446 | |||||||||||||
| 197 | Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 | Qwen | 55.4 | $2.00 / $6.00 | 2 of 15 benchmarks | 17.8% | 1677 | |||||||||||||
| 198 | Chatgpt 4oopenai/chatgpt-4o | OpenAI | 55.4 | — | 1 of 15 benchmarks | 1467 | ||||||||||||||
| 199 | o3 Mini Highopenai/o3-mini-high | OpenAI | 55.3 | — | 2 of 15 benchmarks | 67.4% | 1434 | |||||||||||||
| 200 | Claude Opus 4.8 (xhigh)anthropic/claude-opus-4.8:xhigh | Anthropic | 55.1 | $5.00 / $25.00 | 2 of 15 benchmarks | 54.4% | 45.5% | |||||||||||||
| 201 | Claude Haiku 4.5 (high)anthropic/claude-haiku-4.5:high | Anthropic | 55.1 | $1.00 / $5.00 | 1 of 15 benchmarks | 66.6% | ||||||||||||||
| 202 | SWE-1.7 (none)cognition/swe-1.7:none | Cognition | 55.0 | — | 1 of 15 benchmarks | 42.0% | ||||||||||||||
| 203 | Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct | Qwen | 54.9 | $0.21 / $1.90 | 1 of 15 benchmarks | 1463 | ||||||||||||||
| 204 | GPT 5 Chatopenai/gpt-5-chat | OpenAI | 54.8 | — | 1 of 15 benchmarks | 1462 | ||||||||||||||
| 205 | Grok 4.20 Beta 0309 (reasoning)x-ai/grok-4.20-beta-0309:reasoning | SpaceXAI | 54.7 | — | 2 of 15 benchmarks | 1511 | 1376 | |||||||||||||
| 206 | GLM 5.3z-ai/glm-5.3 | Z.ai | 54.6 | $0.0699 / $1.40 | 1 of 15 benchmarks | 30.2% | ||||||||||||||
| 207 | XBai o4 (medium)metastone/xbai-o4:medium | MetaStoneTec | 54.6 | — | 1 of 15 benchmarks | 65.0% | ||||||||||||||
| 208 | Grok 4.5 (medium)x-ai/grok-4.5:medium | SpaceXAI | 54.5 | $2.00 / $6.00 | 1 of 15 benchmarks | 41.9% | ||||||||||||||
| 209 | GPT-5.1-Codex (medium)openai/gpt-5.1-codex:medium | OpenAI | 54.5 | $1.25 / $10.00 | 1 of 15 benchmarks | 66.0% | ||||||||||||||
| 210 | GPT-5 (medium)openai/gpt-5:medium | OpenAI | 54.4 | $1.25 / $10.00 | 2 of 15 benchmarks | 71.5% | 1417 | |||||||||||||
| 211 | GLM 4.7z-ai/glm-4.7 | Z.ai | 54.2 | $0.60 / $2.20 | 2 of 15 benchmarks | 1484 | 1435 | |||||||||||||
| 212 | GPT-5.4 Nano (high)openai/gpt-5.4-nano:high | OpenAI | 54.2 | $0.20 / $1.25 | 1 of 15 benchmarks | 1460 | ||||||||||||||
| 213 | Qwen3.6 Plusqwen/qwen3.6-plus | Qwen | 54.1 | $0.325 / $1.95 | 3 of 15 benchmarks | 57.9% | 1496 | 1462 | ||||||||||||
| 214 | Claude Haiku 5.5 (medium)anthropic/claude-haiku-5.5:medium | Anthropic | 54.0 | $0.10 / $0.50 | 1 of 15 benchmarks | 41.6% | ||||||||||||||
| 215 | DeepSeek V3.1 Terminus (thinking)deepseek/deepseek-v3.1-terminus:thinking | DeepSeek | 54.0 | $0.27 / $1.00 | 1 of 15 benchmarks | 1460 | ||||||||||||||
| 216 | GPT-5.2openai/gpt-5.2 | OpenAI | 54.0 | $1.75 / $14.00 | 3 of 15 benchmarks | 69.0% | 1482 | 1420 | ||||||||||||
| 217 | Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b | Qwen | 53.7 | $0.60 / $3.60 | 2 of 15 benchmarks | 1490 | 1400 | |||||||||||||
| 218 | Claude Opus 5 (low)anthropic/claude-opus-5:low | Anthropic | 53.6 | $5.00 / $25.00 | 2 of 15 benchmarks | 58.1% | 42.0% | |||||||||||||
| 219 | GPT 4.5 Previewopenai/gpt-4.5-preview | OpenAI | 53.6 | — | 1 of 15 benchmarks | 1458 | ||||||||||||||
| 220 | GPT-5 Mini (medium)openai/gpt-5-mini:medium | OpenAI | 53.5 | $0.25 / $2.00 | 1 of 15 benchmarks | 64.7% | ||||||||||||||
| 221 | Grok 4 Fastx-ai/grok-4-fast | SpaceXAI | 53.4 | — | 1 of 15 benchmarks | 1458 | ||||||||||||||
| 222 | Qwen3.8 Max (xhigh)qwen/qwen3.8-max:xhigh | Qwen | 53.4 | — | 1 of 15 benchmarks | 57.5% | ||||||||||||||
| 223 | Grok 4.7x-ai/grok-4.7 | SpaceXAI | 53.2 | $2.00 / $6.00 | 1 of 15 benchmarks | 29.5% | ||||||||||||||
| 224 | GPT-5.4 (medium)openai/gpt-5.4:medium | OpenAI | 53.0 | $2.50 / $15.00 | 1 of 15 benchmarks | 1442 | ||||||||||||||
| 225 | Claude 3.5 Haikuanthropic/claude-3-5-haiku | Anthropic | 53.0 | — | 2 of 15 benchmarks | 41.7% | 1386 | |||||||||||||
| 226 | Gemma 4 31Bgoogle/gemma-4-31b-it | 53.0 | $0.20 / $0.40 | 2 of 15 benchmarks | 1502 | 1369 | ||||||||||||||
| 227 | DeepSeek V3.1 (thinking)deepseek/deepseek-chat-v3.1:thinking | DeepSeek | 53.0 | $0.25 / $0.95 | 1 of 15 benchmarks | 1456 | ||||||||||||||
| 228 | GLM 5V Turboz-ai/glm-5v-turbo | Z.ai | 52.9 | $1.20 / $4.00 | 2 of 15 benchmarks | 1488 | 1399 | |||||||||||||
| 229 | Kimi K2 0711moonshotai/kimi-k2 | MoonshotAI | 52.9 | $0.57 / $2.30 | 2 of 15 benchmarks | 65.4% | 1459 | |||||||||||||
| 230 | Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | MoonshotAI | 52.8 | $0.60 / $2.50 | 1 of 15 benchmarks | 63.4% | ||||||||||||||
| 231 | Mistral Medium 2508mistralai/mistral-medium-2508 | Mistral AI | 52.7 | — | 1 of 15 benchmarks | 1454 | ||||||||||||||
| 232 | Claude Opus 4.6 (high)anthropic/claude-opus-4.6:high | Anthropic | 52.7 | $5.00 / $25.00 | 5 of 15 benchmarks | 26.6% | 1547 | 1546 | 26.7% | 24.0 | ||||||||||
| 233 | GPT-5.6 Sol (medium)openai/gpt-5.6-sol:medium | OpenAI | 52.6 | $4.00 / $20.00 | 2 of 15 benchmarks | 61.1% | 39.9% | |||||||||||||
| 234 | Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking | Qwen | 52.5 | — | 1 of 15 benchmarks | 1452 | ||||||||||||||
| 235 | Gemini 3.6 Flash (high)google/gemini-3.6-flash:high | 52.5 | $0.75 / $3.75 | 4 of 15 benchmarks | 46.7% | 33.7% | 1518 | 1538 | ||||||||||||
| 236 | Claude Sonnet 4.5anthropic/claude-sonnet-4.5 | Anthropic | 52.4 | $3.00 / $15.00 | 6 of 15 benchmarks | 71.3% | 44.3% | 67.0% | 2.4% | 1512 | 1385 | |||||||||
| 237 | Claude 3.7 Sonnet (thinking 32K)anthropic/claude-3-7-sonnet:thinking-32k | Anthropic | 52.4 | — | 1 of 15 benchmarks | 1452 | ||||||||||||||
| 238 | DeepSeek V4 Pro 0423 (xhigh)deepseek/deepseek-v4-pro:xhigh | DeepSeek | 52.3 | $0.8837 / $1.7675 | 2 of 15 benchmarks | 26.7% | 30.0 | |||||||||||||
| 239 | Step 3.5 Flashstepfun/step-3.5-flash | StepFun | 52.1 | $0.10 / $0.30 | 1 of 15 benchmarks | 1449 | ||||||||||||||
| 240 | Gemini 3.5 Flash (high)google/gemini-3.5-flash:high | 52.1 | $1.50 / $9.00 | 5 of 15 benchmarks | 79.3% | 36.1% | 4.8% | 1508 | 1500 | |||||||||||
| 241 | o3 (medium)openai/o3:medium | OpenAI | 52.0 | $2.00 / $8.00 | 1 of 15 benchmarks | 62.3% | ||||||||||||||
| 242 | Claude Sonnet 5 (max)anthropic/claude-sonnet-5:max | Anthropic | 52.0 | $2.00 / $10.00 | 2 of 15 benchmarks | 53.9% | 42.4% | |||||||||||||
| 243 | Inkling Smallthinkingmachines/inkling-small | Thinking Machines | 51.9 | $0.45 / $1.20 | 2 of 15 benchmarks | 1472 | 1407 | |||||||||||||
| 244 | DeepSeek V3.1deepseek/deepseek-chat-v3.1 | DeepSeek | 51.9 | $0.25 / $0.95 | 1 of 15 benchmarks | 1447 | ||||||||||||||
| 245 | Claude Opus 4.8 (high)anthropic/claude-opus-4.8:high | Anthropic | 51.9 | $5.00 / $25.00 | 6 of 15 benchmarks | 51.8% | 41.0% | 1534 | 1555 | 24.4% | 24.0 | |||||||||
| 246 | Kimi K3moonshotai/kimi-k3 | MoonshotAI | 51.7 | $0.192 / $16.00 | 1 of 15 benchmarks | 25.9% | ||||||||||||||
| 247 | MiniMax M2.7minimax/minimax-m2.7 | MiniMax | 51.5 | $0.21 / $0.84 | 2 of 15 benchmarks | 1480 | 1398 | |||||||||||||
| 248 | Qwen3 235B A22B (nothinking)qwen/qwen3-235b-a22b:nothinking | Qwen | 51.5 | — | 1 of 15 benchmarks | 1444 | ||||||||||||||
| 249 | Gemini 3 Flash Preview (minimal)google/gemini-3-flash-preview:minimal | 51.5 | $0.50 / $3.00 | 2 of 15 benchmarks | 1490 | 1384 | ||||||||||||||
| 250 | Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct | Qwen | 51.4 | $0.09 / $1.10 | 1 of 15 benchmarks | 1444 | ||||||||||||||
| 251 | R1deepseek/deepseek-r1 | DeepSeek | 51.3 | — | 1 of 15 benchmarks | 1444 | ||||||||||||||
| 252 | Qwen3 235B A22Bqwen/qwen3-235b-a22b | Qwen | 51.2 | — | 2 of 15 benchmarks | 65.9% | 1432 | |||||||||||||
| 253 | Trinity Large Previewarcee-ai/trinity-large-preview | Arcee AI | 51.2 | — | 1 of 15 benchmarks | 1443 | ||||||||||||||
| 254 | Grok 3 Betax-ai/grok-3-beta | SpaceXAI | 51.0 | — | 1 of 15 benchmarks | 1442 | ||||||||||||||
| 255 | Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507 | Qwen | 50.9 | $0.45 / $3.50 | 1 of 15 benchmarks | 1442 | ||||||||||||||
| 256 | DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus | DeepSeek | 50.8 | $0.27 / $1.00 | 1 of 15 benchmarks | 1440 | ||||||||||||||
| 257 | o3 Mini (low)openai/o3-mini:low | OpenAI | 50.6 | — | 1 of 15 benchmarks | 57.0% | ||||||||||||||
| 258 | Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | Qwen | 50.6 | $0.10 / $0.30 | 1 of 15 benchmarks | 1438 | ||||||||||||||
| 259 | GPT-5.2 (xhigh)openai/gpt-5.2:xhigh | OpenAI | 50.3 | $1.75 / $14.00 | 1 of 15 benchmarks | 23.0% | ||||||||||||||
| 260 | Hunyuan Vision 1.5 (thinking)tencent/hunyuan-vision-1.5:thinking | Tencent | 50.3 | — | 1 of 15 benchmarks | 1436 | ||||||||||||||
| 261 | Muse Spark 1.3meta/muse-spark-1.3 | Meta | 50.3 | $1.25 / $4.25 | 1 of 15 benchmarks | 25.8% | ||||||||||||||
| 262 | Grok 4.5 (low)x-ai/grok-4.5:low | SpaceXAI | 50.3 | $2.00 / $6.00 | 1 of 15 benchmarks | 37.9% | ||||||||||||||
| 263 | Grok 3 Mini Beta (high)x-ai/grok-3-mini-beta:high | SpaceXAI | 50.2 | — | 2 of 15 benchmarks | 66.7% | 1392 | |||||||||||||
| 264 | Claude Opus 4.1anthropic/claude-opus-4.1 | Anthropic | 50.1 | $15.00 / $75.00 | 4 of 15 benchmarks | 73.3% | 7.9% | 1505 | 1389 | |||||||||||
| 265 | GPT-6 Sol (low)openai/gpt-6-sol:low | OpenAI | 50.0 | $2.00 / $10.00 | 1 of 15 benchmarks | 37.3% | ||||||||||||||
| 266 | Claude Opus 4anthropic/claude-opus-4 | Anthropic | 50.0 | — | 3 of 15 benchmarks | 70.7% | 46.9% | 1465 | ||||||||||||
| 267 | Grok 4 0709x-ai/grok-4-0709 | SpaceXAI | 50.0 | — | 1 of 15 benchmarks | 1435 | ||||||||||||||
| 268 | GPT-5.3-Codexopenai/gpt-5.3-codex | OpenAI | 49.8 | $1.75 / $14.00 | 1 of 15 benchmarks | 1406 | ||||||||||||||
| 269 | GPT-6 Luna (high)openai/gpt-6-luna:high | OpenAI | 49.8 | $0.10 / $0.50 | 1 of 15 benchmarks | 37.3% | ||||||||||||||
| 270 | Grok 4.3x-ai/grok-4.3 | SpaceXAI | 49.6 | $1.25 / $2.50 | 2 of 15 benchmarks | 1487 | 1357 | |||||||||||||
| 271 | Claude Sonnet 5 (xhigh)anthropic/claude-sonnet-5:xhigh | Anthropic | 49.6 | $2.00 / $10.00 | 2 of 15 benchmarks | 49.7% | 42.7% | |||||||||||||
| 272 | Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 49.6 | $0.0765 / $0.255 | 2 of 15 benchmarks | 1483 | 1359 | ||||||||||||||
| 273 | GPT-6 Luna (xhigh)openai/gpt-6-luna:xhigh | OpenAI | 49.5 | $0.10 / $0.50 | 1 of 15 benchmarks | 37.1% | ||||||||||||||
| 274 | Gemini 2.5 Progoogle/gemini-2.5-pro | 49.3 | $1.25 / $10.00 | 4 of 15 benchmarks | 57.6% | 73.6% | 1464 | 1228 | ||||||||||||
| 275 | Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl | NVIDIA | 49.3 | $0.15 / $0.47 | 2 of 15 benchmarks | 1460 | 1399 | |||||||||||||
| 276 | Claude Opus 4 (thinking)anthropic/claude-opus-4:thinking | Anthropic | 49.3 | — | 1 of 15 benchmarks | 56.6% | ||||||||||||||
| 277 | o4 Miniopenai/o4-mini | OpenAI | 49.2 | — | 3 of 15 benchmarks | 45.0% | 33.9% | 1433 | ||||||||||||
| 278 | Mistral Medium 2505mistralai/mistral-medium-2505 | Mistral AI | 49.2 | — | 1 of 15 benchmarks | 1433 | ||||||||||||||
| 279 | GPT-5 Mini (high)openai/gpt-5-mini:high | OpenAI | 49.1 | $0.25 / $2.00 | 1 of 15 benchmarks | 1432 | ||||||||||||||
| 280 | Devstral Small 2512mistralai/devstral-small-2512 | Mistral AI | 49.0 | — | 1 of 15 benchmarks | 56.4% | ||||||||||||||
| 281 | o1openai/o1 | OpenAI | 49.0 | — | 2 of 15 benchmarks | 64.6% | 1433 | |||||||||||||
| 282 | GPT-5.1 (medium)openai/gpt-5.1:medium | OpenAI | 48.9 | $1.25 / $10.00 | 2 of 15 benchmarks | 66.0% | 1397 | |||||||||||||
| 283 | Grok 4.6x-ai/grok-4.6 | SpaceXAI | 48.9 | $2.00 / $6.00 | 1 of 15 benchmarks | 25.3% | ||||||||||||||
| 284 | DeepSeek V4 Flash 0423 (max)deepseek/deepseek-v4-flash:max | DeepSeek | 48.8 | $0.091 / $0.182 | 1 of 15 benchmarks | 53.3% | ||||||||||||||
| 285 | Muse Spark 1.1 (xhigh)meta/muse-spark-1.1:xhigh | Meta | 48.8 | $1.25 / $4.25 | 1 of 15 benchmarks | 53.3% | ||||||||||||||
| 286 | MiniMax M2.5minimax/minimax-m2.5 | MiniMax | 48.7 | $0.30 / $1.20 | 3 of 15 benchmarks | 68.3% | 1447 | 1386 | ||||||||||||
| 287 | Ernie 5.0 Preview 1022baidu/ernie-5.0-preview-1022 | Baidu | 48.6 | — | 1 of 15 benchmarks | 1431 | ||||||||||||||
| 288 | Muse Glimmer 30Bmeta/muse-glimmer-30b | Meta | 48.6 | $0.30 / $1.20 | 2 of 15 benchmarks | 1480 | 1355 | |||||||||||||
| 289 | Claude Sonnet 5.5 (medium)anthropic/claude-sonnet-5.5:medium | Anthropic | 48.5 | $2.00 / $10.00 | 1 of 15 benchmarks | 36.5% | ||||||||||||||
| 290 | DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 | DeepSeek | 48.5 | $0.29 / $1.14 | 1 of 15 benchmarks | 1428 | ||||||||||||||
| 291 | GLM 5.3 Flash (max)z-ai/glm-5.3-flash:max | Z.ai | 48.5 | $0.15 / $0.50 | 2 of 15 benchmarks | 63.4% | 31.8% | |||||||||||||
| 292 | Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning-30b-a3b | NVIDIA | 48.4 | — | 1 of 15 benchmarks | 1428 | ||||||||||||||
| 293 | GLM 4.5 Airz-ai/glm-4.5-air | Z.ai | 48.3 | $0.20 / $1.10 | 1 of 15 benchmarks | 1427 | ||||||||||||||
| 294 | Claude 3.5 Sonnetanthropic/claude-3-5-sonnet | Anthropic | 48.3 | — | 6 of 15 benchmarks | 62.8% | 51.3% | 24.9% | 25.3% | 36.4% | 1436 | |||||||||
| 295 | Claude Sonnet 5anthropic/claude-sonnet-5 | Anthropic | 48.1 | $2.00 / $10.00 | 2 of 15 benchmarks | 25.6% | 27.0 | |||||||||||||
| 296 | GLM 4.7 Flashz-ai/glm-4.7-flash | Z.ai | 48.0 | $0.0605 / $0.40 | 1 of 15 benchmarks | 1423 | ||||||||||||||
| 297 | GPT-6 Luna (medium)openai/gpt-6-luna:medium | OpenAI | 48.0 | $0.10 / $0.50 | 1 of 15 benchmarks | 35.5% | ||||||||||||||
| 298 | Claude Sonnet 4 (thinking)anthropic/claude-sonnet-4:thinking | Anthropic | 47.9 | — | 1 of 15 benchmarks | 56.0% | ||||||||||||||
| 299 | Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking | Qwen | 47.9 | — | 1 of 15 benchmarks | 1421 | ||||||||||||||
| 300 | GPT-5.1openai/gpt-5.1 | OpenAI | 47.8 | $1.25 / $10.00 | 2 of 15 benchmarks | 1475 | 1342 | |||||||||||||
| 301 | Kimi K2 Thinking Turbomoonshotai/kimi-k2-thinking-turbo | Moonshot AI | 47.7 | — | 2 of 15 benchmarks | 1486 | 1322 | |||||||||||||
| 302 | MiniMax M1minimax/minimax-m1 | MiniMax | 47.7 | — | 1 of 15 benchmarks | 1416 | ||||||||||||||
| 303 | DeepSeek V3.2 (thinking)deepseek/deepseek-v3.2:thinking | DeepSeek | 47.6 | $0.26 / $0.38 | 3 of 15 benchmarks | 60.0% | 1476 | 1363 | ||||||||||||
| 304 | GLM 4.5z-ai/glm-4.5 | Z.ai | 47.6 | $0.60 / $2.20 | 2 of 15 benchmarks | 54.2% | 1455 | |||||||||||||
| 305 | GLM 4.6Vz-ai/glm-4.6v | Z.ai | 47.6 | $0.30 / $0.90 | 1 of 15 benchmarks | 1416 | ||||||||||||||
| 306 | Solar Pro 4upstage/solar-pro4 | Upstage | 47.5 | $0.15 / $0.60 | 2 of 15 benchmarks | 1462 | 1369 | |||||||||||||
| 307 | INTELLECT-3prime-intellect/intellect-3 | Prime Intellect | 47.4 | — | 1 of 15 benchmarks | 1415 | ||||||||||||||
| 308 | Gemini 3.7 Flashgoogle/gemini-3.7-flash | 47.4 | $0.75 / $3.75 | 1 of 15 benchmarks | 20.3% | |||||||||||||||
| 309 | Claude Opus 4.5 (128K)anthropic/claude-opus-4.5:128k | Anthropic | 47.4 | $5.00 / $25.00 | 1 of 15 benchmarks | 14.3% | ||||||||||||||
| 310 | GPT-5.5 (medium)openai/gpt-5.5:medium | OpenAI | 47.3 | $5.00 / $30.00 | 2 of 15 benchmarks | 54.0% | 36.6% | |||||||||||||
| 311 | Mistral Small 2506mistralai/mistral-small-2506 | Mistral AI | 47.2 | — | 1 of 15 benchmarks | 1412 | ||||||||||||||
| 312 | Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct | Qwen | 47.1 | $0.15 / $0.60 | 1 of 15 benchmarks | 51.6% | ||||||||||||||
| 313 | Step 3stepfun/step-3 | StepFun | 47.1 | — | 1 of 15 benchmarks | 1409 | ||||||||||||||
| 314 | Ling Flash 2.0inclusionai/ling-flash-2.0 | inclusionAI | 47.0 | — | 1 of 15 benchmarks | 1409 | ||||||||||||||
| 315 | Grok 4.1 (thinking)x-ai/grok-4.1:thinking | SpaceXAI | 46.9 | — | 2 of 15 benchmarks | 1500 | 1217 | |||||||||||||
| 316 | Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b | NVIDIA | 46.9 | $0.075 / $0.40 | 1 of 15 benchmarks | 1407 | ||||||||||||||
| 317 | Claude Opus 4.7 (xhigh)anthropic/claude-opus-4.7:xhigh | Anthropic | 46.8 | $5.00 / $25.00 | 1 of 15 benchmarks | 34.9% | ||||||||||||||
| 318 | Qwen3 32Bqwen/qwen3-32b | Qwen | 46.7 | $0.08 / $0.28 | 1 of 15 benchmarks | 1406 | ||||||||||||||
| 319 | Llama 3.3 Nemotron Super 49B v1.5nvidia/llama-3.3-nemotron-super-49b-v1.5 | NVIDIA | 46.6 | — | 1 of 15 benchmarks | 1404 | ||||||||||||||
| 320 | GPT-5.4 (xhigh)openai/gpt-5.4:xhigh | OpenAI | 46.6 | $2.50 / $15.00 | 2 of 15 benchmarks | 51.8% | 25.4% | |||||||||||||
| 321 | Claude Haiku 5.5 (low)anthropic/claude-haiku-5.5:low | Anthropic | 46.5 | $0.10 / $0.50 | 1 of 15 benchmarks | 34.8% | ||||||||||||||
| 322 | Gemini 3.7 Flash (low)google/gemini-3.7-flash:low | 46.5 | $0.75 / $3.75 | 2 of 15 benchmarks | 53.8% | 36.9% | ||||||||||||||
| 323 | Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b | Qwen | 46.5 | $0.26 / $2.08 | 2 of 15 benchmarks | 1458 | 1360 | |||||||||||||
| 324 | GLM 4.5Vz-ai/glm-4.5v | Z.ai | 46.5 | $0.60 / $1.80 | 1 of 15 benchmarks | 1403 | ||||||||||||||
| 325 | Qwen 2.5 (max)qwen/qwen-2.5:max | Qwen | 46.4 | — | 1 of 15 benchmarks | 1401 | ||||||||||||||
| 326 | GPT-5.6 Terra (high)openai/gpt-5.6-terra:high | OpenAI | 46.3 | $2.00 / $12.00 | 2 of 15 benchmarks | 53.8% | 36.9% | |||||||||||||
| 327 | Devstral Small 2505mistralai/devstral-small-2505 | Mistral AI | 46.3 | — | 1 of 15 benchmarks | 46.8% | ||||||||||||||
| 328 | GPT-5.5 (low)openai/gpt-5.5:low | OpenAI | 46.3 | $5.00 / $30.00 | 4 of 15 benchmarks | 27.0% | 30.6% | 32.6% | 38.0 | |||||||||||
| 329 | Gemini 3.6 Flash (medium)google/gemini-3.6-flash:medium | 46.3 | $0.75 / $3.75 | 1 of 15 benchmarks | 34.4% | |||||||||||||||
| 330 | Hunyuan T1tencent/hunyuan-t1 | Tencent | 46.3 | — | 1 of 15 benchmarks | 1401 | ||||||||||||||
| 331 | Hunyuan TurboStencent/hunyuan-turbos | Tencent | 46.1 | — | 1 of 15 benchmarks | 1399 | ||||||||||||||
| 332 | GPT-4.1openai/gpt-4.1 | OpenAI | 46.1 | $2.00 / $8.00 | 3 of 15 benchmarks | 48.5% | 31.1% | 1456 | ||||||||||||
| 333 | Granite 4.2 30Bibm-granite/granite-4.2-30b | IBM | 46.0 | — | 1 of 15 benchmarks | 1398 | ||||||||||||||
| 334 | Gemini 3.8 Flashgoogle/gemini-3.8-flash | 46.0 | $0.75 / $3.75 | 1 of 15 benchmarks | 19.6% | |||||||||||||||
| 335 | Gemini 2.5 Flash Lite (nothinking)google/gemini-2.5-flash-lite:nothinking | 45.9 | $0.10 / $0.40 | 1 of 15 benchmarks | 1397 | |||||||||||||||
| 336 | Qwen3 Coder 480B A35b Instructqwen/qwen3-coder-480b-a35b-instruct | Qwen | 45.9 | — | 3 of 15 benchmarks | 69.6% | 1457 | 1275 | ||||||||||||
| 337 | Mistral Medium 3.5mistralai/mistral-medium-3-5 | Mistral | 45.8 | $1.50 / $7.50 | 2 of 15 benchmarks | 1478 | 1262 | |||||||||||||
| 338 | Nova 2 Liteamazon/nova-2-lite-v1 | Amazon | 45.8 | $0.30 / $2.50 | 1 of 15 benchmarks | 1393 | ||||||||||||||
| 339 | Kimi K2 Instructmoonshotai/kimi-k2-instruct | Moonshot AI | 45.6 | — | 1 of 15 benchmarks | 43.8% | ||||||||||||||
| 340 | Llama 3.1 Nemotron Ultra 253B v1nvidia/llama-3.1-nemotron-ultra-253b-v1 | NVIDIA | 45.4 | — | 1 of 15 benchmarks | 1391 | ||||||||||||||
| 341 | o3 Miniopenai/o3-mini | OpenAI | 45.3 | — | 4 of 15 benchmarks | 42.4% | 32.3% | 63.0% | 1417 | |||||||||||
| 342 | Ring Flash 2.0inclusionai/ring-flash-2.0 | inclusionAI | 45.3 | — | 1 of 15 benchmarks | 1390 | ||||||||||||||
| 343 | Hy3 previewtencent/hy3-preview | Tencent | 45.3 | $0.18 / $0.60 | 2 of 15 benchmarks | 1452 | 1359 | |||||||||||||
| 344 | GPT-5.4 Mini (high)openai/gpt-5.4-mini:high | OpenAI | 45.1 | $0.75 / $4.50 | 3 of 15 benchmarks | 23.1% | 1495 | 1398 | ||||||||||||
| 345 | Command A (03-2025)cohere/command-a-03-2025 | Cohere | 45.1 | — | 1 of 15 benchmarks | 1388 | ||||||||||||||
| 346 | MiniMax M2.1minimax/minimax-m2.1 | MiniMax | 45.0 | — | 2 of 15 benchmarks | 1437 | 1384 | |||||||||||||
| 347 | Nova Premier 1.0amazon/nova-premier-v1 | Amazon | 45.0 | $2.50 / $12.50 | 1 of 15 benchmarks | 42.4% | ||||||||||||||
| 348 | Kimi K2.7 Code (none)moonshotai/kimi-k2.7-code:none | MoonshotAI | 45.0 | $0.60 / $3.50 | 1 of 15 benchmarks | 30.1% | ||||||||||||||
| 349 | Claude Opus 4.6 (max)anthropic/claude-opus-4.6:max | Anthropic | 45.0 | $5.00 / $25.00 | 1 of 15 benchmarks | 12.7% | ||||||||||||||
| 350 | Magistral Medium 2506mistralai/magistral-medium-2506 | Mistral AI | 44.9 | — | 1 of 15 benchmarks | 1387 | ||||||||||||||
| 351 | GPT-5.2-Codexopenai/gpt-5.2-codex | OpenAI | 44.8 | $1.75 / $14.00 | 3 of 15 benchmarks | 72.8% | 66.3% | 1338 | ||||||||||||
| 352 | Claude Sonnet 5.5 (low)anthropic/claude-sonnet-5.5:low | Anthropic | 44.8 | $2.00 / $10.00 | 1 of 15 benchmarks | 29.3% | ||||||||||||||
| 353 | Qwen3.5-27Bqwen/qwen3.5-27b | Qwen | 44.8 | $0.26 / $2.60 | 2 of 15 benchmarks | 1451 | 1357 | |||||||||||||
| 354 | Grok 3 Mini Betax-ai/grok-3-mini-beta | SpaceXAI | 44.7 | — | 1 of 15 benchmarks | 1386 | ||||||||||||||
| 355 | O1 Miniopenai/o1-mini | OpenAI | 44.6 | — | 1 of 15 benchmarks | 1386 | ||||||||||||||
| 356 | DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp | DeepSeek | 44.5 | $0.27 / $0.41 | 2 of 15 benchmarks | 1467 | 1270 | |||||||||||||
| 357 | GPT-5 Nano (high)openai/gpt-5-nano:high | OpenAI | 44.3 | $0.05 / $0.40 | 1 of 15 benchmarks | 1385 | ||||||||||||||
| 358 | Qwen3 30B A3Bqwen/qwen3-30b-a3b | Qwen | 44.2 | $0.12 / $0.50 | 1 of 15 benchmarks | 1385 | ||||||||||||||
| 359 | Laguna M.1poolside/laguna-m.1 | Poolside | 44.1 | — | 1 of 15 benchmarks | 1349 | ||||||||||||||
| 360 | GPT-5 (high)openai/gpt-5:high | OpenAI | 44.0 | $1.25 / $10.00 | 4 of 15 benchmarks | 73.5% | 4.4% | 12.7% | 1471 | |||||||||||
| 361 | DeepSeek V4 Pro 0813 (high)deepseek/deepseek-v4-pro-0813:high | DeepSeek | 44.0 | $0.111 / $4.44 | 1 of 15 benchmarks | 28.6% | ||||||||||||||
| 362 | Grok 4.6 (low)x-ai/grok-4.6:low | SpaceXAI | 44.0 | $2.00 / $6.00 | 2 of 15 benchmarks | 41.6% | 40.1% | |||||||||||||
| 363 | Gemini 2.5 Flash Lite (thinking)google/gemini-2.5-flash-lite:thinking | 44.0 | $0.10 / $0.40 | 1 of 15 benchmarks | 1383 | |||||||||||||||
| 364 | QwQ 32Bqwen/qwq-32b | Qwen | 43.9 | — | 1 of 15 benchmarks | 1382 | ||||||||||||||
| 365 | Claude Opus 4.7 (low)anthropic/claude-opus-4.7:low | Anthropic | 43.8 | $5.00 / $25.00 | 1 of 15 benchmarks | 27.6% | ||||||||||||||
| 366 | OLMo 3.1 32B Instructallenai/olmo-3.1-32b-instruct | Allen Institute for AI | 43.7 | — | 1 of 15 benchmarks | 1381 | ||||||||||||||
| 367 | Qwen-Plusqwen/qwen-plus | Qwen | 43.6 | $0.26 / $0.78 | 1 of 15 benchmarks | 1378 | ||||||||||||||
| 368 | Kimi K2.7 Codemoonshotai/kimi-k2.7-code | MoonshotAI | 43.5 | $0.60 / $3.50 | 2 of 15 benchmarks | 30.5% | 1474 | |||||||||||||
| 369 | GPT-5.4 Mini (xhigh)openai/gpt-5.4-mini:xhigh | OpenAI | 43.5 | $0.75 / $4.50 | 1 of 15 benchmarks | 27.0% | ||||||||||||||
| 370 | Granite 4.2 3Bibm-granite/granite-4.2-3b | IBM | 43.5 | — | 1 of 15 benchmarks | 1377 | ||||||||||||||
| 371 | GPT-4.1 Nanoopenai/gpt-4.1-nano | OpenAI | 43.4 | $0.10 / $0.40 | 1 of 15 benchmarks | 1373 | ||||||||||||||
| 372 | Mistral Large 3mistralai/mistral-large-3 | Mistral AI | 43.3 | — | 2 of 15 benchmarks | 1471 | 1233 | |||||||||||||
| 373 | Devstral Small 2507mistralai/devstral-small-2507 | Mistral AI | 43.3 | — | 1 of 15 benchmarks | 38.0% | ||||||||||||||
| 374 | DeepSeek V4 Flash 0423 (xhigh)deepseek/deepseek-v4-flash:xhigh | DeepSeek | 43.2 | $0.091 / $0.182 | 2 of 15 benchmarks | 20.9% | 27.0 | |||||||||||||
| 375 | GPT-5.1-Codexopenai/gpt-5.1-codex | OpenAI | 43.2 | $1.25 / $10.00 | 1 of 15 benchmarks | 1338 | ||||||||||||||
| 376 | Mimo v2 Flashxiaomi/mimo-v2-flash | Xiaomi | 43.1 | — | 2 of 15 benchmarks | 1447 | 1331 | |||||||||||||
| 377 | gpt-oss-20bopenai/gpt-oss-20b | OpenAI | 43.0 | $0.03 / $0.13 | 1 of 15 benchmarks | 1368 | ||||||||||||||
| 378 | GPT-5 Nano (medium)openai/gpt-5-nano:medium | OpenAI | 42.9 | $0.05 / $0.40 | 1 of 15 benchmarks | 34.8% | ||||||||||||||
| 379 | Granite 4.2 8Bibm-granite/granite-4.2-8b | IBM | 42.9 | $0.06 / $0.25 | 1 of 15 benchmarks | 1366 | ||||||||||||||
| 380 | Mercuryinception/mercury | Inception | 42.8 | — | 1 of 15 benchmarks | 1364 | ||||||||||||||
| 381 | GPT-6 Luna (low)openai/gpt-6-luna:low | OpenAI | 42.8 | $0.10 / $0.50 | 1 of 15 benchmarks | 25.7% | ||||||||||||||
| 382 | GLM 4.6z-ai/glm-4.6 | Z.ai | 42.6 | $0.50 / $2.00 | 3 of 15 benchmarks | 55.4% | 1458 | 1342 | ||||||||||||
| 383 | Grok 4.1 Fast (reasoning)x-ai/grok-4-1-fast:reasoning | SpaceXAI | 42.6 | — | 2 of 15 benchmarks | 1461 | 1242 | |||||||||||||
| 384 | GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | OpenAI | 42.6 | $2.50 / $10.00 | 1 of 15 benchmarks | 31.0% | ||||||||||||||
| 385 | Composer 2.5 (none)cursor/composer-2.5:none | Cursor | 42.5 | — | 1 of 15 benchmarks | 25.6% | ||||||||||||||
| 386 | Llama 3.3 Nemotron Super 49B v1nvidia/llama-3.3-nemotron-super-49b-v1 | NVIDIA | 42.4 | — | 1 of 15 benchmarks | 1362 | ||||||||||||||
| 387 | Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | 42.4 | $0.25 / $1.50 | 2 of 15 benchmarks | 1457 | 1256 | ||||||||||||||
| 388 | Mistral Small 3.1 24B Instruct 2503mistralai/mistral-small-3.1-24b-instruct-2503 | Mistral AI | 42.3 | — | 1 of 15 benchmarks | 1361 | ||||||||||||||
| 389 | GLM 5.2 (none)z-ai/glm-5.2:none | Z.ai | 42.3 | $0.006 / $6.80 | 1 of 15 benchmarks | 24.5% | ||||||||||||||
| 390 | Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | NVIDIA | 42.2 | $0.06 / $0.24 | 1 of 15 benchmarks | 1361 | ||||||||||||||
| 391 | Laguna XS.2poolside/laguna-xs.2 | Poolside | 42.0 | — | 1 of 15 benchmarks | 1303 | ||||||||||||||
| 392 | Claude Sonnet 4.6 (max)anthropic/claude-sonnet-4.6:max | Anthropic | 42.0 | $3.00 / $15.00 | 1 of 15 benchmarks | 24.3% | ||||||||||||||
| 393 | OLMo 3 32B Thinkallenai/olmo-3-32b-think | Allen Institute for AI | 41.9 | — | 1 of 15 benchmarks | 1360 | ||||||||||||||
| 394 | Hunyuan Large Visiontencent/hunyuan-large-vision | Tencent | 41.8 | — | 1 of 15 benchmarks | 1358 | ||||||||||||||
| 395 | GPT-5.6 Sol (low)openai/gpt-5.6-sol:low | OpenAI | 41.7 | $4.00 / $20.00 | 2 of 15 benchmarks | 45.4% | 35.4% | |||||||||||||
| 396 | Gemma 3 27Bgoogle/gemma-3-27b-it | 41.7 | $0.08 / $0.45 | 1 of 15 benchmarks | 1358 | |||||||||||||||
| 397 | Gemini 1.5 Pro 002google/gemini-1.5-pro-002 | 41.6 | — | 1 of 15 benchmarks | 1356 | |||||||||||||||
| 398 | Claude Opus 4.6 (medium)anthropic/claude-opus-4.6:medium | Anthropic | 41.5 | $5.00 / $25.00 | 1 of 15 benchmarks | 23.7% | ||||||||||||||
| 399 | GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13 | OpenAI | 41.4 | $5.00 / $15.00 | 4 of 15 benchmarks | 38.8% | 31.3% | 12.0% | 1369 | |||||||||||
| 400 | Claude Haiku 4.5anthropic/claude-haiku-4.5 | Anthropic | 41.3 | $1.00 / $5.00 | 3 of 15 benchmarks | 64.7% | 1481 | 1330 | ||||||||||||
| 401 | Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct | Qwen | 41.3 | $0.36 / $0.40 | 1 of 15 benchmarks | 1355 | ||||||||||||||
| 402 | Mistral Large 2407mistralai/mistral-large-2407 | Mistral | 41.2 | $2.00 / $6.00 | 1 of 15 benchmarks | 1354 | ||||||||||||||
| 403 | Qwen (max)qwen/qwen:max | Qwen | 41.0 | — | 1 of 15 benchmarks | 1352 | ||||||||||||||
| 404 | Step 1o Turbo 202506stepfun/step-1o-turbo-202506 | StepFun | 40.8 | — | 1 of 15 benchmarks | 1351 | ||||||||||||||
| 405 | Gemini 3.6 Flash (low)google/gemini-3.6-flash:low | 40.8 | $0.75 / $3.75 | 1 of 15 benchmarks | 22.8% | |||||||||||||||
| 406 | KAT-Coder-Pro V1kwaipilot/kat-coder-pro-v1 | Kwaipilot | 40.7 | — | 1 of 15 benchmarks | 1257 | ||||||||||||||
| 407 | Gemini 2.5 Flashgoogle/gemini-2.5-flash | 40.6 | $0.30 / $2.50 | 3 of 15 benchmarks | 28.7% | 61.9% | 1424 | |||||||||||||
| 408 | DeepSeek V3deepseek/deepseek-chat | DeepSeek | 40.5 | $0.32 / $0.89 | 3 of 15 benchmarks | 36.7% | 27.2% | 1387 | ||||||||||||
| 409 | Claude Sonnet 4.6 (medium)anthropic/claude-sonnet-4.6:medium | Anthropic | 40.5 | $3.00 / $15.00 | 1 of 15 benchmarks | 21.1% | ||||||||||||||
| 410 | Gemini 1.5 Pro 001google/gemini-1.5-pro-001 | 40.5 | — | 1 of 15 benchmarks | 1346 | |||||||||||||||
| 411 | Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct | Meta | 40.4 | $0.59 / $0.79 | 1 of 15 benchmarks | 1346 | ||||||||||||||
| 412 | GPT-5.4 Mini (medium)openai/gpt-5.4-mini:medium | OpenAI | 40.3 | $0.75 / $4.50 | 1 of 15 benchmarks | 20.8% | ||||||||||||||
| 413 | Mistral Large 2411mistralai/mistral-large-2411 | Mistral AI | 40.3 | — | 1 of 15 benchmarks | 1346 | ||||||||||||||
| 414 | Qwen 2.5qwen/qwen-2.5 | Qwen | 40.2 | — | 2 of 15 benchmarks | 40.2% | 24.7% | |||||||||||||
| 415 | DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp | DeepSeek | 40.2 | $0.44 / $1.32 | 1 of 15 benchmarks | 14.8% | ||||||||||||||
| 416 | Amazon Nova Pro v1.0amazon/amazon-nova-pro-v1.0 | Amazon | 40.1 | — | 1 of 15 benchmarks | 1343 | ||||||||||||||
| 417 | Mimo v2 Flash (thinking)xiaomi/mimo-v2-flash:thinking | Xiaomi | 40.1 | — | 2 of 15 benchmarks | 1432 | 1292 | |||||||||||||
| 418 | DeepSeek V4 Flash 0731 (high)deepseek/deepseek-v4-flash-0731:high | DeepSeek | 40.0 | $0.0434 / $0.30 | 1 of 15 benchmarks | 18.8% | ||||||||||||||
| 419 | Gemini 2.0 Flash Lite Preview 02 05google/gemini-2.0-flash-lite-preview-02-05 | 40.0 | — | 1 of 15 benchmarks | 1342 | |||||||||||||||
| 420 | GPT-4.1 Miniopenai/gpt-4.1-mini | OpenAI | 40.0 | $0.40 / $1.60 | 2 of 15 benchmarks | 23.9% | 1433 | |||||||||||||
| 421 | GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini | OpenAI | 40.0 | $0.25 / $2.00 | 1 of 15 benchmarks | 1245 | ||||||||||||||
| 422 | Claude Opus 4.6 (low)anthropic/claude-opus-4.6:low | Anthropic | 39.8 | $5.00 / $25.00 | 1 of 15 benchmarks | 18.3% | ||||||||||||||
| 423 | Claude Sonnet 5 (medium)anthropic/claude-sonnet-5:medium | Anthropic | 39.7 | $2.00 / $10.00 | 2 of 15 benchmarks | 39.8% | 35.2% | |||||||||||||
| 424 | Claude Opus 4.8 (low)anthropic/claude-opus-4.8:low | Anthropic | 39.7 | $5.00 / $25.00 | 2 of 15 benchmarks | 40.8% | 35.1% | |||||||||||||
| 425 | OLMo 3.1 32B Thinkallenai/olmo-3.1-32b-think | Allen Institute for AI | 39.6 | — | 1 of 15 benchmarks | 1339 | ||||||||||||||
| 426 | Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b | Qwen | 39.6 | $0.14 / $1.00 | 2 of 15 benchmarks | 1435 | 1253 | |||||||||||||
| 427 | Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct | Meta | 39.5 | — | 1 of 15 benchmarks | 1333 | ||||||||||||||
| 428 | DeepSeek V4 Pro 0423 (none)deepseek/deepseek-v4-pro:none | DeepSeek | 39.5 | $0.8837 / $1.7675 | 1 of 15 benchmarks | 17.6% | ||||||||||||||
| 429 | Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | Qwen | 39.5 | $0.065 / $0.26 | 2 of 15 benchmarks | 1436 | 1244 | |||||||||||||
| 430 | GPT-4openai/gpt-4 | OpenAI | 39.4 | $30.00 / $60.00 | 1 of 15 benchmarks | 1330 | ||||||||||||||
| 431 | Claude 3 Sonnetanthropic/claude-3-sonnet | Anthropic | 39.3 | — | 1 of 15 benchmarks | 1318 | ||||||||||||||
| 432 | Gemini 1.5 Flash 002google/gemini-1.5-flash-002 | 39.2 | — | 1 of 15 benchmarks | 1316 | |||||||||||||||
| 433 | Gemma 3 12Bgoogle/gemma-3-12b-it | 39.1 | $0.05 / $0.15 | 1 of 15 benchmarks | 1316 | |||||||||||||||
| 434 | Claude Sonnet 4.6 (low)anthropic/claude-sonnet-4.6:low | Anthropic | 39.0 | $3.00 / $15.00 | 1 of 15 benchmarks | 15.0% | ||||||||||||||
| 435 | Mistral Small 24B Instruct 2501mistralai/mistral-small-24b-instruct-2501 | Mistral AI | 38.9 | — | 1 of 15 benchmarks | 1312 | ||||||||||||||
| 436 | Gemini 1.5 Flash 001google/gemini-1.5-flash-001 | 38.8 | — | 1 of 15 benchmarks | 1309 | |||||||||||||||
| 437 | MiniMax M3 (none)minimax/minimax-m3:none | MiniMax | 38.8 | $0.30 / $1.20 | 1 of 15 benchmarks | 14.7% | ||||||||||||||
| 438 | GPT 4 1106 Previewopenai/gpt-4-1106-preview | OpenAI | 38.7 | — | 4 of 15 benchmarks | 22.4% | 28.3% | 12.5% | 1340 | |||||||||||
| 439 | Muse Spark 1.2meta/muse-spark-1.2 | Meta | 38.7 | $1.25 / $4.25 | 1 of 15 benchmarks | 12.0% | ||||||||||||||
| 440 | Gemma 3n E4Bgoogle/gemma-3n-e4b-it | 38.7 | — | 1 of 15 benchmarks | 1307 | |||||||||||||||
| 441 | Amazon Nova Lite v1.0amazon/amazon-nova-lite-v1.0 | Amazon | 38.6 | — | 1 of 15 benchmarks | 1305 | ||||||||||||||
| 442 | Mistral Largemistralai/mistral-large | Mistral | 38.3 | $2.00 / $6.00 | 1 of 15 benchmarks | 1296 | ||||||||||||||
| 443 | Nemotron 3 Ultra (none)nvidia/nemotron-3-ultra-550b-a55b:none | NVIDIA | 38.3 | $0.60 / $2.40 | 1 of 15 benchmarks | 13.6% | ||||||||||||||
| 444 | DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek | 38.3 | $0.26 / $0.38 | 3 of 15 benchmarks | 59.0% | 1469 | 1326 | ||||||||||||
| 445 | Amazon Nova Micro v1.0amazon/amazon-nova-micro-v1.0 | Amazon | 38.2 | — | 1 of 15 benchmarks | 1288 | ||||||||||||||
| 446 | Grok 4 Fast (reasoning)x-ai/grok-4-fast:reasoning | SpaceXAI | 38.2 | — | 2 of 15 benchmarks | 1439 | 1162 | |||||||||||||
| 447 | Command R (08-2024)cohere/command-r-08-2024 | Cohere | 38.1 | $0.15 / $0.60 | 1 of 15 benchmarks | 1281 | ||||||||||||||
| 448 | Qwen3.7 Plus (none)qwen/qwen3.7-plus:none | Qwen | 38.0 | $0.32 / $1.28 | 1 of 15 benchmarks | 10.2% | ||||||||||||||
| 449 | Command R+ (08-2024)cohere/command-r-plus-08-2024 | Cohere | 38.0 | $2.50 / $10.00 | 1 of 15 benchmarks | 1280 | ||||||||||||||
| 450 | OLMo 2 0325 32B Instructallenai/olmo-2-0325-32b-instruct | Allen Institute for AI | 37.9 | — | 1 of 15 benchmarks | 1280 | ||||||||||||||
| 451 | MiniMax M2minimax/minimax-m2 | MiniMax | 37.8 | — | 3 of 15 benchmarks | 61.0% | 1383 | 1299 | ||||||||||||
| 452 | SWE-1.6 (none)cognition/swe-1.6:none | Cognition | 37.8 | — | 1 of 15 benchmarks | 9.4% | ||||||||||||||
| 453 | Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct | Mistral | 37.7 | $2.00 / $6.00 | 1 of 15 benchmarks | 1278 | ||||||||||||||
| 454 | Grok Code Fast 1x-ai/grok-code-fast-1 | SpaceXAI | 37.7 | — | 1 of 15 benchmarks | 1164 | ||||||||||||||
| 455 | Gemma 3 4Bgoogle/gemma-3-4b-it | 37.6 | — | 1 of 15 benchmarks | 1273 | |||||||||||||||
| 456 | GPT-5.4 Mini (low)openai/gpt-5.4-mini:low | OpenAI | 37.5 | $0.75 / $4.50 | 1 of 15 benchmarks | 9.3% | ||||||||||||||
| 457 | Gemini 1.5 Flash 8B 001google/gemini-1.5-flash-8b-001 | 37.5 | — | 1 of 15 benchmarks | 1271 | |||||||||||||||
| 458 | GPT-5.6 Terra (medium)openai/gpt-5.6-terra:medium | OpenAI | 37.5 | $2.00 / $12.00 | 2 of 15 benchmarks | 35.1% | 33.9% | |||||||||||||
| 459 | Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | Meta | 37.4 | $0.02 / $0.04 | 1 of 15 benchmarks | 1260 | ||||||||||||||
| 460 | Devstral Medium 2507mistralai/devstral-medium-2507 | Mistral AI | 37.3 | — | 1 of 15 benchmarks | 1072 | ||||||||||||||
| 461 | Mistral Medium 3.5 (none)mistralai/mistral-medium-3-5:none | Mistral | 37.3 | $1.50 / $7.50 | 1 of 15 benchmarks | 8.0% | ||||||||||||||
| 462 | GPT-4oopenai/gpt-4o | OpenAI | 37.3 | $2.50 / $10.00 | 1 of 15 benchmarks | 12.2% | ||||||||||||||
| 463 | QwQ 32B Previewqwen/qwq-32b-preview | Qwen | 37.3 | — | 1 of 15 benchmarks | 1174 | ||||||||||||||
| 464 | Inklingthinkingmachines/inkling | Thinking Machines | 37.2 | $1.00 / $4.05 | 4 of 15 benchmarks | 14.0% | 4.1% | 1494 | 1414 | |||||||||||
| 465 | Trinity Large Thinkingarcee-ai/trinity-large-thinking | Arcee AI | 37.0 | — | 2 of 15 benchmarks | 1412 | 1236 | |||||||||||||
| 466 | gpt-oss-120bopenai/gpt-oss-120b | OpenAI | 37.0 | $0.15 / $0.60 | 2 of 15 benchmarks | 26.0% | 1389 | |||||||||||||
| 467 | GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | OpenAI | 36.5 | $2.50 / $10.00 | 5 of 15 benchmarks | 27.0% | 39.7% | 30.4% | 29.5% | 1360 | ||||||||||
| 468 | Devstral 2 2512mistralai/devstral-2512 | Mistral | 36.5 | $0.40 / $2.00 | 2 of 15 benchmarks | 53.8% | 1196 | |||||||||||||
| 469 | GPT-5 Miniopenai/gpt-5-mini | OpenAI | 36.5 | $0.25 / $2.00 | 2 of 15 benchmarks | 56.2% | 39.7% | |||||||||||||
| 470 | Claude Opus 4.8 (medium)anthropic/claude-opus-4.8:medium | Anthropic | 36.1 | $5.00 / $25.00 | 4 of 15 benchmarks | 48.7% | 40.5% | 20.9% | 19.0 | |||||||||||
| 471 | Claude Sonnet 5 (low)anthropic/claude-sonnet-5:low | Anthropic | 35.4 | $2.00 / $10.00 | 2 of 15 benchmarks | 30.5% | 28.7% | |||||||||||||
| 472 | Kimi K3 (low)moonshotai/kimi-k3:low | MoonshotAI | 34.9 | $0.192 / $16.00 | 2 of 15 benchmarks | 18.6% | 22.0 | |||||||||||||
| 473 | Llama 4 Maverick 17B 128e Instructmeta-llama/llama-4-maverick-17b-128e-instruct | Meta | 34.7 | — | 2 of 15 benchmarks | 21.0% | 1372 | |||||||||||||
| 474 | Claude 3 Opusanthropic/claude-3-opus | Anthropic | 34.7 | — | 4 of 15 benchmarks | 15.8% | 26.3% | 10.5% | 1355 | |||||||||||
| 475 | Mercury 2inception/mercury-2 | Inception | 34.7 | — | 2 of 15 benchmarks | 1392 | 1171 | |||||||||||||
| 476 | Gemini 2.0 Flash 001google/gemini-2.0-flash-001 | 33.7 | — | 2 of 15 benchmarks | 13.5% | 1363 | ||||||||||||||
| 477 | GPT-4 Turboopenai/gpt-4-turbo | OpenAI | 33.5 | — | 2 of 15 benchmarks | 28.7% | 1347 | |||||||||||||
| 478 | Claude 2anthropic/claude-2 | Anthropic | 33.3 | — | 3 of 15 benchmarks | 4.4% | 3.0% | 2.0% | ||||||||||||
| 479 | Llama 4 Scout 17B 16e Instructmeta-llama/llama-4-scout-17b-16e-instruct | Meta | 33.3 | — | 2 of 15 benchmarks | 9.1% | 1363 | |||||||||||||
| 480 | Claude Sonnet 4.6 (high)anthropic/claude-sonnet-4.6:high | Anthropic | 32.8 | $3.00 / $15.00 | 2 of 15 benchmarks | 29.9% | 23.5% | |||||||||||||
| 481 | GPT-5.6 Luna (medium)openai/gpt-5.6-luna:medium | OpenAI | 32.6 | $0.20 / $1.20 | 2 of 15 benchmarks | 11.3% | 25.7% | |||||||||||||
| 482 | GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18 | OpenAI | 32.6 | $0.15 / $0.60 | 2 of 15 benchmarks | 27.5% | 1348 | |||||||||||||
| 483 | GPT-5.6 Terra (low)openai/gpt-5.6-terra:low | OpenAI | 32.4 | $2.00 / $12.00 | 2 of 15 benchmarks | 24.1% | 24.1% | |||||||||||||
| 484 | Granite 4.1 8Bibm-granite/granite-4.1-8b | IBM | 31.5 | — | 2 of 15 benchmarks | 1353 | 1193 | |||||||||||||
| 485 | Qwen2.5 Coder 32B Instructqwen/qwen2.5-coder-32b-instruct | Qwen | 31.1 | — | 2 of 15 benchmarks | 9.0% | 1342 | |||||||||||||
| 486 | Gemini 3.1 Pro Preview (high)google/gemini-3.1-pro-preview:high | 30.5 | $2.00 / $12.00 | 2 of 15 benchmarks | 11.7% | 8.9% | ||||||||||||||
| 487 | GPT-5.6 Luna (low)openai/gpt-5.6-luna:low | OpenAI | 29.4 | $0.20 / $1.20 | 2 of 15 benchmarks | 1.6% | 15.4% | |||||||||||||
| 488 | SWE Llamaprinceton-nlp/swe-llama | Princeton NLP | 28.7 | — | 3 of 15 benchmarks | 1.4% | 1.3% | 0.7% | ||||||||||||
| 489 | GLM 5.2 (high)z-ai/glm-5.2:high | Z.ai | 27.5 | $0.006 / $6.80 | 3 of 15 benchmarks | 36.3% | 17.4% | 18.0 | ||||||||||||
| 490 | Claude 3 Haikuanthropic/claude-3-haiku | Anthropic | 27.4 | — | 3 of 15 benchmarks | 40.6% | 20.2% | 1301 | ||||||||||||
| 491 | SWE Llama 13Bprinceton-nlp/swe-llama-13b | Princeton NLP | 27.0 | — | 3 of 15 benchmarks | 1.2% | 1.0% | 0.7% | ||||||||||||
| 492 | Claude Opus 4.7 (medium)anthropic/claude-opus-4.7:medium | Anthropic | 26.7 | $5.00 / $25.00 | 3 of 15 benchmarks | 28.9% | 7.0% | 7.0 | ||||||||||||
| 493 | GPT 3.5openai/gpt-3.5 | OpenAI | 22.4 | — | 3 of 15 benchmarks | 0.4% | 0.3% | 0.2% |
How this ranks
Every benchmark value becomes a percentile among the models that have it, so accuracy scores, Elo ratings and word error rates compare without hand-tuned scaling. Metrics where lower is better are inverted first. Raw values are never summed or averaged across benchmarks. A model's mean percentile is then shrunk toward the mean of the models that were broadly benchmarked, so a model tested twice cannot outrank a broadly tested one on two lucky results. Turning a data source off runs that same ranking code again in your browser over the sources you left on.
A model scored on fewer than 3 of the 15 ranked benchmarks in this category still ranks here, on the benchmarks it does have, and its row carries a partial coverage mark. On an equal score it sits under the model that earned the same number across more of the board.
Data sources
Turn a source off to drop every benchmark it feeds and re-rank the board in your browser. Your choice follows you across the leaderboard pages.
- DeepSWE v1.1
Pass@1 across all 113 DeepSWE v1.1 tasks, run by Datacurve with mini-swe-agent through Pier; reasoning-effort configurations remain separate.
- Epoch AI Benchmarking HubCC BY 4.0
Benchmark runs by Epoch AI, from the AI Benchmarking Hub.
- FrontierCode 1.1
Main weighted rubric Scores on FrontierCode 1.1's 100 hardest tasks, run by Cognition across five trials; results identify model, harness, and effort.
- FrontierSWE V2
Mean@5 score, the mean reward over five trials on every FrontierSWE V2 task; results identify the evaluated model and harness.
- LiveCodeBenchMIT
Maintainer-published Code Generation pass@1 over the 454-problem release_v6 window (2024-08-01 through 2025-05-01), from the stable 2025-08-01 snapshot; it does not cover newer frontier families.
- LMArenaCC BY 4.0
Arena ratings by LMArena, from the public leaderboard dataset.
- SWE-bench
Resolve rates published by the SWE-bench maintainers.
- Warden
Security review results published by Warden.