Best LLM for math
Research-grade problem sets plus competition math. Contamination-resistant private sets carry the same weight as public ones.
Aldena runs these models inside your team's projects. See what each one costs.
| rank | model | vendor | composite | pricein / out | benchmarks | % | % | % | % | % | elo |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol (max)openai/gpt-6.1-sol:max | OpenAI | 82.1 | $2.00 / $10.00 | 4 of 6 benchmarks | 93.7% | 100.0% | 100.0% | 1498 | ||
| 2 | Claude Fable 5 (max)anthropic/claude-fable-5:max | Anthropic | 81.5 | $10.00 / $50.00 | 4 of 6 benchmarks | 100.0% | 87.0% | 100.0% | 99.7% | ||
| 3 | Claude Fable 5.1 (max)anthropic/claude-fable-5.1:max | Anthropic | 81.4 | $10.00 / $50.00 | 4 of 6 benchmarks | 90.2% | 87.8% | 100.0% | 1525 | ||
| 4 | GPT-6 Astra (max)openai/gpt-6-astra:max | OpenAI | 80.6 | $10.00 / $50.00 | 4 of 6 benchmarks | 93.7% | 97.6% | 100.0% | 1481 | ||
| 5 | Gemini 4 Argon (high)google/gemini-4-argon:high | 80.0 | $2.00 / $10.00 | 4 of 6 benchmarks | 86.0% | 78.0% | 100.0% | 1528 | |||
| 6 | Claude Fable 5.2 (max)anthropic/claude-fable-5.2:max | Anthropic | 79.4 | $8.00 / $40.00 | 3 of 6 benchmarks | 95.1% | 100.0% | 99.7% | |||
| 7 | Claude Opus 5.5 (max)anthropic/claude-opus-5.5:max | Anthropic | 78.7 | $4.00 / $20.00 | 3 of 6 benchmarks | 91.2% | 95.0% | 100.0% | |||
| 8 | GPT-6.1 Terra (max)openai/gpt-6.1-terra:max | OpenAI | 78.3 | $1.00 / $5.00 | 3 of 6 benchmarks | 90.9% | 92.7% | 100.0% | |||
| 9 | Claude Opus 5 (max)anthropic/claude-opus-5:max | Anthropic | 78.1 | $5.00 / $25.00 | 4 of 6 benchmarks | 85.6% | 73.2% | 98.9% | 1515 | ||
| 10 | GPT-5.6 Sol (max)openai/gpt-5.6-sol:max | OpenAI | 77.2 | $4.00 / $20.00 | 3 of 6 benchmarks | 89.1% | 82.9% | 100.0% | |||
| 11 | Muse Wonder (max)meta/muse-wonder:max | Meta | 76.8 | $4.00 / $20.00 | 4 of 6 benchmarks | 82.1% | 70.7% | 99.4% | 1495 | ||
| 12 | Claude Sonnet 5.5 (max)anthropic/claude-sonnet-5.5:max | Anthropic | 76.8 | $2.00 / $10.00 | 3 of 6 benchmarks | 88.8% | 80.5% | 100.0% | |||
| 13 | GPT-5.4 (high)openai/gpt-5.4:high | OpenAI | 75.8 | $2.50 / $15.00 | 4 of 6 benchmarks | 80.0% | 50.0% | 97.8% | 1491 | ||
| 14 | GPT-6 Sol (max)openai/gpt-6-sol:max | OpenAI | 75.8 | $2.00 / $10.00 | 4 of 6 benchmarks | 89.8% | 90.0% | 100.0% | 1440 | ||
| 15 | Claude Fable 5 (high)anthropic/claude-fable-5:high | Anthropic | 75.0 | $10.00 / $50.00 | 2 of 6 benchmarks | 100.0% | 1521 | ||||
| 16 | GPT-5.6 Terra (max)openai/gpt-5.6-terra:max | OpenAI | 74.7 | $2.00 / $12.00 | 3 of 6 benchmarks | 86.0% | 70.7% | 99.7% | |||
| 17 | Kimi K3.1 Pro (max)moonshotai/kimi-k3.1-pro:max | MoonshotAI | 73.6 | $2.00 / $10.00 | 3 of 6 benchmarks | 78.3% | 65.8% | 100.0% | |||
| 18 | Claude Opus 4.8 (max)anthropic/claude-opus-4.8:max | Anthropic | 73.3 | $5.00 / $25.00 | 4 of 6 benchmarks | 47.2% | 80.0% | 56.1% | 98.3% | ||
| 19 | GPT-5.6 Luna (max)openai/gpt-5.6-luna:max | OpenAI | 72.5 | $0.20 / $1.20 | 3 of 6 benchmarks | 82.1% | 61.0% | 98.3% | |||
| 20 | GPT 5.5 Pro Pre Release (xhigh)openai/gpt-5.5-pro-pre-release:xhigh | OpenAI | 72.4 | — | 3 of 6 benchmarks | 51.0% | 39.6% | 100.0% | |||
| 21 | Kimi K3 (max)moonshotai/kimi-k3:max | MoonshotAI | 72.2 | $0.192 / $16.00 | 4 of 6 benchmarks | 72.2% | 39.0% | 97.2% | 1502 | ||
| 22 | GPT 5.5 Pre Release (xhigh)openai/gpt-5.5-pre-release:xhigh | OpenAI | 72.0 | — | 3 of 6 benchmarks | 51.7% | 35.4% | 100.0% | |||
| 23 | Gemini 3.7 Flash (high)google/gemini-3.7-flash:high | 71.9 | $0.75 / $3.75 | 4 of 6 benchmarks | 71.6% | 36.6% | 97.2% | 1502 | |||
| 24 | GPT-6 Luna (max)openai/gpt-6-luna:max | OpenAI | 71.9 | $0.10 / $0.50 | 4 of 6 benchmarks | 79.0% | 56.1% | 98.9% | 1450 | ||
| 25 | GPT-5.4 Pro (xhigh)openai/gpt-5.4-pro:xhigh | OpenAI | 71.6 | $30.00 / $180.00 | 3 of 6 benchmarks | 50.0% | 82.5% | 58.5% | |||
| 26 | Muse Spark 1.3 (max)meta/muse-spark-1.3:max | Meta | 71.5 | $1.25 / $4.25 | 3 of 6 benchmarks | 74.0% | 46.3% | 1507 | |||
| 27 | Gemini 3.5 Flash (high)google/gemini-3.5-flash:high | 71.2 | $1.50 / $9.00 | 5 of 6 benchmarks | 80.0% | 62.8% | 26.8% | 95.6% | 1497 | ||
| 28 | GPT-5.5 Pro (xhigh)openai/gpt-5.5-pro:xhigh | OpenAI | 71.1 | $30.00 / $180.00 | 2 of 6 benchmarks | 87.7% | 78.0% | ||||
| 29 | Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | 71.1 | $2.00 / $12.00 | 5 of 6 benchmarks | 88.9% | 59.6% | 26.8% | 95.6% | 1488 | ||
| 30 | Qwen3.8 Max (xhigh)qwen/qwen3.8-max:xhigh | Qwen | 71.1 | — | 3 of 6 benchmarks | 74.7% | 46.3% | 99.4% | |||
| 31 | GPT-5.4 (xhigh)openai/gpt-5.4:xhigh | OpenAI | 71.1 | $2.50 / $15.00 | 4 of 6 benchmarks | 47.6% | 78.6% | 49.0% | 95.3% | ||
| 32 | Gemini 3.8 Flash (high)google/gemini-3.8-flash:high | 70.3 | $0.75 / $3.75 | 4 of 6 benchmarks | 68.4% | 21.9% | 98.9% | 1519 | |||
| 33 | Muse Spark 1.3 (xhigh)meta/muse-spark-1.3:xhigh | Meta | 70.2 | $1.25 / $4.25 | 3 of 6 benchmarks | 74.4% | 41.5% | 99.2% | |||
| 34 | DeepSeek V4.1 Flash 1017 (max)deepseek/deepseek-v4.1-flash-1017:max | DeepSeek | 70.1 | $0.006 / $0.50 | 3 of 6 benchmarks | 71.2% | 46.3% | 99.4% | |||
| 35 | DeepSeek V4.1 Flash (max)deepseek/deepseek-v4.1-flash:max | DeepSeek | 69.6 | $0.051 / $0.567 | 4 of 6 benchmarks | 67.4% | 26.8% | 98.3% | 1495 | ||
| 36 | GPT-5.5 (xhigh)openai/gpt-5.5:xhigh | OpenAI | 69.6 | $5.00 / $30.00 | 2 of 6 benchmarks | 85.3% | 72.5% | ||||
| 37 | Qwen3.7 Maxqwen/qwen3.7-max | Qwen | 68.0 | $1.475 / $4.425 | 4 of 6 benchmarks | 64.6% | 34.1% | 95.6% | 1483 | ||
| 38 | GLM 5.3 (max)z-ai/glm-5.3:max | Z.ai | 68.0 | $0.0699 / $1.40 | 4 of 6 benchmarks | 68.8% | 29.3% | 91.1% | 1502 | ||
| 39 | Qwen3.8 Max (0902) (xhigh)qwen/qwen3.8-max-0902:xhigh | Qwen | 67.9 | $2.00 / $6.00 | 3 of 6 benchmarks | 65.6% | 34.1% | 100.0% | |||
| 40 | Claude Opus 5 (high)anthropic/claude-opus-5:high | Anthropic | 67.6 | $5.00 / $25.00 | 1 of 6 benchmarks | 1521 | |||||
| 41 | GPT-5.2 (high)openai/gpt-5.2:high | OpenAI | 67.4 | $1.75 / $14.00 | 4 of 6 benchmarks | 60.0% | 18.8% | 96.1% | 1457 | ||
| 42 | Claude Opus 4.6 (max)anthropic/claude-opus-4.6:max | Anthropic | 67.4 | $5.00 / $25.00 | 4 of 6 benchmarks | 90.0% | 66.0% | 26.8% | 91.1% | ||
| 43 | Claude Opus 5.5 (high)anthropic/claude-opus-5.5:high | Anthropic | 67.3 | $4.00 / $20.00 | 1 of 6 benchmarks | 1518 | |||||
| 44 | GPT-5.2 (xhigh)openai/gpt-5.2:xhigh | OpenAI | 67.1 | $1.75 / $14.00 | 4 of 6 benchmarks | 40.7% | 67.4% | 31.7% | 96.1% | ||
| 45 | Claude Opus 4.6 (high)anthropic/claude-opus-4.6:high | Anthropic | 67.1 | $5.00 / $25.00 | 1 of 6 benchmarks | 1516 | |||||
| 46 | GPT-6 Astra (high)openai/gpt-6-astra:high | OpenAI | 66.9 | $10.00 / $50.00 | 1 of 6 benchmarks | 97.6% | |||||
| 47 | GPT-6 Astra (xhigh)openai/gpt-6-astra:xhigh | OpenAI | 66.9 | $10.00 / $50.00 | 1 of 6 benchmarks | 97.6% | |||||
| 48 | Muse Spark Open (xhigh)meta/muse-spark-open:xhigh | Meta | 66.8 | $1.25 / $4.25 | 3 of 6 benchmarks | 69.8% | 31.7% | 98.1% | |||
| 49 | Grok 4.6 (xhigh)x-ai/grok-4.6:xhigh | SpaceXAI | 66.8 | $2.00 / $6.00 | 3 of 6 benchmarks | 66.0% | 31.7% | 99.2% | |||
| 50 | GLM 5.3 Flashz-ai/glm-5.3-flash | Z.ai | 66.8 | $0.15 / $0.50 | 1 of 6 benchmarks | 1504 | |||||
| 51 | Claude Opus 4.6 (64K)anthropic/claude-opus-4.6:64k | Anthropic | 66.7 | $5.00 / $25.00 | 3 of 6 benchmarks | 90.0% | 20.8% | 94.4% | |||
| 52 | Qwen3.8 Maxqwen/qwen3.8-max | Qwen | 66.6 | — | 1 of 6 benchmarks | 1504 | |||||
| 53 | Kimi K2.6moonshotai/kimi-k2.6 | MoonshotAI | 66.6 | $0.65 / $3.41 | 5 of 6 benchmarks | 39.0% | 57.2% | 25.6% | 96.1% | 1479 | |
| 54 | GPT 5.5 Pro Pre Release (high)openai/gpt-5.5-pro-pre-release:high | OpenAI | 66.5 | — | 2 of 6 benchmarks | 52.4% | 39.6% | ||||
| 55 | Claude Opus 4.7 (high)anthropic/claude-opus-4.7:high | Anthropic | 66.5 | $5.00 / $25.00 | 1 of 6 benchmarks | 1504 | |||||
| 56 | GPT-6 Astra (medium)openai/gpt-6-astra:medium | OpenAI | 66.3 | $10.00 / $50.00 | 1 of 6 benchmarks | 97.6% | |||||
| 57 | Claude Haiku 5.5 (max)anthropic/claude-haiku-5.5:max | Anthropic | 65.8 | $0.10 / $0.50 | 2 of 6 benchmarks | 75.1% | 46.3% | ||||
| 58 | GPT-5.5openai/gpt-5.5 | OpenAI | 65.8 | $5.00 / $30.00 | 1 of 6 benchmarks | 1500 | |||||
| 59 | Gemini 3.6 Flash (high)google/gemini-3.6-flash:high | 65.6 | $0.75 / $3.75 | 4 of 6 benchmarks | 59.0% | 21.9% | 94.2% | 1501 | |||
| 60 | GPT-5 (high)openai/gpt-5:high | OpenAI | 65.3 | $1.25 / $10.00 | 6 of 6 benchmarks | 32.4% | 55.4% | 21.9% | 91.4% | 98.1% | 1435 |
| 61 | GPT-6 Astra (low)openai/gpt-6-astra:low | OpenAI | 65.2 | $10.00 / $50.00 | 1 of 6 benchmarks | 87.8% | |||||
| 62 | Claude Opus 4.6 (32K)anthropic/claude-opus-4.6:32k | Anthropic | 65.2 | $5.00 / $25.00 | 3 of 6 benchmarks | 80.0% | 20.8% | 93.1% | |||
| 63 | GPT-5.6 Sol (xhigh)openai/gpt-5.6-sol:xhigh | OpenAI | 65.1 | $4.00 / $20.00 | 1 of 6 benchmarks | 1494 | |||||
| 64 | Muse Spark 1.1meta/muse-spark-1.1 | Meta | 65.0 | $1.25 / $4.25 | 1 of 6 benchmarks | 1493 | |||||
| 65 | Claude Haiku 5.5 (xhigh)anthropic/claude-haiku-5.5:xhigh | Anthropic | 64.9 | $0.10 / $0.50 | 1 of 6 benchmarks | 98.9% | |||||
| 66 | Claude Opus 4.8 (high)anthropic/claude-opus-4.8:high | Anthropic | 64.9 | $5.00 / $25.00 | 1 of 6 benchmarks | 1492 | |||||
| 67 | Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | 64.8 | $0.50 / $3.00 | 5 of 6 benchmarks | 60.0% | 51.2% | 17.1% | 92.8% | 1475 | ||
| 68 | Grok 4.6 (high)x-ai/grok-4.6:high | SpaceXAI | 64.8 | $2.00 / $6.00 | 2 of 6 benchmarks | 97.8% | 1444 | ||||
| 69 | GPT-5.5 (high)openai/gpt-5.5:high | OpenAI | 64.8 | $5.00 / $30.00 | 1 of 6 benchmarks | 1491 | |||||
| 70 | GPT-6 Astra (none)openai/gpt-6-astra:none | OpenAI | 64.7 | $10.00 / $50.00 | 1 of 6 benchmarks | 82.9% | |||||
| 71 | Claude Haiku 5.5 (high)anthropic/claude-haiku-5.5:high | Anthropic | 64.5 | $0.10 / $0.50 | 2 of 6 benchmarks | 97.2% | 1448 | ||||
| 72 | Muse Spark 1.2 (xhigh)meta/muse-spark-1.2:xhigh | Meta | 64.5 | $1.25 / $4.25 | 1 of 6 benchmarks | 1491 | |||||
| 73 | GPT-5.2 Pro (xhigh)openai/gpt-5.2-pro:xhigh | OpenAI | 64.5 | $21.00 / $168.00 | 2 of 6 benchmarks | 74.0% | 46.0% | ||||
| 74 | DeepSeek V4 Pro 0813 (max)deepseek/deepseek-v4-pro-0813:max | DeepSeek | 64.4 | $0.111 / $4.44 | 3 of 6 benchmarks | 64.6% | 26.8% | 98.6% | |||
| 75 | Claude Opus 4.7anthropic/claude-opus-4.7 | Anthropic | 64.4 | $5.00 / $25.00 | 1 of 6 benchmarks | 1490 | |||||
| 76 | Claude Sonnet 5.5 (xhigh)anthropic/claude-sonnet-5.5:xhigh | Anthropic | 64.3 | $2.00 / $10.00 | 1 of 6 benchmarks | 1489 | |||||
| 77 | Qwen3.7 Plusqwen/qwen3.7-plus | Qwen | 64.1 | $0.32 / $1.28 | 2 of 6 benchmarks | 93.3% | 1465 | ||||
| 78 | Hy3tencent/hy3 | Tencent | 63.9 | $0.0825 / $0.33 | 1 of 6 benchmarks | 1484 | |||||
| 79 | GLM 5.2 (max)z-ai/glm-5.2:max | Z.ai | 63.8 | $0.006 / $6.80 | 4 of 6 benchmarks | 59.2% | 29.3% | 86.4% | 1487 | ||
| 80 | DeepSeek V4 Pro 0423 (high)deepseek/deepseek-v4-pro:high | DeepSeek | 63.8 | $0.8837 / $1.7675 | 2 of 6 benchmarks | 95.6% | 1450 | ||||
| 81 | MiMo-V2.6-Proxiaomi/mimo-v2.6-pro | Xiaomi | 63.6 | $0.435 / $0.87 | 1 of 6 benchmarks | 1482 | |||||
| 82 | GPT-5.2 (medium)openai/gpt-5.2:medium | OpenAI | 63.5 | $1.75 / $14.00 | 3 of 6 benchmarks | 60.0% | 16.7% | 93.9% | |||
| 83 | Gemini 3.5 Flash (medium)google/gemini-3.5-flash:medium | 63.5 | $1.50 / $9.00 | 1 of 6 benchmarks | 1481 | ||||||
| 84 | Claude Opus 4.6anthropic/claude-opus-4.6 | Anthropic | 63.4 | $5.00 / $25.00 | 3 of 6 benchmarks | 38.3% | 14.6% | 1503 | |||
| 85 | Mistral Large 4 (high)mistralai/mistral-large-4-0:high | Mistral | 63.3 | $0.70 / $2.10 | 3 of 6 benchmarks | 58.6% | 26.8% | 98.3% | |||
| 86 | Claude Fable 5 (low)anthropic/claude-fable-5:low | Anthropic | 63.3 | $10.00 / $50.00 | 1 of 6 benchmarks | 97.8% | |||||
| 87 | Claude Opus 4.8 (low)anthropic/claude-opus-4.8:low | Anthropic | 63.3 | $5.00 / $25.00 | 1 of 6 benchmarks | 97.8% | |||||
| 88 | Claude Opus 5anthropic/claude-opus-5 | Anthropic | 63.3 | $5.00 / $25.00 | 1 of 6 benchmarks | 97.8% | |||||
| 89 | MiMo-V2.5-Proxiaomi/mimo-v2.5-pro | Xiaomi | 63.2 | $0.48 / $1.80 | 1 of 6 benchmarks | 1479 | |||||
| 90 | Inklingthinkingmachines/inkling | Thinking Machines | 63.0 | $1.00 / $4.05 | 1 of 6 benchmarks | 1479 | |||||
| 91 | GPT-5.6 Terra (xhigh)openai/gpt-5.6-terra:xhigh | OpenAI | 62.9 | $2.00 / $12.00 | 1 of 6 benchmarks | 1478 | |||||
| 92 | Gemini 2.5 Pro Preview 05-06google/gemini-2.5-pro-preview-05-06 | 62.8 | — | 1 of 6 benchmarks | 95.9% | ||||||
| 93 | Ernie 5.1baidu/ernie-5.1 | Baidu | 62.7 | — | 1 of 6 benchmarks | 1478 | |||||
| 94 | GPT-5.6 Luna (xhigh)openai/gpt-5.6-luna:xhigh | OpenAI | 62.6 | $0.20 / $1.20 | 1 of 6 benchmarks | 1476 | |||||
| 95 | Claude Opus 4.8anthropic/claude-opus-4.8 | Anthropic | 62.5 | $5.00 / $25.00 | 1 of 6 benchmarks | 1476 | |||||
| 96 | Gemini 3 Progoogle/gemini-3-pro | 62.4 | — | 1 of 6 benchmarks | 1475 | ||||||
| 97 | Seed 2.1 Turbo (high)bytedance-seed/seed-2-1-turbo:high | ByteDance Seed | 62.2 | $0.50 / $2.50 | 1 of 6 benchmarks | 96.1% | |||||
| 98 | Muse Sparkmeta/muse-spark | Meta | 62.1 | — | 4 of 6 benchmarks | 39.0% | 14.6% | 88.9% | 1468 | ||
| 99 | Claude Opus 4.7 (max)anthropic/claude-opus-4.7:max | Anthropic | 62.1 | $5.00 / $25.00 | 3 of 6 benchmarks | 70.2% | 31.7% | 86.7% | |||
| 100 | GPT-5 (medium)openai/gpt-5:medium | OpenAI | 62.0 | $1.25 / $10.00 | 4 of 6 benchmarks | 27.2% | 6.3% | 87.2% | 97.9% | ||
| 101 | Claude Opus 4.5 (high 32K)anthropic/claude-opus-4.5:high-32k | Anthropic | 62.0 | $5.00 / $25.00 | 1 of 6 benchmarks | 1472 | |||||
| 102 | Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | Reflection | 61.9 | $0.30 / $1.00 | 1 of 6 benchmarks | 1472 | |||||
| 103 | Qwen3.6 Max Previewqwen/qwen3.6-max-preview | Qwen | 61.8 | — | 4 of 6 benchmarks | 50.0% | 4.2% | 91.1% | 1472 | ||
| 104 | Claude Sonnet 5 (high)anthropic/claude-sonnet-5:high | Anthropic | 61.8 | $2.00 / $10.00 | 1 of 6 benchmarks | 1472 | |||||
| 105 | Grok 4.5 (high)x-ai/grok-4.5:high | SpaceXAI | 61.5 | $2.00 / $6.00 | 3 of 6 benchmarks | 57.2% | 24.4% | 97.8% | |||
| 106 | Step 5 Previewstepfun/step-5-preview | StepFun | 61.5 | $1.00 / $2.70 | 1 of 6 benchmarks | 1471 | |||||
| 107 | Grok 4.5x-ai/grok-4.5 | SpaceXAI | 61.4 | $2.00 / $6.00 | 1 of 6 benchmarks | 1470 | |||||
| 108 | Kimi K2.5 (thinking)moonshotai/kimi-k2.5:thinking | MoonshotAI | 61.3 | $0.532 / $3.325 | 1 of 6 benchmarks | 1470 | |||||
| 109 | Gemini 3 Flash Preview (high)google/gemini-3-flash-preview:high | 61.2 | $0.50 / $3.00 | 1 of 6 benchmarks | 95.6% | ||||||
| 110 | Gemini 3.1 Pro Preview (high)google/gemini-3.1-pro-preview:high | 61.2 | $2.00 / $12.00 | 1 of 6 benchmarks | 95.6% | ||||||
| 111 | GPT-5.4 (medium)openai/gpt-5.4:medium | OpenAI | 61.2 | $2.50 / $15.00 | 1 of 6 benchmarks | 95.6% | |||||
| 112 | GPT-5.6 Sol (low)openai/gpt-5.6-sol:low | OpenAI | 61.2 | $4.00 / $20.00 | 1 of 6 benchmarks | 95.6% | |||||
| 113 | GPT-5 Pro (high)openai/gpt-5-pro:high | OpenAI | 61.2 | $15.00 / $120.00 | 3 of 6 benchmarks | 60.0% | 55.8% | 19.5% | |||
| 114 | Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 61.1 | $0.0765 / $0.255 | 1 of 6 benchmarks | 1469 | ||||||
| 115 | Qwen3.5 Max Previewqwen/qwen3.5-max-preview | Qwen | 60.9 | — | 1 of 6 benchmarks | 1468 | |||||
| 116 | MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash | Xiaomi | 60.8 | $0.14 / $0.28 | 1 of 6 benchmarks | 1468 | |||||
| 117 | Grok 4.7 (xhigh)x-ai/grok-4.7:xhigh | SpaceXAI | 60.7 | $2.00 / $6.00 | 4 of 6 benchmarks | 53.0% | 17.1% | 98.1% | 1444 | ||
| 118 | Gemma 4 31Bgoogle/gemma-4-31b-it | 60.6 | $0.20 / $0.40 | 1 of 6 benchmarks | 1467 | ||||||
| 119 | Claude Sonnet 5 (xhigh)anthropic/claude-sonnet-5:xhigh | Anthropic | 60.6 | $2.00 / $10.00 | 1 of 6 benchmarks | 94.7% | |||||
| 120 | Grok 4.20 Beta 0309 (reasoning)x-ai/grok-4.20-beta-0309:reasoning | SpaceXAI | 60.4 | — | 1 of 6 benchmarks | 1464 | |||||
| 121 | DeepSeek V4 Flash 0731 (max)deepseek/deepseek-v4-flash-0731:max | DeepSeek | 60.0 | $0.0434 / $0.30 | 3 of 6 benchmarks | 57.5% | 24.4% | 94.4% | |||
| 122 | Claude Sonnet 4.6anthropic/claude-sonnet-4.6 | Anthropic | 60.0 | $3.00 / $15.00 | 1 of 6 benchmarks | 1461 | |||||
| 123 | GLM 5.1z-ai/glm-5.1 | Z.ai | 60.0 | $1.40 / $4.40 | 5 of 6 benchmarks | 33.5% | 36.8% | 12.5% | 93.3% | 1474 | |
| 124 | Qwen3.6 Plusqwen/qwen3.6-plus | Qwen | 59.9 | $0.325 / $1.95 | 5 of 6 benchmarks | 50.0% | 38.3% | 8.3% | 93.3% | 1452 | |
| 125 | Gemini 3 Pro Previewgoogle/gemini-3-pro-preview | 59.9 | — | 3 of 6 benchmarks | 37.6% | 18.8% | 91.4% | ||||
| 126 | GPT-5.4openai/gpt-5.4 | OpenAI | 59.9 | $2.50 / $15.00 | 1 of 6 benchmarks | 1459 | |||||
| 127 | Mistral Large 4mistralai/mistral-large-4-0 | Mistral | 59.8 | $0.70 / $2.10 | 1 of 6 benchmarks | 1459 | |||||
| 128 | GPT-5.1 (high)openai/gpt-5.1:high | OpenAI | 59.7 | $1.25 / $10.00 | 4 of 6 benchmarks | 31.0% | 12.5% | 88.6% | 1458 | ||
| 129 | Claude Opus 5 (low)anthropic/claude-opus-5:low | Anthropic | 59.5 | $5.00 / $25.00 | 1 of 6 benchmarks | 93.3% | |||||
| 130 | Kimi K3 (high)moonshotai/kimi-k3:high | MoonshotAI | 59.5 | $0.192 / $16.00 | 1 of 6 benchmarks | 93.3% | |||||
| 131 | Grok 4.20 Multi Agent Beta 0309x-ai/grok-4.20-multi-agent-beta-0309 | SpaceXAI | 59.4 | — | 1 of 6 benchmarks | 1455 | |||||
| 132 | Claude Sonnet 4.5 (high 32K)anthropic/claude-sonnet-4.5:high-32k | Anthropic | 59.3 | $3.00 / $15.00 | 1 of 6 benchmarks | 1455 | |||||
| 133 | Gemini 3 Flash Preview (minimal)google/gemini-3-flash-preview:minimal | 59.1 | $0.50 / $3.00 | 1 of 6 benchmarks | 1453 | ||||||
| 134 | GPT-5.2 Chatopenai/gpt-5.2-chat | OpenAI | 59.0 | — | 1 of 6 benchmarks | 1453 | |||||
| 135 | GPT-5 Mini (high)openai/gpt-5-mini:high | OpenAI | 58.8 | $0.25 / $2.00 | 6 of 6 benchmarks | 27.2% | 46.7% | 12.2% | 86.7% | 97.8% | 1407 |
| 136 | Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b | NVIDIA | 58.8 | $0.60 / $2.40 | 2 of 6 benchmarks | 86.7% | 1443 | ||||
| 137 | Inkling Smallthinkingmachines/inkling-small | Thinking Machines | 58.8 | $0.45 / $1.20 | 1 of 6 benchmarks | 1451 | |||||
| 138 | Mimo v2 Proxiaomi/mimo-v2-pro | Xiaomi | 58.6 | — | 1 of 6 benchmarks | 1451 | |||||
| 139 | Qwen3.8 27Bqwen/qwen3.8-27b | Qwen | 58.3 | $0.15 / $1.875 | 1 of 6 benchmarks | 1450 | |||||
| 140 | Claude Sonnet 5 (max)anthropic/claude-sonnet-5:max | Anthropic | 58.0 | $2.00 / $10.00 | 3 of 6 benchmarks | 65.6% | 29.3% | 80.0% | |||
| 141 | Seed-2.0-Lite (high)bytedance-seed/seed-2.0-lite:high | ByteDance Seed | 58.0 | $0.25 / $2.00 | 1 of 6 benchmarks | 91.1% | |||||
| 142 | Dola Seed 2.0 Probytedance/dola-seed-2.0-pro | ByteDance | 58.0 | — | 1 of 6 benchmarks | 1449 | |||||
| 143 | o3openai/o3 | OpenAI | 57.8 | $2.00 / $8.00 | 1 of 6 benchmarks | 1448 | |||||
| 144 | GLM 5.3 Flash (max)z-ai/glm-5.3-flash:max | Z.ai | 57.5 | $0.15 / $0.50 | 3 of 6 benchmarks | 55.8% | 17.1% | 93.9% | |||
| 145 | Claude Opus 4.1 (thinking 16K)anthropic/claude-opus-4.1:thinking-16k | Anthropic | 57.4 | $15.00 / $75.00 | 1 of 6 benchmarks | 1444 | |||||
| 146 | DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro | DeepSeek | 57.3 | $0.8837 / $1.7675 | 1 of 6 benchmarks | 1443 | |||||
| 147 | Gemini 3.5 Flash (low)google/gemini-3.5-flash:low | 57.1 | $1.50 / $9.00 | 1 of 6 benchmarks | 88.9% | ||||||
| 148 | GPT-5.6 Terra (low)openai/gpt-5.6-terra:low | OpenAI | 57.1 | $2.00 / $12.00 | 1 of 6 benchmarks | 88.9% | |||||
| 149 | gpt-oss-120b (high)openai/gpt-oss-120b:high | OpenAI | 57.1 | $0.15 / $0.60 | 1 of 6 benchmarks | 88.9% | |||||
| 150 | Grok 4.1 (thinking)x-ai/grok-4.1:thinking | SpaceXAI | 56.9 | — | 1 of 6 benchmarks | 1443 | |||||
| 151 | Kimi K2.5 Instantmoonshotai/kimi-k2.5-instant | Moonshot AI | 56.8 | — | 1 of 6 benchmarks | 1442 | |||||
| 152 | o4 Mini Highopenai/o4-mini-high | OpenAI | 56.7 | — | 5 of 6 benchmarks | 24.8% | 36.1% | 4.9% | 81.7% | 97.8% | |
| 153 | Muse Glimmer 30Bmeta/muse-glimmer-30b | Meta | 56.6 | $0.30 / $1.20 | 1 of 6 benchmarks | 1442 | |||||
| 154 | Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | 56.5 | $0.30 / $2.50 | 1 of 6 benchmarks | 1442 | ||||||
| 155 | DeepSeek V4 Flash 0423 (high)deepseek/deepseek-v4-flash:high | DeepSeek | 56.4 | $0.091 / $0.182 | 1 of 6 benchmarks | 1441 | |||||
| 156 | Kimi K2.7 Codemoonshotai/kimi-k2.7-code | MoonshotAI | 56.1 | $0.60 / $3.50 | 3 of 6 benchmarks | 54.0% | 12.2% | 95.6% | |||
| 157 | GPT-5.4 Mini (high)openai/gpt-5.4-mini:high | OpenAI | 56.1 | $0.75 / $4.50 | 4 of 6 benchmarks | 50.0% | 2.1% | 87.2% | 1439 | ||
| 158 | Kimi K2 Thinking Turbomoonshotai/kimi-k2-thinking-turbo | Moonshot AI | 56.1 | — | 3 of 6 benchmarks | 20.0% | 83.1% | 1436 | |||
| 159 | GPT-5 Mini (medium)openai/gpt-5-mini:medium | OpenAI | 55.9 | $0.25 / $2.00 | 4 of 6 benchmarks | 20.3% | 4.2% | 78.3% | 96.8% | ||
| 160 | MiMo-V2.5xiaomi/mimo-v2.5 | Xiaomi | 55.9 | $0.40 / $2.00 | 1 of 6 benchmarks | 1437 | |||||
| 161 | GLM 5V Turboz-ai/glm-5v-turbo | Z.ai | 55.8 | $1.20 / $4.00 | 1 of 6 benchmarks | 1436 | |||||
| 162 | Kimi K2p5moonshotai/kimi-k2p5 | Moonshot AI | 55.7 | — | 3 of 6 benchmarks | 27.9% | 4.2% | 92.2% | |||
| 163 | Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | 55.6 | $0.25 / $1.50 | 1 of 6 benchmarks | 1436 | ||||||
| 164 | Claude Opus 4.7 (xhigh)anthropic/claude-opus-4.7:xhigh | Anthropic | 55.6 | $5.00 / $25.00 | 3 of 6 benchmarks | 43.8% | 0.0% | 97.8% | |||
| 165 | Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b | Qwen | 55.5 | $0.60 / $3.60 | 3 of 6 benchmarks | 29.5% | 88.9% | 1450 | |||
| 166 | Ernie 5.0 0110baidu/ernie-5.0-0110 | Baidu | 55.3 | — | 1 of 6 benchmarks | 1434 | |||||
| 167 | Mimo v2 Omnixiaomi/mimo-v2-omni | Xiaomi | 55.1 | — | 1 of 6 benchmarks | 1433 | |||||
| 168 | Claude Sonnet 4.6 (32K)anthropic/claude-sonnet-4.6:32k | Anthropic | 55.0 | $3.00 / $15.00 | 1 of 6 benchmarks | 85.8% | |||||
| 169 | Grok 4.20 0309 (reasoning)x-ai/grok-4.20-0309:reasoning | SpaceXAI | 55.0 | — | 3 of 6 benchmarks | 44.9% | 17.1% | 92.2% | |||
| 170 | GPT-5.2openai/gpt-5.2 | OpenAI | 54.9 | $1.75 / $14.00 | 1 of 6 benchmarks | 1432 | |||||
| 171 | GPT-5.3 Chatopenai/gpt-5.3-chat | OpenAI | 54.8 | — | 1 of 6 benchmarks | 1430 | |||||
| 172 | Inkling Small (xhigh)thinkingmachines/inkling-small:xhigh | Thinking Machines | 54.7 | $0.45 / $1.20 | 3 of 6 benchmarks | 46.3% | 17.1% | 90.0% | |||
| 173 | Hy3 previewtencent/hy3-preview | Tencent | 54.6 | $0.18 / $0.60 | 1 of 6 benchmarks | 1429 | |||||
| 174 | Grok 4.3 (high)x-ai/grok-4.3:high | SpaceXAI | 54.5 | $1.25 / $2.50 | 3 of 6 benchmarks | 42.8% | 14.6% | 93.3% | |||
| 175 | DeepSeek V3.2 (thinking)deepseek/deepseek-v3.2:thinking | DeepSeek | 54.5 | $0.26 / $0.38 | 1 of 6 benchmarks | 1429 | |||||
| 176 | GPT-5.4 Nano (high)openai/gpt-5.4-nano:high | OpenAI | 54.4 | $0.20 / $1.25 | 5 of 6 benchmarks | 25.9% | 44.9% | 12.2% | 87.8% | 1424 | |
| 177 | Claude Opus 4.8 (none)anthropic/claude-opus-4.8:none | Anthropic | 54.3 | $5.00 / $25.00 | 1 of 6 benchmarks | 84.4% | |||||
| 178 | GPT-5.4 (low)openai/gpt-5.4:low | OpenAI | 54.3 | $2.50 / $15.00 | 1 of 6 benchmarks | 84.4% | |||||
| 179 | GPT-5.5 (low)openai/gpt-5.5:low | OpenAI | 54.3 | $5.00 / $30.00 | 1 of 6 benchmarks | 84.4% | |||||
| 180 | Mistral Medium 3.5mistralai/mistral-medium-3-5 | Mistral | 54.3 | $1.50 / $7.50 | 1 of 6 benchmarks | 1427 | |||||
| 181 | GPT-5.2 (low)openai/gpt-5.2:low | OpenAI | 54.1 | $1.75 / $14.00 | 3 of 6 benchmarks | 40.0% | 6.3% | 78.9% | |||
| 182 | Grok 4.1x-ai/grok-4.1 | SpaceXAI | 54.0 | — | 1 of 6 benchmarks | 1426 | |||||
| 183 | Qwen3.5 Plusqwen/qwen3.5-plus | Qwen | 54.0 | $0.30 / $1.80 | 3 of 6 benchmarks | 50.0% | 2.1% | 86.7% | |||
| 184 | Qwen3.6 27Bqwen/qwen3.6-27b | Qwen | 54.0 | $0.32 / $3.20 | 2 of 6 benchmarks | 35.1% | 91.1% | ||||
| 185 | Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b | Qwen | 53.5 | $0.26 / $2.08 | 1 of 6 benchmarks | 1425 | |||||
| 186 | Claude Sonnet 4.6 (medium)anthropic/claude-sonnet-4.6:medium | Anthropic | 53.3 | $3.00 / $15.00 | 1 of 6 benchmarks | 82.2% | |||||
| 187 | Gemini 3.6 Flash (low)google/gemini-3.6-flash:low | 53.3 | $0.75 / $3.75 | 1 of 6 benchmarks | 82.2% | ||||||
| 188 | Gemma 4 26B A4B (minimal)google/gemma-4-26b-a4b-it:minimal | 53.3 | $0.0765 / $0.255 | 1 of 6 benchmarks | 82.2% | ||||||
| 189 | DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | DeepSeek | 53.3 | $0.091 / $0.182 | 1 of 6 benchmarks | 1424 | |||||
| 190 | Qwen3 Maxqwen/qwen3-max | Qwen | 53.1 | — | 4 of 6 benchmarks | 18.9% | 73.3% | 97.1% | 1425 | ||
| 191 | Grok 4 Fastx-ai/grok-4-fast | SpaceXAI | 53.0 | — | 1 of 6 benchmarks | 1424 | |||||
| 192 | DeepSeek V4 Pro 0423 (max)deepseek/deepseek-v4-pro:max | DeepSeek | 53.0 | $0.8837 / $1.7675 | 3 of 6 benchmarks | 45.3% | 2.4% | 96.7% | |||
| 193 | GPT-5.4 Mini (xhigh)openai/gpt-5.4-mini:xhigh | OpenAI | 52.9 | $0.75 / $4.50 | 3 of 6 benchmarks | 51.2% | 9.8% | 88.9% | |||
| 194 | GPT-5.1openai/gpt-5.1 | OpenAI | 52.9 | $1.25 / $10.00 | 1 of 6 benchmarks | 1423 | |||||
| 195 | Qwen3.5-27Bqwen/qwen3.5-27b | Qwen | 52.8 | $0.26 / $2.60 | 1 of 6 benchmarks | 1423 | |||||
| 196 | MiniMax M2.7minimax/minimax-m2.7 | MiniMax | 52.6 | $0.21 / $0.84 | 1 of 6 benchmarks | 1422 | |||||
| 197 | DeepSeek V3.2 Exp (thinking)deepseek/deepseek-v3.2-exp:thinking | DeepSeek | 52.5 | $0.27 / $0.41 | 1 of 6 benchmarks | 1422 | |||||
| 198 | Claude Opus 4 (thinking 16K)anthropic/claude-opus-4:thinking-16k | Anthropic | 52.4 | — | 1 of 6 benchmarks | 1421 | |||||
| 199 | GLM 5.2 (low)z-ai/glm-5.2:low | Z.ai | 52.3 | $0.006 / $6.80 | 2 of 6 benchmarks | 54.7% | 75.6% | ||||
| 200 | Gemini 3.5 Flash (minimal)google/gemini-3.5-flash:minimal | 52.3 | $1.50 / $9.00 | 1 of 6 benchmarks | 80.0% | ||||||
| 201 | Gemini 3.6 Flash (minimal)google/gemini-3.6-flash:minimal | 52.3 | $0.75 / $3.75 | 1 of 6 benchmarks | 80.0% | ||||||
| 202 | Grok 4.1 Fast (reasoning)x-ai/grok-4-1-fast:reasoning | SpaceXAI | 52.3 | — | 1 of 6 benchmarks | 1420 | |||||
| 203 | GPT-5.1 (medium)openai/gpt-5.1:medium | OpenAI | 52.3 | $1.25 / $10.00 | 3 of 6 benchmarks | 26.9% | 4.2% | 85.6% | |||
| 204 | o3 (high)openai/o3:high | OpenAI | 52.2 | $2.00 / $8.00 | 5 of 6 benchmarks | 18.7% | 33.3% | 2.1% | 83.9% | 97.8% | |
| 205 | Grok 4.3x-ai/grok-4.3 | SpaceXAI | 52.1 | $1.25 / $2.50 | 1 of 6 benchmarks | 1418 | |||||
| 206 | o4 Miniopenai/o4-mini | OpenAI | 52.0 | — | 1 of 6 benchmarks | 1418 | |||||
| 207 | Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl | NVIDIA | 51.8 | $0.15 / $0.47 | 1 of 6 benchmarks | 1417 | |||||
| 208 | MiniMax M3minimax/minimax-m3 | MiniMax | 51.7 | $0.30 / $1.20 | 2 of 6 benchmarks | 71.1% | 1425 | ||||
| 209 | Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | Qwen | 51.6 | $0.14 / $0.80 | 1 of 6 benchmarks | 1416 | |||||
| 210 | Kimi K2 0905moonshotai/kimi-k2-0905 | MoonshotAI | 51.5 | $0.60 / $2.50 | 1 of 6 benchmarks | 1416 | |||||
| 211 | Claude Sonnet 4.6 (16K)anthropic/claude-sonnet-4.6:16k | Anthropic | 51.4 | $3.00 / $15.00 | 2 of 6 benchmarks | 80.0% | 0.0% | ||||
| 212 | DeepSeek V3.1 (thinking)deepseek/deepseek-chat-v3.1:thinking | DeepSeek | 51.4 | $0.25 / $0.95 | 1 of 6 benchmarks | 1415 | |||||
| 213 | R1deepseek/deepseek-r1 | DeepSeek | 51.3 | — | 3 of 6 benchmarks | 53.3% | 93.0% | 1412 | |||
| 214 | Solar Pro 4upstage/solar-pro4 | Upstage | 51.3 | $0.15 / $0.60 | 1 of 6 benchmarks | 1414 | |||||
| 215 | Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct | Qwen | 51.1 | $0.09 / $1.10 | 1 of 6 benchmarks | 1414 | |||||
| 216 | LongCat Flash Chatmeituan/longcat-flash-chat | Meituan | 51.0 | — | 1 of 6 benchmarks | 1414 | |||||
| 217 | Claude Opus 4.5 (16K)anthropic/claude-opus-4.5:16k | Anthropic | 50.9 | $5.00 / $25.00 | 3 of 6 benchmarks | 40.0% | 2.1% | 81.7% | |||
| 218 | Claude Sonnet 4.6 (high)anthropic/claude-sonnet-4.6:high | Anthropic | 50.9 | $3.00 / $15.00 | 1 of 6 benchmarks | 75.6% | |||||
| 219 | DeepSeek V3.1deepseek/deepseek-chat-v3.1 | DeepSeek | 50.9 | $0.25 / $0.95 | 1 of 6 benchmarks | 1413 | |||||
| 220 | Grok 4 Fast (reasoning)x-ai/grok-4-fast:reasoning | SpaceXAI | 50.6 | — | 1 of 6 benchmarks | 1412 | |||||
| 221 | Ernie 5.0 Preview 1203baidu/ernie-5.0-preview-1203 | Baidu | 50.4 | — | 1 of 6 benchmarks | 1411 | |||||
| 222 | Claude Opus 4.5 (32K)anthropic/claude-opus-4.5:32k | Anthropic | 50.3 | $5.00 / $25.00 | 4 of 6 benchmarks | 20.7% | 34.4% | 4.9% | 86.1% | ||
| 223 | Gemma 4 31B (minimal)google/gemma-4-31b-it:minimal | 50.3 | $0.20 / $0.40 | 1 of 6 benchmarks | 73.3% | ||||||
| 224 | GPT 5 Chatopenai/gpt-5-chat | OpenAI | 50.3 | — | 1 of 6 benchmarks | 1411 | |||||
| 225 | Claude Sonnet 4.5 (59K)anthropic/claude-sonnet-4.5:59k | Anthropic | 50.2 | $3.00 / $15.00 | 2 of 6 benchmarks | 13.5% | 77.8% | ||||
| 226 | DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp | DeepSeek | 50.1 | $0.27 / $0.41 | 1 of 6 benchmarks | 1410 | |||||
| 227 | Claude Sonnet 4.5 (32K)anthropic/claude-sonnet-4.5:32k | Anthropic | 50.1 | $3.00 / $15.00 | 5 of 6 benchmarks | 15.2% | 23.9% | 2.4% | 77.8% | 97.7% | |
| 228 | Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct | Qwen | 49.9 | $0.21 / $1.90 | 1 of 6 benchmarks | 1409 | |||||
| 229 | Claude Opus 4.5anthropic/claude-opus-4.5 | Anthropic | 49.9 | $5.00 / $25.00 | 4 of 6 benchmarks | 20.7% | 4.2% | 48.1% | 1463 | ||
| 230 | o3 (medium)openai/o3:medium | OpenAI | 49.7 | $2.00 / $8.00 | 3 of 6 benchmarks | 16.9% | 29.8% | 84.4% | |||
| 231 | Claude Sonnet 4 (32K)anthropic/claude-sonnet-4:32k | Anthropic | 49.7 | — | 1 of 6 benchmarks | 71.1% | |||||
| 232 | Claude Sonnet 4.5 (16K)anthropic/claude-sonnet-4.5:16k | Anthropic | 49.7 | $3.00 / $15.00 | 1 of 6 benchmarks | 71.1% | |||||
| 233 | Claude Sonnet 4.6 (max)anthropic/claude-sonnet-4.6:max | Anthropic | 49.7 | $3.00 / $15.00 | 1 of 6 benchmarks | 71.1% | |||||
| 234 | Step 3.5 Flashstepfun/step-3.5-flash | StepFun | 49.5 | $0.10 / $0.30 | 1 of 6 benchmarks | 1406 | |||||
| 235 | GLM 5z-ai/glm-5 | Z.ai | 49.5 | $1.00 / $3.20 | 4 of 6 benchmarks | 16.4% | 2.1% | 80.0% | 1443 | ||
| 236 | DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek | 49.5 | $0.26 / $0.38 | 3 of 6 benchmarks | 22.1% | 2.1% | 1426 | |||
| 237 | Gemini 2.5 Progoogle/gemini-2.5-pro | 49.5 | $1.25 / $10.00 | 6 of 6 benchmarks | 14.1% | 24.6% | 0.0% | 84.7% | 95.6% | 1439 | |
| 238 | Qwen3.7 Plus (none)qwen/qwen3.7-plus:none | Qwen | 49.4 | $0.32 / $1.28 | 2 of 6 benchmarks | 34.4% | 80.0% | ||||
| 239 | GPT-5 (low)openai/gpt-5:low | OpenAI | 49.3 | $1.25 / $10.00 | 1 of 6 benchmarks | 37.2% | |||||
| 240 | Qwen3.5-35B-A3B (none)qwen/qwen3.5-35b-a3b:none | Qwen | 49.2 | $0.14 / $1.00 | 1 of 6 benchmarks | 70.0% | |||||
| 241 | Hunyuan T1tencent/hunyuan-t1 | Tencent | 49.1 | — | 1 of 6 benchmarks | 1405 | |||||
| 242 | GPT-5 Nano (medium)openai/gpt-5-nano:medium | OpenAI | 49.1 | $0.05 / $0.40 | 4 of 6 benchmarks | 10.0% | 2.1% | 74.2% | 95.2% | ||
| 243 | Seed 1.6bytedance-seed/seed-1.6 | ByteDance Seed | 49.1 | $0.25 / $2.00 | 1 of 6 benchmarks | 69.4% | |||||
| 244 | Inkling (xhigh)thinkingmachines/inkling:xhigh | Thinking Machines | 49.0 | $1.00 / $4.05 | 3 of 6 benchmarks | 33.3% | 4.9% | 88.9% | |||
| 245 | Claude Sonnet 4 (thinking 32K)anthropic/claude-sonnet-4:thinking-32k | Anthropic | 49.0 | — | 1 of 6 benchmarks | 1404 | |||||
| 246 | Qwen3.5 397B A17B (none)qwen/qwen3.5-397b-a17b:none | Qwen | 49.0 | $0.60 / $3.60 | 2 of 6 benchmarks | 31.2% | 82.2% | ||||
| 247 | Chatgpt 4oopenai/chatgpt-4o | OpenAI | 48.8 | — | 1 of 6 benchmarks | 1403 | |||||
| 248 | Kimi K3 (low)moonshotai/kimi-k3:low | MoonshotAI | 48.6 | $0.192 / $16.00 | 1 of 6 benchmarks | 68.9% | |||||
| 249 | GPT-5.6 Sol (none)openai/gpt-5.6-sol:none | OpenAI | 48.6 | $4.00 / $20.00 | 1 of 6 benchmarks | 68.9% | |||||
| 250 | Mistral Large 3mistralai/mistral-large-3 | Mistral AI | 48.4 | — | 1 of 6 benchmarks | 1401 | |||||
| 251 | Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking | Qwen | 48.3 | — | 1 of 6 benchmarks | 1399 | |||||
| 252 | GPT-5.1 (low)openai/gpt-5.1:low | OpenAI | 48.0 | $1.25 / $10.00 | 2 of 6 benchmarks | 17.3% | 63.9% | ||||
| 253 | DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus | DeepSeek | 47.9 | $0.27 / $1.00 | 1 of 6 benchmarks | 1396 | |||||
| 254 | Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview | 47.9 | $1.25 / $10.00 | 2 of 6 benchmarks | 30.0% | 2.1% | |||||
| 255 | Mistral Medium 2508mistralai/mistral-medium-2508 | Mistral AI | 47.6 | — | 1 of 6 benchmarks | 1395 | |||||
| 256 | GPT-5.6 Luna (low)openai/gpt-5.6-luna:low | OpenAI | 47.5 | $0.20 / $1.20 | 2 of 6 benchmarks | 41.4% | 66.7% | ||||
| 257 | Ernie 5.0 Preview 1022baidu/ernie-5.0-preview-1022 | Baidu | 47.5 | — | 1 of 6 benchmarks | 1393 | |||||
| 258 | Qwen3 14Bqwen/qwen3-14b | Qwen | 47.5 | $0.12 / $0.24 | 1 of 6 benchmarks | 66.4% | |||||
| 259 | Claude Haiku 4.5 (32K)anthropic/claude-haiku-4.5:32k | Anthropic | 47.4 | $1.00 / $5.00 | 4 of 6 benchmarks | 5.9% | 2.1% | 66.7% | 96.4% | ||
| 260 | o1 (medium)openai/o1:medium | OpenAI | 47.4 | — | 3 of 6 benchmarks | 10.2% | 73.3% | 94.4% | |||
| 261 | Gemini 3.1 Flash Lite (high)google/gemini-3.1-flash-lite:high | 47.4 | $0.25 / $1.50 | 2 of 6 benchmarks | 27.7% | 80.0% | |||||
| 262 | gpt-oss-20b (medium)openai/gpt-oss-20b:medium | OpenAI | 47.3 | $0.03 / $0.13 | 1 of 6 benchmarks | 65.3% | |||||
| 263 | MiniMax M2.5minimax/minimax-m2.5 | MiniMax | 47.3 | $0.30 / $1.20 | 1 of 6 benchmarks | 1392 | |||||
| 264 | Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking | Qwen | 47.1 | — | 1 of 6 benchmarks | 1391 | |||||
| 265 | Qwen3.7 Flashqwen/qwen3.7-flash | Qwen | 47.1 | $0.03 / $0.13 | 2 of 6 benchmarks | 19.3% | 86.7% | ||||
| 266 | Qwen3 235B A22B (nothinking)qwen/qwen3-235b-a22b:nothinking | Qwen | 46.9 | — | 1 of 6 benchmarks | 1391 | |||||
| 267 | Qwen3.6 Plus (none)qwen/qwen3.6-plus:none | Qwen | 46.8 | $0.325 / $1.95 | 1 of 6 benchmarks | 32.3% | |||||
| 268 | Grok 3 Mini Beta (low)x-ai/grok-3-mini-beta:low | SpaceXAI | 46.8 | — | 3 of 6 benchmarks | 2.8% | 62.2% | 90.9% | |||
| 269 | Grok 4 0709x-ai/grok-4-0709 | SpaceXAI | 46.8 | — | 3 of 6 benchmarks | 19.7% | 2.1% | 1425 | |||
| 270 | GPT 5.5 Instantopenai/gpt-5.5-instant | OpenAI | 46.7 | — | 4 of 6 benchmarks | 26.3% | 2.4% | 68.1% | 1462 | ||
| 271 | MiniMax M2.1minimax/minimax-m2.1 | MiniMax | 46.7 | — | 1 of 6 benchmarks | 1390 | |||||
| 272 | o1 (high)openai/o1:high | OpenAI | 46.6 | — | 4 of 6 benchmarks | 9.3% | 14.7% | 73.3% | 94.7% | ||
| 273 | Llama 3.3 Nemotron Super 49B v1.5nvidia/llama-3.3-nemotron-super-49b-v1.5 | NVIDIA | 46.5 | — | 1 of 6 benchmarks | 1389 | |||||
| 274 | GPT-5.2 (none)openai/gpt-5.2:none | OpenAI | 46.4 | $1.75 / $14.00 | 1 of 6 benchmarks | 62.2% | |||||
| 275 | Kimi K2 0711moonshotai/kimi-k2 | MoonshotAI | 46.3 | $0.57 / $2.30 | 1 of 6 benchmarks | 1388 | |||||
| 276 | Qwen3 32Bqwen/qwen3-32b | Qwen | 46.2 | $0.08 / $0.28 | 2 of 6 benchmarks | 66.9% | 1398 | ||||
| 277 | R1 0528deepseek/deepseek-r1-0528 | DeepSeek | 46.2 | $0.50 / $2.15 | 4 of 6 benchmarks | 0.0% | 66.4% | 96.6% | 1392 | ||
| 278 | Qwen3.5-9B (none)qwen/qwen3.5-9b:none | Qwen | 46.2 | $0.17 / $0.25 | 1 of 6 benchmarks | 61.7% | |||||
| 279 | GLM 4.5 Airz-ai/glm-4.5-air | Z.ai | 46.2 | $0.20 / $1.10 | 1 of 6 benchmarks | 1386 | |||||
| 280 | o3 Mini (medium)openai/o3-mini:medium | OpenAI | 46.1 | — | 4 of 6 benchmarks | 11.3% | 10.5% | 63.9% | 95.2% | ||
| 281 | Claude 3.7 Sonnet (thinking 32K)anthropic/claude-3-7-sonnet:thinking-32k | Anthropic | 46.0 | — | 1 of 6 benchmarks | 1386 | |||||
| 282 | Claude Opus 4 (16K)anthropic/claude-opus-4:16k | Anthropic | 45.9 | — | 1 of 6 benchmarks | 60.0% | |||||
| 283 | Trinity Large Thinkingarcee-ai/trinity-large-thinking | Arcee AI | 45.9 | — | 1 of 6 benchmarks | 1382 | |||||
| 284 | Gemini 3.5 Flash Lite (low)google/gemini-3.5-flash-lite:low | 45.9 | $0.30 / $2.50 | 1 of 6 benchmarks | 60.0% | ||||||
| 285 | o3 Miniopenai/o3-mini | OpenAI | 45.8 | — | 1 of 6 benchmarks | 1382 | |||||
| 286 | Claude 3.7 Sonnet (32K)anthropic/claude-3-7-sonnet:32k | Anthropic | 45.8 | — | 3 of 6 benchmarks | 3.5% | 53.3% | 90.0% | |||
| 287 | GPT-5 Nano (high)openai/gpt-5-nano:high | OpenAI | 45.8 | $0.05 / $0.40 | 6 of 6 benchmarks | 20.0% | 20.0% | 2.4% | 81.1% | 94.9% | 1348 |
| 288 | Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b | Qwen | 45.7 | $0.10 / $0.90 | 2 of 6 benchmarks | 17.5% | 86.7% | ||||
| 289 | Qwen3.6 27B (none)qwen/qwen3.6-27b:none | Qwen | 45.7 | $0.32 / $3.20 | 2 of 6 benchmarks | 34.0% | 66.7% | ||||
| 290 | Llama 3.1 Nemotron Ultra 253B v1nvidia/llama-3.1-nemotron-ultra-253b-v1 | NVIDIA | 45.6 | — | 1 of 6 benchmarks | 1381 | |||||
| 291 | gpt-oss-120bopenai/gpt-oss-120b | OpenAI | 45.5 | $0.15 / $0.60 | 1 of 6 benchmarks | 1381 | |||||
| 292 | Qwen3 Coder 480B A35b Instructqwen/qwen3-coder-480b-a35b-instruct | Qwen | 45.3 | — | 1 of 6 benchmarks | 1376 | |||||
| 293 | GPT-5.4 (none)openai/gpt-5.4:none | OpenAI | 45.2 | $2.50 / $15.00 | 1 of 6 benchmarks | 57.8% | |||||
| 294 | GPT-5.5 (none)openai/gpt-5.5:none | OpenAI | 45.2 | $5.00 / $30.00 | 1 of 6 benchmarks | 57.8% | |||||
| 295 | Mimo v2 Flashxiaomi/mimo-v2-flash | Xiaomi | 45.1 | — | 1 of 6 benchmarks | 1375 | |||||
| 296 | Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507 | Qwen | 45.1 | $0.45 / $3.50 | 4 of 6 benchmarks | 20.0% | 0.0% | 86.7% | 1396 | ||
| 297 | Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning-30b-a3b | NVIDIA | 45.0 | — | 1 of 6 benchmarks | 1375 | |||||
| 298 | INTELLECT-3prime-intellect/intellect-3 | Prime Intellect | 44.8 | — | 1 of 6 benchmarks | 1374 | |||||
| 299 | Mimo v2 Flash (thinking)xiaomi/mimo-v2-flash:thinking | Xiaomi | 44.6 | — | 1 of 6 benchmarks | 1372 | |||||
| 300 | GLM 5.1 (none)z-ai/glm-5.1:none | Z.ai | 44.6 | $1.40 / $4.40 | 1 of 6 benchmarks | 24.9% | |||||
| 301 | o3 Mini Highopenai/o3-mini-high | OpenAI | 44.6 | — | 6 of 6 benchmarks | 12.4% | 18.6% | 0.0% | 76.9% | 96.5% | 1405 |
| 302 | Grok 3 Mini Betax-ai/grok-3-mini-beta | SpaceXAI | 44.4 | — | 1 of 6 benchmarks | 1370 | |||||
| 303 | Claude Opus 4.1anthropic/claude-opus-4.1 | Anthropic | 44.3 | $15.00 / $75.00 | 3 of 6 benchmarks | 5.9% | 40.0% | 1433 | |||
| 304 | o1openai/o1 | OpenAI | 44.3 | — | 3 of 6 benchmarks | 31.1% | 81.7% | 1409 | |||
| 305 | Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b | NVIDIA | 44.3 | $0.075 / $0.40 | 1 of 6 benchmarks | 1370 | |||||
| 306 | Claude Sonnet 4 (16K)anthropic/claude-sonnet-4:16k | Anthropic | 44.3 | — | 1 of 6 benchmarks | 53.3% | |||||
| 307 | GPT-5.6 Terra (none)openai/gpt-5.6-terra:none | OpenAI | 44.3 | $2.00 / $12.00 | 1 of 6 benchmarks | 53.3% | |||||
| 308 | GPT-5.4 Mini (low)openai/gpt-5.4-mini:low | OpenAI | 44.2 | $0.75 / $4.50 | 1 of 6 benchmarks | 24.6% | |||||
| 309 | Claude 3.7 Sonnet (16K)anthropic/claude-3-7-sonnet:16k | Anthropic | 44.2 | — | 3 of 6 benchmarks | 4.1% | 46.7% | 86.3% | |||
| 310 | MiniMax M1minimax/minimax-m1 | MiniMax | 44.1 | — | 1 of 6 benchmarks | 1370 | |||||
| 311 | GPT 4.5 Previewopenai/gpt-4.5-preview | OpenAI | 44.1 | — | 3 of 6 benchmarks | 37.8% | 78.6% | 1407 | |||
| 312 | Gemini 3.5 Flash Lite (minimal)google/gemini-3.5-flash-lite:minimal | 43.9 | $0.30 / $2.50 | 1 of 6 benchmarks | 51.1% | ||||||
| 313 | Qwen3.7 Flash (none)qwen/qwen3.7-flash:none | Qwen | 43.9 | $0.03 / $0.13 | 2 of 6 benchmarks | 19.3% | 77.8% | ||||
| 314 | Gemini 2.5 Flash Lite (thinking)google/gemini-2.5-flash-lite:thinking | 43.8 | $0.10 / $0.40 | 1 of 6 benchmarks | 1364 | ||||||
| 315 | gpt-oss-20b (high)openai/gpt-oss-20b:high | OpenAI | 43.8 | $0.03 / $0.13 | 1 of 6 benchmarks | 50.8% | |||||
| 316 | Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b | Qwen | 43.6 | $0.14 / $1.00 | 2 of 6 benchmarks | 54.4% | 1397 | ||||
| 317 | Qwen3.6 Flash (none)qwen/qwen3.6-flash:none | Qwen | 43.4 | $0.1875 / $1.125 | 1 of 6 benchmarks | 22.5% | |||||
| 318 | Trinity Large Previewarcee-ai/trinity-large-preview | Arcee AI | 43.4 | — | 1 of 6 benchmarks | 1362 | |||||
| 319 | Qwen 2.5 (max)qwen/qwen-2.5:max | Qwen | 43.3 | — | 1 of 6 benchmarks | 1362 | |||||
| 320 | O1 Miniopenai/o1-mini | OpenAI | 43.1 | — | 1 of 6 benchmarks | 1361 | |||||
| 321 | Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | MoonshotAI | 43.1 | $0.60 / $2.50 | 2 of 6 benchmarks | 21.4% | 0.0% | ||||
| 322 | O1 Mini (high)openai/o1-mini:high | OpenAI | 43.1 | — | 3 of 6 benchmarks | 1.4% | 46.9% | 89.2% | |||
| 323 | Claude Haiku 4.5anthropic/claude-haiku-4.5 | Anthropic | 43.0 | $1.00 / $5.00 | 4 of 6 benchmarks | 4.1% | 35.8% | 86.9% | 1402 | ||
| 324 | Gemini 2.5 Flash Lite (nothinking)google/gemini-2.5-flash-lite:nothinking | 43.0 | $0.10 / $0.40 | 1 of 6 benchmarks | 1361 | ||||||
| 325 | DeepSeek V4 Pro 0423 (none)deepseek/deepseek-v4-pro:none | DeepSeek | 43.0 | $0.8837 / $1.7675 | 1 of 6 benchmarks | 46.7% | |||||
| 326 | Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | Qwen | 43.0 | $0.10 / $0.30 | 2 of 6 benchmarks | 62.2% | 1378 | ||||
| 327 | Claude Opus 4.1 (27K)anthropic/claude-opus-4.1:27k | Anthropic | 42.9 | $15.00 / $75.00 | 3 of 6 benchmarks | 7.2% | 4.2% | 68.9% | |||
| 328 | GLM 4.5Vz-ai/glm-4.5v | Z.ai | 42.9 | $0.60 / $1.80 | 1 of 6 benchmarks | 1360 | |||||
| 329 | Step 3stepfun/step-3 | StepFun | 42.8 | — | 1 of 6 benchmarks | 1360 | |||||
| 330 | o4 Mini (medium)openai/o4-mini:medium | OpenAI | 42.8 | — | 4 of 6 benchmarks | 19.0% | 28.8% | 2.1% | 73.3% | ||
| 331 | Gemini 2.5 Flashgoogle/gemini-2.5-flash | 42.8 | $0.30 / $2.50 | 4 of 6 benchmarks | 4.8% | 4.2% | 70.8% | 1405 | |||
| 332 | GPT-5.6 Luna (none)openai/gpt-5.6-luna:none | OpenAI | 42.7 | $0.20 / $1.20 | 2 of 6 benchmarks | 39.6% | 40.0% | ||||
| 333 | Grok 3 Mini Beta (high)x-ai/grok-3-mini-beta:high | SpaceXAI | 42.7 | — | 5 of 6 benchmarks | 5.9% | 0.0% | 77.8% | 88.1% | 1389 | |
| 334 | MiniMax M2minimax/minimax-m2 | MiniMax | 42.5 | — | 1 of 6 benchmarks | 1354 | |||||
| 335 | GPT-5.4 Nano (low)openai/gpt-5.4-nano:low | OpenAI | 42.5 | $0.20 / $1.25 | 2 of 6 benchmarks | 20.4% | 68.9% | ||||
| 336 | Qwen3.6 35B A3B (none)qwen/qwen3.6-35b-a3b:none | Qwen | 42.5 | $0.10 / $0.90 | 2 of 6 benchmarks | 20.4% | 68.9% | ||||
| 337 | Qwen3.5-9Bqwen/qwen3.5-9b | Qwen | 42.1 | $0.17 / $0.25 | 1 of 6 benchmarks | 42.8% | |||||
| 338 | gpt-oss-20b (low)openai/gpt-oss-20b:low | OpenAI | 41.9 | $0.03 / $0.13 | 1 of 6 benchmarks | 40.3% | |||||
| 339 | Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | NVIDIA | 41.8 | $0.06 / $0.24 | 1 of 6 benchmarks | 1347 | |||||
| 340 | GLM 5.2 (none)z-ai/glm-5.2:none | Z.ai | 41.7 | $0.006 / $6.80 | 2 of 6 benchmarks | 42.5% | 28.9% | ||||
| 341 | Hunyuan TurboStencent/hunyuan-turbos | Tencent | 41.7 | — | 1 of 6 benchmarks | 1344 | |||||
| 342 | GLM 4.7z-ai/glm-4.7 | Z.ai | 41.6 | $0.60 / $2.20 | 4 of 6 benchmarks | 2.4% | 0.0% | 83.3% | 1427 | ||
| 343 | Ling Flash 2.0inclusionai/ling-flash-2.0 | inclusionAI | 41.5 | — | 1 of 6 benchmarks | 1344 | |||||
| 344 | GLM 4.6z-ai/glm-4.6 | Z.ai | 41.4 | $0.50 / $2.00 | 3 of 6 benchmarks | 3.8% | 2.1% | 1418 | |||
| 345 | Ring Flash 2.0inclusionai/ring-flash-2.0 | inclusionAI | 41.2 | — | 1 of 6 benchmarks | 1338 | |||||
| 346 | QwQ 32Bqwen/qwq-32b | Qwen | 41.1 | — | 2 of 6 benchmarks | 59.2% | 1363 | ||||
| 347 | gpt-oss-20bopenai/gpt-oss-20b | OpenAI | 41.0 | $0.03 / $0.13 | 1 of 6 benchmarks | 1335 | |||||
| 348 | Nova 2 Liteamazon/nova-2-lite-v1 | Amazon | 40.9 | $0.30 / $2.50 | 1 of 6 benchmarks | 1329 | |||||
| 349 | GLM 4.7 Flashz-ai/glm-4.7-flash | Z.ai | 40.9 | $0.0605 / $0.40 | 2 of 6 benchmarks | 58.3% | 1362 | ||||
| 350 | O1 Mini (medium)openai/o1-mini:medium | OpenAI | 40.8 | — | 3 of 6 benchmarks | 1.7% | 44.7% | 84.3% | |||
| 351 | Gemini 2.0 Flash Lite Preview 02 05google/gemini-2.0-flash-lite-preview-02-05 | 40.8 | — | 1 of 6 benchmarks | 1327 | ||||||
| 352 | Qwen3 30B A3Bqwen/qwen3-30b-a3b | Qwen | 40.7 | $0.12 / $0.50 | 2 of 6 benchmarks | 62.8% | 1351 | ||||
| 353 | Claude Opus 4 (27K)anthropic/claude-opus-4:27k | Anthropic | 40.4 | — | 3 of 6 benchmarks | 4.1% | 4.2% | 64.4% | |||
| 354 | Granite 4.1 8Bibm-granite/granite-4.1-8b | IBM | 40.3 | — | 1 of 6 benchmarks | 1318 | |||||
| 355 | GPT-5 Mini (low)openai/gpt-5-mini:low | OpenAI | 40.3 | $0.25 / $2.00 | 1 of 6 benchmarks | 18.3% | |||||
| 356 | Qwen3.5-Flash (none)qwen/qwen3.5-flash-02-23:none | Qwen | 40.3 | $0.065 / $0.26 | 1 of 6 benchmarks | 18.3% | |||||
| 357 | Qwen3.6 Flashqwen/qwen3.6-flash | Qwen | 40.2 | $0.1875 / $1.125 | 4 of 6 benchmarks | 20.0% | 17.2% | 0.0% | 84.4% | ||
| 358 | Claude 3.7 Sonnet (64K)anthropic/claude-3-7-sonnet:64k | Anthropic | 40.1 | — | 4 of 6 benchmarks | 3.1% | 0.0% | 57.8% | 91.2% | ||
| 359 | OLMo 3 32B Thinkallenai/olmo-3-32b-think | Allen Institute for AI | 39.9 | — | 1 of 6 benchmarks | 1311 | |||||
| 360 | o3 (low)openai/o3:low | OpenAI | 39.8 | $2.00 / $8.00 | 3 of 6 benchmarks | 9.7% | 19.3% | 60.0% | |||
| 361 | Command A (03-2025)cohere/command-a-03-2025 | Cohere | 39.8 | — | 1 of 6 benchmarks | 1310 | |||||
| 362 | Claude Sonnet 4.5anthropic/claude-sonnet-4.5 | Anthropic | 39.7 | $3.00 / $15.00 | 4 of 6 benchmarks | 9.3% | 2.1% | 35.6% | 1427 | ||
| 363 | MiniMax M3 (none)minimax/minimax-m3:none | MiniMax | 39.4 | $0.30 / $1.20 | 1 of 6 benchmarks | 26.7% | |||||
| 364 | Qwen3 14B (none)qwen/qwen3-14b:none | Qwen | 39.2 | $0.12 / $0.24 | 1 of 6 benchmarks | 25.8% | |||||
| 365 | Qwen3 30B A3B (none)qwen/qwen3-30b-a3b:none | Qwen | 39.1 | $0.12 / $0.50 | 1 of 6 benchmarks | 25.6% | |||||
| 366 | OLMo 3.1 32B Thinkallenai/olmo-3.1-32b-think | Allen Institute for AI | 39.0 | — | 1 of 6 benchmarks | 1302 | |||||
| 367 | GLM 4.7 Flash (none)z-ai/glm-4.7-flash:none | Z.ai | 39.0 | $0.0605 / $0.40 | 1 of 6 benchmarks | 25.0% | |||||
| 368 | OLMo 3.1 32B Instructallenai/olmo-3.1-32b-instruct | Allen Institute for AI | 38.8 | — | 1 of 6 benchmarks | 1298 | |||||
| 369 | Qwen3 32B (none)qwen/qwen3-32b:none | Qwen | 38.8 | $0.08 / $0.28 | 1 of 6 benchmarks | 23.1% | |||||
| 370 | o4 Mini (low)openai/o4-mini:low | OpenAI | 38.5 | — | 3 of 6 benchmarks | 10.7% | 16.1% | 57.8% | |||
| 371 | Claude Opus 4anthropic/claude-opus-4 | Anthropic | 38.5 | — | 5 of 6 benchmarks | 4.5% | 0.0% | 42.2% | 85.0% | 1403 | |
| 372 | Gemini 3.1 Flash Lite (low)google/gemini-3.1-flash-lite:low | 38.4 | $0.25 / $1.50 | 2 of 6 benchmarks | 22.5% | 44.4% | |||||
| 373 | Step 1o Turbo 202506stepfun/step-1o-turbo-202506 | StepFun | 38.3 | — | 1 of 6 benchmarks | 1295 | |||||
| 374 | Claude Sonnet 4 (59K)anthropic/claude-sonnet-4:59k | Anthropic | 38.3 | — | 2 of 6 benchmarks | 0.0% | 68.9% | ||||
| 375 | GPT-4.1 Miniopenai/gpt-4.1-mini | OpenAI | 38.0 | $0.40 / $1.60 | 5 of 6 benchmarks | 10.0% | 6.7% | 44.7% | 87.3% | 1353 | |
| 376 | Grok 3 Betax-ai/grok-3-beta | SpaceXAI | 38.0 | — | 5 of 6 benchmarks | 3.8% | 0.0% | 55.6% | 88.8% | 1371 | |
| 377 | Magistral Medium 2506mistralai/magistral-medium-2506 | Mistral AI | 37.8 | — | 1 of 6 benchmarks | 1287 | |||||
| 378 | Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | Qwen | 37.6 | $0.065 / $0.26 | 5 of 6 benchmarks | 10.0% | 9.5% | 0.0% | 84.4% | 1401 | |
| 379 | GPT-4openai/gpt-4 | OpenAI | 37.5 | $30.00 / $60.00 | 1 of 6 benchmarks | 1285 | |||||
| 380 | Gemini 3.5 Flash Lite (high)google/gemini-3.5-flash-lite:high | 37.5 | $0.30 / $2.50 | 3 of 6 benchmarks | 26.0% | 0.0% | 71.1% | ||||
| 381 | Qwen3 235B A22Bqwen/qwen3-235b-a22b | Qwen | 37.4 | — | 3 of 6 benchmarks | 0.0% | 68.9% | 1391 | |||
| 382 | Hunyuan Large Visiontencent/hunyuan-large-vision | Tencent | 37.3 | — | 1 of 6 benchmarks | 1280 | |||||
| 383 | Gemini 3.1 Flash Lite (minimal)google/gemini-3.1-flash-lite:minimal | 37.2 | $0.25 / $1.50 | 2 of 6 benchmarks | 21.4% | 37.8% | |||||
| 384 | Qwen2.5 Coder 32B Instructqwen/qwen2.5-coder-32b-instruct | Qwen | 36.8 | — | 1 of 6 benchmarks | 1269 | |||||
| 385 | Gemini 1.5 Pro 002google/gemini-1.5-pro-002 | 36.5 | — | 3 of 6 benchmarks | 23.1% | 70.4% | 1340 | ||||
| 386 | GPT-5 (minimal)openai/gpt-5:minimal | OpenAI | 36.5 | $1.25 / $10.00 | 2 of 6 benchmarks | 18.3% | 46.7% | ||||
| 387 | Gemma 3 27Bgoogle/gemma-3-27b-it | 36.5 | $0.08 / $0.45 | 3 of 6 benchmarks | 22.5% | 74.0% | 1323 | ||||
| 388 | Amazon Nova Pro v1.0amazon/amazon-nova-pro-v1.0 | Amazon | 36.5 | — | 1 of 6 benchmarks | 1269 | |||||
| 389 | Gemini 2.0 Flash 001google/gemini-2.0-flash-001 | 36.5 | — | 4 of 6 benchmarks | 1.7% | 31.1% | 82.2% | 1356 | |||
| 390 | Gemma 3n E4Bgoogle/gemma-3n-e4b-it | 36.3 | — | 1 of 6 benchmarks | 1260 | ||||||
| 391 | Claude Sonnet 4anthropic/claude-sonnet-4 | Anthropic | 36.0 | — | 5 of 6 benchmarks | 4.1% | 0.0% | 28.9% | 84.4% | 1390 | |
| 392 | Claude Opus 4.1 (16K)anthropic/claude-opus-4.1:16k | Anthropic | 36.0 | $15.00 / $75.00 | 2 of 6 benchmarks | 0.0% | 64.4% | ||||
| 393 | GPT-5.1 (none)openai/gpt-5.1:none | OpenAI | 36.0 | $1.25 / $10.00 | 2 of 6 benchmarks | 2.1% | 37.8% | ||||
| 394 | Mistral Largemistralai/mistral-large | Mistral | 35.8 | $2.00 / $6.00 | 1 of 6 benchmarks | 1245 | |||||
| 395 | Amazon Nova Lite v1.0amazon/amazon-nova-lite-v1.0 | Amazon | 35.7 | — | 1 of 6 benchmarks | 1244 | |||||
| 396 | Claude Opus 4.1 (32K)anthropic/claude-opus-4.1:32k | Anthropic | 35.4 | $15.00 / $75.00 | 2 of 6 benchmarks | 12.6% | 2.4% | ||||
| 397 | Command R+ (08-2024)cohere/command-r-plus-08-2024 | Cohere | 35.4 | $2.50 / $10.00 | 1 of 6 benchmarks | 1232 | |||||
| 398 | o1 (low)openai/o1:low | OpenAI | 35.3 | — | 2 of 6 benchmarks | 8.4% | 53.3% | ||||
| 399 | Mistral Small 2506mistralai/mistral-small-2506 | Mistral AI | 35.1 | — | 2 of 6 benchmarks | 30.3% | 1338 | ||||
| 400 | GPT-5 Mini (minimal)openai/gpt-5-mini:minimal | OpenAI | 35.1 | $0.25 / $2.00 | 2 of 6 benchmarks | 6.0% | 55.6% | ||||
| 401 | OLMo 2 0325 32B Instructallenai/olmo-2-0325-32b-instruct | Allen Institute for AI | 35.0 | — | 1 of 6 benchmarks | 1227 | |||||
| 402 | Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct | Qwen | 34.9 | $0.10 / $0.20 | 1 of 6 benchmarks | 2.5% | |||||
| 403 | Amazon Nova Micro v1.0amazon/amazon-nova-micro-v1.0 | Amazon | 34.9 | — | 1 of 6 benchmarks | 1223 | |||||
| 404 | Claude 3.7 Sonnetanthropic/claude-3-7-sonnet | Anthropic | 34.8 | — | 4 of 6 benchmarks | 3.1% | 21.9% | 68.2% | 1364 | ||
| 405 | QwQ 32B Previewqwen/qwq-32b-preview | Qwen | 34.8 | — | 1 of 6 benchmarks | 1209 | |||||
| 406 | Command R (08-2024)cohere/command-r-08-2024 | Cohere | 34.7 | $0.15 / $0.60 | 1 of 6 benchmarks | 1208 | |||||
| 407 | Mistral Nemomistralai/mistral-nemo | Mistral | 34.5 | $0.029 / $0.03 | 1 of 6 benchmarks | 10.8% | |||||
| 408 | Mistral Medium 2505mistralai/mistral-medium-2505 | Mistral AI | 34.4 | — | 4 of 6 benchmarks | 0.3% | 32.2% | 81.6% | 1347 | ||
| 409 | DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 | DeepSeek | 34.1 | $0.29 / $1.14 | 4 of 6 benchmarks | 0.0% | 37.8% | 75.5% | 1367 | ||
| 410 | GPT-5 Nano (low)openai/gpt-5-nano:low | OpenAI | 33.7 | $0.05 / $0.40 | 2 of 6 benchmarks | 6.0% | 46.7% | ||||
| 411 | DeepSeek V3deepseek/deepseek-chat | DeepSeek | 33.6 | $0.32 / $0.89 | 4 of 6 benchmarks | 1.7% | 48.9% | 64.8% | 1310 | ||
| 412 | GPT-5.4 Nano (none)openai/gpt-5.4-nano:none | OpenAI | 33.3 | $0.20 / $1.25 | 2 of 6 benchmarks | 4.6% | 46.7% | ||||
| 413 | GPT-5.4 Mini (none)openai/gpt-5.4-mini:none | OpenAI | 33.1 | $0.75 / $4.50 | 2 of 6 benchmarks | 17.2% | 26.7% | ||||
| 414 | Gemma 3 12Bgoogle/gemma-3-12b-it | 33.0 | $0.05 / $0.15 | 2 of 6 benchmarks | 16.7% | 1318 | |||||
| 415 | o3 Mini (low)openai/o3-mini:low | OpenAI | 32.6 | — | 2 of 6 benchmarks | 3.9% | 44.4% | ||||
| 416 | GPT 4 1106 Previewopenai/gpt-4-1106-preview | OpenAI | 32.5 | — | 2 of 6 benchmarks | 40.0% | 1303 | ||||
| 417 | GPT-4.1openai/gpt-4.1 | OpenAI | 32.4 | $2.00 / $8.00 | 6 of 6 benchmarks | 5.5% | 6.0% | 0.0% | 38.3% | 83.0% | 1374 |
| 418 | GLM 4.5z-ai/glm-4.5 | Z.ai | 32.3 | $0.60 / $2.20 | 3 of 6 benchmarks | 0.0% | 0.0% | 1411 | |||
| 419 | Grok 2 1212x-ai/grok-2-1212 | SpaceXAI | 32.2 | — | 3 of 6 benchmarks | 0.7% | 11.5% | 63.5% | |||
| 420 | Llama 4 Maverick 17B 128e Instructmeta-llama/llama-4-maverick-17b-128e-instruct | Meta | 31.8 | — | 4 of 6 benchmarks | 0.7% | 20.6% | 73.0% | 1317 | ||
| 421 | Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct | Qwen | 31.7 | $0.36 / $0.40 | 3 of 6 benchmarks | 8.1% | 63.2% | 1296 | |||
| 422 | Qwen-Plusqwen/qwen-plus | Qwen | 31.6 | $0.26 / $0.78 | 4 of 6 benchmarks | 1.7% | 17.8% | 65.3% | 1322 | ||
| 423 | GPT-5 Nano (minimal)openai/gpt-5-nano:minimal | OpenAI | 31.1 | $0.05 / $0.40 | 2 of 6 benchmarks | 1.8% | 35.6% | ||||
| 424 | GPT-4.1 Nanoopenai/gpt-4.1-nano | OpenAI | 30.8 | $0.10 / $0.40 | 4 of 6 benchmarks | 1.0% | 28.9% | 70.0% | 1273 | ||
| 425 | Magistral Small 2506mistralai/magistral-small-2506 | Mistral AI | 30.7 | — | 2 of 6 benchmarks | 0.0% | 30.0% | ||||
| 426 | GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13 | OpenAI | 29.8 | $5.00 / $15.00 | 3 of 6 benchmarks | 6.3% | 51.0% | 1305 | |||
| 427 | Qwen (max)qwen/qwen:max | Qwen | 29.8 | — | 4 of 6 benchmarks | 1.0% | 16.1% | 67.2% | 1291 | ||
| 428 | Gemma 3 4Bgoogle/gemma-3-4b-it | 28.8 | — | 2 of 6 benchmarks | 7.5% | 1254 | |||||
| 429 | Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct | Mistral | 28.1 | $2.00 / $6.00 | 2 of 6 benchmarks | 24.2% | 1228 | ||||
| 430 | Mistral Large 2407mistralai/mistral-large-2407 | Mistral | 28.0 | $2.00 / $6.00 | 3 of 6 benchmarks | 8.5% | 44.8% | 1288 | |||
| 431 | GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | OpenAI | 28.0 | $2.50 / $10.00 | 3 of 6 benchmarks | 0.3% | 6.3% | 49.8% | |||
| 432 | Gemini 1.5 Pro 001google/gemini-1.5-pro-001 | 27.4 | — | 3 of 6 benchmarks | 6.8% | 40.8% | 1300 | ||||
| 433 | Gemini 1.5 Flash 8B 001google/gemini-1.5-flash-8b-001 | 27.3 | — | 2 of 6 benchmarks | 4.6% | 1230 | |||||
| 434 | Mistral Small 3.1 24B Instruct 2503mistralai/mistral-small-3.1-24b-instruct-2503 | Mistral AI | 27.2 | — | 3 of 6 benchmarks | 3.9% | 46.8% | 1277 | |||
| 435 | Llama 4 Scout 17B 16e Instructmeta-llama/llama-4-scout-17b-16e-instruct | Meta | 27.2 | — | 4 of 6 benchmarks | 0.0% | 7.8% | 62.3% | 1310 | ||
| 436 | Claude 3 Opusanthropic/claude-3-opus | Anthropic | 27.0 | — | 3 of 6 benchmarks | 4.7% | 37.5% | 1313 | |||
| 437 | Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct | Meta | 26.9 | $0.59 / $0.79 | 3 of 6 benchmarks | 5.1% | 41.6% | 1296 | |||
| 438 | Claude 3.5 Sonnetanthropic/claude-3-5-sonnet | Anthropic | 26.8 | — | 5 of 6 benchmarks | 1.0% | 0.0% | 8.5% | 57.0% | 1352 | |
| 439 | Claude 2anthropic/claude-2 | Anthropic | 26.5 | — | 2 of 6 benchmarks | 2.5% | 11.7% | ||||
| 440 | Gemini 1.5 Flash 002google/gemini-1.5-flash-002 | 26.5 | — | 4 of 6 benchmarks | 0.0% | 16.3% | 61.9% | 1289 | |||
| 441 | Mistral Small 24B Instruct 2501mistralai/mistral-small-24b-instruct-2501 | Mistral AI | 26.5 | — | 3 of 6 benchmarks | 6.7% | 44.8% | 1261 | |||
| 442 | Mistral Large 2411mistralai/mistral-large-2411 | Mistral AI | 25.5 | — | 4 of 6 benchmarks | 0.3% | 7.8% | 50.3% | 1282 | ||
| 443 | GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18 | OpenAI | 24.5 | $0.15 / $0.60 | 4 of 6 benchmarks | 0.7% | 6.9% | 52.6% | 1275 | ||
| 444 | Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct | Meta | 24.3 | — | 3 of 6 benchmarks | 3.6% | 36.7% | 1269 | |||
| 445 | GPT-4 Turboopenai/gpt-4-turbo | OpenAI | 24.0 | — | 4 of 6 benchmarks | 0.7% | 6.7% | 46.7% | 1296 | ||
| 446 | Claude 3.5 Haikuanthropic/claude-3-5-haiku | Anthropic | 23.9 | — | 4 of 6 benchmarks | 0.3% | 4.3% | 46.4% | 1287 | ||
| 447 | Gemini 1.5 Flash 001google/gemini-1.5-flash-001 | 23.9 | — | 3 of 6 benchmarks | 3.9% | 25.1% | 1259 | ||||
| 448 | GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | OpenAI | 22.9 | $2.50 / $10.00 | 5 of 6 benchmarks | 0.3% | 0.3% | 6.4% | 53.3% | 1309 | |
| 449 | Claude 3 Sonnetanthropic/claude-3-sonnet | Anthropic | 22.6 | — | 3 of 6 benchmarks | 2.5% | 18.2% | 1254 | |||
| 450 | Claude 3 Haikuanthropic/claude-3-haiku | Anthropic | 21.9 | — | 3 of 6 benchmarks | 1.8% | 14.9% | 1232 | |||
| 451 | Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | Meta | 21.8 | $0.02 / $0.04 | 3 of 6 benchmarks | 1.7% | 22.9% | 1188 |
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 6 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.
- Epoch AI Benchmarking HubCC BY 4.0
Benchmark runs by Epoch AI, from the AI Benchmarking Hub.
- LMArenaCC BY 4.0
Arena ratings by LMArena, from the public leaderboard dataset.