llm leaderboard

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.

493 of 493 ranked models
Ranked models
rankmodelvendorcompositepricein / outbenchmarks%%%%%%%%%%%eloelo%count
1
GPT-6 Astra (max)openai/gpt-6-astra:max
OpenAI84.6$10.00 / $50.005 of 15 benchmarks73.2%53.3%76.2%15481767
2
Claude Opus 5.5 (high)anthropic/claude-opus-5.5:high
Anthropic81.4$4.00 / $20.003 of 15 benchmarks54.0%78.9%1546
3
Claude Opus 5.5 (max)anthropic/claude-opus-5.5:max
Anthropic80.1$4.00 / $20.003 of 15 benchmarks54.4%71.4%1818
4
Claude Fable 5.1 (max)anthropic/claude-fable-5.1:max
Anthropic79.3$10.00 / $50.004 of 15 benchmarks50.3%57.1%15341744
5
Claude Fable 5 (high)anthropic/claude-fable-5:high
Anthropic78.8$10.00 / $50.005 of 15 benchmarks68.6%52.7%63.9%15511625
6
Claude Opus 5 (max)anthropic/claude-opus-5:max
Anthropic78.2$5.00 / $25.005 of 15 benchmarks73.7%48.0%45.7%15281691
7
Claude Sonnet 5.5 (xhigh)anthropic/claude-sonnet-5.5:xhigh
Anthropic78.1$2.00 / $10.003 of 15 benchmarks52.1%15171773
8
Gemini 4 Carbon (high)google/gemini-4-carbon:high
Google77.6—2 of 15 benchmarks15671768
9
Claude Opus 5 (high)anthropic/claude-opus-5:high
Anthropic77.4$5.00 / $25.004 of 15 benchmarks72.8%48.0%15321656
10
Claude Opus 4.6anthropic/claude-opus-4.6
Anthropic76.9$5.00 / $25.004 of 15 benchmarks78.7%72.0%15471537
11
Gemini 4 Argon (high)google/gemini-4-argon:high
Google76.6$2.00 / $10.005 of 15 benchmarks45.9%58.9%64.8%15531683
12
GPT-6.1 Sol (max)openai/gpt-6.1-sol:max
OpenAI76.5$2.00 / $10.004 of 15 benchmarks47.6%54.3%15411743
13
Kimi K3 (max)moonshotai/kimi-k3:max
MoonshotAI75.9$0.192 / $16.005 of 15 benchmarks68.5%1537165737.2%44.0
14
GPT-6 Astra (xhigh)openai/gpt-6-astra:xhigh
OpenAI75.7$10.00 / $50.002 of 15 benchmarks74.1%50.6%
15
GPT-6.1 Terra (max)openai/gpt-6.1-terra:max
OpenAI75.3$1.00 / $5.002 of 15 benchmarks78.1%1678
16
GPT-6 Sol (max)openai/gpt-6-sol:max
OpenAI74.9$2.00 / $10.004 of 15 benchmarks49.3%53.3%15191674
17
Claude Opus 4.5anthropic/claude-opus-4.5
Anthropic74.6$5.00 / $25.005 of 15 benchmarks76.7%52.6%70.7%15231469
18
GPT-6 Astra (high)openai/gpt-6-astra:high
OpenAI74.1$10.00 / $50.003 of 15 benchmarks73.2%50.9%46.7%
19
GPT-5.6 Sol (xhigh)openai/gpt-5.6-sol:xhigh
OpenAI73.8$4.00 / $20.004 of 15 benchmarks70.7%46.8%15331615
20
Claude Fable 5.1 (high)anthropic/claude-fable-5.1:high
Anthropic73.7$10.00 / $50.002 of 15 benchmarks50.3%73.3%
21
Claude Sonnet 5.5 (high)anthropic/claude-sonnet-5.5:high
Anthropic73.3$2.00 / $10.002 of 15 benchmarks49.4%1713
22
Claude Fable 5 (xhigh)anthropic/claude-fable-5:xhigh
Anthropic73.3$10.00 / $50.002 of 15 benchmarks69.9%53.5%
23
Muse Spark 1.3 (max)meta/muse-spark-1.3:max
Meta73.3$1.25 / $4.252 of 15 benchmarks15321654
24
DeepSeek V4.1 Flash (max)deepseek/deepseek-v4.1-flash:max
DeepSeek73.1$0.051 / $0.5672 of 15 benchmarks15251664
25
MiMo-V2.6-Proxiaomi/mimo-v2.6-pro
Xiaomi72.8$0.435 / $0.872 of 15 benchmarks15381624
26
Claude Opus 5 (medium)anthropic/claude-opus-5:medium
Anthropic71.3$5.00 / $25.002 of 15 benchmarks68.9%53.4%
27
GPT-6 Astra (medium)openai/gpt-6-astra:medium
OpenAI71.2$10.00 / $50.002 of 15 benchmarks72.8%48.8%
28
Claude Fable 5.2anthropic/claude-fable-5.2
Anthropic70.6$8.00 / $40.001 of 15 benchmarks69.9%
29
Claude Fable 5.2 (max)anthropic/claude-fable-5.2:max
Anthropic70.6$8.00 / $40.001 of 15 benchmarks90.5%
30
Claude Opus 5.5 (medium)anthropic/claude-opus-5.5:medium
Anthropic70.6$4.00 / $20.001 of 15 benchmarks54.6%
31
o4 Mini Highopenai/o4-mini-high
OpenAI70.6—1 of 15 benchmarks80.2%
32
GPT 5.5 Pre Release (xhigh)openai/gpt-5.5-pre-release:xhigh
OpenAI70.2—1 of 15 benchmarks80.6%
33
Muse Wonder (max)meta/muse-wonder:max
Meta70.0$4.00 / $20.003 of 15 benchmarks31.4%15461650
34
Claude Opus 4.7anthropic/claude-opus-4.7
Anthropic69.8$5.00 / $25.002 of 15 benchmarks15461555
35
Claude Fable 5 (max)anthropic/claude-fable-5:max
Anthropic69.8$10.00 / $50.003 of 15 benchmarks69.7%51.6%39.5%
36
Claude Opus 4.5 (medium)anthropic/claude-opus-4.5:medium
Anthropic69.5$5.00 / $25.001 of 15 benchmarks79.2%
37
MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash
Xiaomi69.3$0.14 / $0.282 of 15 benchmarks15111636
38
o3 (high)openai/o3:high
OpenAI69.3$2.00 / $8.001 of 15 benchmarks75.8%
39
Gemini 3 Flash Previewgoogle/gemini-3-flash-preview
Google69.2$0.50 / $3.004 of 15 benchmarks75.4%72.7%15051440
40
GPT-6 Astraopenai/gpt-6-astra
OpenAI69.1$10.00 / $50.001 of 15 benchmarks65.5%
41
Doubao-Seed-Codebytedance/doubao-seed-code
ByteDance69.1—1 of 15 benchmarks78.8%
42
Kimi K3.1 Pro (max)moonshotai/kimi-k3.1-pro:max
MoonshotAI68.8$2.00 / $10.001 of 15 benchmarks1687
43
GPT-5.6 Sol (max)openai/gpt-5.6-sol:max
OpenAI68.5$4.00 / $20.003 of 15 benchmarks72.7%47.5%44.8%
44
Muse Spark 1.1meta/muse-spark-1.1
Meta68.4$1.25 / $4.252 of 15 benchmarks15331542
45
Claude Opus 5.5 (xhigh)anthropic/claude-opus-5.5:xhigh
Anthropic68.3$4.00 / $20.001 of 15 benchmarks51.4%
46
o4 Mini (medium)openai/o4-mini:medium
OpenAI67.9—1 of 15 benchmarks74.2%
47
Claude Fable 5.1 (medium)anthropic/claude-fable-5.1:medium
Anthropic67.8$10.00 / $50.001 of 15 benchmarks50.9%
48
Muse Sparkmeta/muse-spark
Meta67.8—1 of 15 benchmarks1528
49
GLM 5.3 (max)z-ai/glm-5.3:max
Z.ai67.8$0.0699 / $1.404 of 15 benchmarks69.0%40.1%15221622
50
Claude Opus 5.5anthropic/claude-opus-5.5
Anthropic67.7$4.00 / $20.001 of 15 benchmarks62.3%
51
Claude Opus 4.8anthropic/claude-opus-4.8
Anthropic67.2$5.00 / $25.002 of 15 benchmarks15291536
52
GPT-6.1 Sol (medium)openai/gpt-6.1-sol:medium
OpenAI66.8$2.00 / $10.001 of 15 benchmarks50.2%
53
Claude Opus 4.5 (high)anthropic/claude-opus-4.5:high
Anthropic66.8$5.00 / $25.001 of 15 benchmarks76.8%
54
Grok 4.6 (high)x-ai/grok-4.6:high
SpaceXAI66.6$2.00 / $6.006 of 15 benchmarks65.2%48.0%1508161829.1%38.0
55
SWE-2 (max)cognition/swe-2:max
Cognition66.6—1 of 15 benchmarks50.0%
56
Grok 4.7 (xhigh)x-ai/grok-4.7:xhigh
SpaceXAI66.4$2.00 / $6.003 of 15 benchmarks45.6%14921640
57
Claude Sonnet 5.5anthropic/claude-sonnet-5.5
Anthropic66.2$2.00 / $10.001 of 15 benchmarks61.9%
58
Claude Fable 5.1 (low)anthropic/claude-fable-5.1:low
Anthropic66.2$10.00 / $50.001 of 15 benchmarks49.8%
59
Claude Opus 5 (xhigh)anthropic/claude-opus-5:xhigh
Anthropic66.1$5.00 / $25.002 of 15 benchmarks73.2%43.6%
60
Qwen3.6 Max Previewqwen/qwen3.6-max-preview
Qwen66.1—3 of 15 benchmarks76.7%15101482
61
Grok 4.5x-ai/grok-4.5
SpaceXAI65.9$2.00 / $6.002 of 15 benchmarks15141552
62
Claude Sonnet 4.6anthropic/claude-sonnet-4.6
Anthropic65.6$3.00 / $15.005 of 15 benchmarks75.2%1528152229.1%32.0
63
Inkling 2 Smallthinkingmachines/inkling-2-small
Thinking Machines65.6—2 of 15 benchmarks14861649
64
GPT-6.1 Sol (xhigh)openai/gpt-6.1-sol:xhigh
OpenAI65.6$2.00 / $10.001 of 15 benchmarks49.3%
65
Hy4 previewtencent/hy4-preview
Tencent65.6$0.7506 / $2.25091 of 15 benchmarks1632
66
GLM 5.1z-ai/glm-5.1
Z.ai65.5$1.40 / $4.403 of 15 benchmarks74.2%15131508
67
Claude Fable 5 (medium)anthropic/claude-fable-5:medium
Anthropic65.5$10.00 / $50.002 of 15 benchmarks65.4%49.8%
68
Claude Opus 4.5 (high 32K)anthropic/claude-opus-4.5:high-32k
Anthropic65.2$5.00 / $25.002 of 15 benchmarks15301493
69
DeepSeek V4 Pro 0423 (high)deepseek/deepseek-v4-pro:high
DeepSeek65.1$0.8837 / $1.76752 of 15 benchmarks15031581
70
Gemini 3 Flash Preview (high)google/gemini-3-flash-preview:high
Google65.1$0.50 / $3.001 of 15 benchmarks75.8%
71
MiniMax M2.5 (high)minimax/minimax-m2.5:high
MiniMax65.1$0.30 / $1.201 of 15 benchmarks75.8%
72
GPT-5.2 Chatopenai/gpt-5.2-chat
OpenAI65.1—1 of 15 benchmarks1515
73
Dola Seed 2.0 Probytedance/dola-seed-2.0-pro
ByteDance65.0—1 of 15 benchmarks1514
74
DeepSeek V4 Pro 0423 (max)deepseek/deepseek-v4-pro:max
DeepSeek64.9$0.8837 / $1.76752 of 15 benchmarks77.6%62.8%
75
Qwen3.8 Flash Nextqwen/qwen3.8-flash-next
Qwen64.9—1 of 15 benchmarks1624
76
Claude Fable 5.1 (xhigh)anthropic/claude-fable-5.1:xhigh
Anthropic64.8$10.00 / $50.001 of 15 benchmarks48.7%
77
Gemini 4 Carbongoogle/gemini-4-carbon
Google64.8—1 of 15 benchmarks61.2%
78
Gemini 3.7 Flash (high)google/gemini-3.7-flash:high
Google64.8$0.75 / $3.755 of 15 benchmarks65.3%42.2%41.1%15201588
79
Qwen3.8 27Bqwen/qwen3.8-27b
Qwen64.7$0.15 / $1.8752 of 15 benchmarks14951591
80
GPT 5.5 Instantopenai/gpt-5.5-instant
OpenAI64.7—1 of 15 benchmarks1514
81
Qwen3.5 Max Previewqwen/qwen3.5-max-preview
Qwen64.6—1 of 15 benchmarks1513
82
GPT-6 Sol (xhigh)openai/gpt-6-sol:xhigh
OpenAI64.6$2.00 / $10.001 of 15 benchmarks48.5%
83
Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtools
Google64.5$2.00 / $12.001 of 15 benchmarks75.6%
84
Muse Spark 1.3 (xhigh)meta/muse-spark-1.3:xhigh
Meta64.4$1.25 / $4.251 of 15 benchmarks1621
85
Ernie 5.1baidu/ernie-5.1
Baidu64.2—1 of 15 benchmarks1512
86
Claude Opus 4.1 (thinking 16K)anthropic/claude-opus-4.1:thinking-16k
Anthropic64.1$15.00 / $75.001 of 15 benchmarks1511
87
EXAONE 4.0 32Blg-ai/exaone-4.0-32b
LG AI Research63.9—1 of 15 benchmarks70.0%
88
Muse Spark 1.2 (xhigh)meta/muse-spark-1.2:xhigh
Meta63.6$1.25 / $4.253 of 15 benchmarks54.9%15431534
89
GPT-5.3-Codex (high)openai/gpt-5.3-codex:high
OpenAI63.4$1.75 / $14.001 of 15 benchmarks74.8%
90
Grok 4.20 Multi Agent Beta 0309x-ai/grok-4.20-multi-agent-beta-0309
SpaceXAI63.4—1 of 15 benchmarks1508
91
Claude Fable 5.1anthropic/claude-fable-5.1
Anthropic63.3$10.00 / $50.001 of 15 benchmarks56.3%
92
GPT-5.5 (high)openai/gpt-5.5:high
OpenAI63.3$5.00 / $30.007 of 15 benchmarks64.4%40.6%10.0%1518148747.7%72.0
93
GPT-6.1 Sol (high)openai/gpt-6.1-sol:high
OpenAI63.3$2.00 / $10.001 of 15 benchmarks48.0%
94
Grok 4.5 (high)x-ai/grok-4.5:high
SpaceXAI63.2$2.00 / $6.005 of 15 benchmarks53.8%42.4%32.2%47.7%55.0
95
GPT-6 Sol (high)openai/gpt-6-sol:high
OpenAI63.1$2.00 / $10.001 of 15 benchmarks47.7%
96
Grok 4.6 (medium)x-ai/grok-4.6:medium
SpaceXAI63.1$2.00 / $6.002 of 15 benchmarks67.5%46.1%
97
Kimi K2.6moonshotai/kimi-k2.6
MoonshotAI63.0$0.65 / $3.416 of 15 benchmarks76.7%2.4%1516150936.0%45.0
98
GPT-5openai/gpt-5
OpenAI63.0$1.25 / $10.001 of 15 benchmarks74.4%
99
MiMo-V2.5-Proxiaomi/mimo-v2.5-pro
Xiaomi63.0$0.48 / $1.802 of 15 benchmarks15201479
100
Grok 4.7 (high)x-ai/grok-4.7:high
SpaceXAI62.8$2.00 / $6.001 of 15 benchmarks47.6%
101
Step 5 Previewstepfun/step-5-preview
StepFun62.7$1.00 / $2.701 of 15 benchmarks1505
102
Kimi K3 (high)moonshotai/kimi-k3:high
MoonshotAI62.7$0.192 / $16.002 of 15 benchmarks31.4%41.0
103
OpenReasoning Nemotron 32Bnvidia/openreasoning-nemotron-32b
NVIDIA62.6—1 of 15 benchmarks69.8%
104
MiniMax M3.1 Flashminimax/minimax-m3.1-flash
MiniMax62.4$0.075 / $0.301 of 15 benchmarks1582
105
Gemini 4 Argon (medium)google/gemini-4-argon:medium
Google62.3$2.00 / $10.001 of 15 benchmarks47.5%
106
R1 0528deepseek/deepseek-r1-0528
DeepSeek62.3$0.50 / $2.152 of 15 benchmarks73.1%1464
107
Gemini 3 Progoogle/gemini-3-pro
Google62.0—3 of 15 benchmarks68.7%15171441
108
DeepSeek V4 Flash 0423 (high)deepseek/deepseek-v4-flash:high
DeepSeek61.9$0.091 / $0.1822 of 15 benchmarks14801582
109
Gemini 4 Argongoogle/gemini-4-argon
Google61.9$2.00 / $10.001 of 15 benchmarks55.0%
110
Gemini 3.8 Flash (medium)google/gemini-3.8-flash:medium
Google61.9$0.75 / $3.752 of 15 benchmarks71.0%41.2%
111
Claude Opus 5.5 (low)anthropic/claude-opus-5.5:low
Anthropic61.8$4.00 / $20.001 of 15 benchmarks47.3%
112
Claude Haiku 5.5 (high)anthropic/claude-haiku-5.5:high
Anthropic61.5$0.10 / $0.503 of 15 benchmarks41.9%14901595
113
Claude Haiku 5.5 (max)anthropic/claude-haiku-5.5:max
Anthropic61.5$0.10 / $0.502 of 15 benchmarks46.4%43.8%
114
Step 5 Preview (high)stepfun/step-5-preview:high
StepFun61.5$1.00 / $2.701 of 15 benchmarks1572
115
SWE-2 (high)cognition/swe-2:high
Cognition61.4—1 of 15 benchmarks47.2%
116
Gemini 4 Argon (low)google/gemini-4-argon:low
Google61.4$2.00 / $10.001 of 15 benchmarks47.2%
117
Qwen3.7 Maxqwen/qwen3.7-max
Qwen61.4$1.475 / $4.4254 of 15 benchmarks77.3%9.5%15241515
118
Qwen3.7 Plusqwen/qwen3.7-plus
Qwen61.2$0.32 / $1.281 of 15 benchmarks1500
119
GLM 5z-ai/glm-5
Z.ai61.2$1.00 / $3.204 of 15 benchmarks72.1%69.7%14981435
120
Qwen3.8 Maxqwen/qwen3.8-max
Qwen61.2—3 of 15 benchmarks15.8%15241670
121
Gemini 3.5 Flash (medium)google/gemini-3.5-flash:medium
Google61.2$1.50 / $9.002 of 15 benchmarks15061490
122
Hy3tencent/hy3
Tencent61.1$0.0825 / $0.332 of 15 benchmarks15041506
123
Claude Opus 4 (thinking 16K)anthropic/claude-opus-4:thinking-16k
Anthropic61.0—1 of 15 benchmarks1499
124
Claude Fable 5 (low)anthropic/claude-fable-5:low
Anthropic60.8$10.00 / $50.002 of 15 benchmarks59.6%48.0%
125
GPT-6 Astra (low)openai/gpt-6-astra:low
OpenAI60.8$10.00 / $50.002 of 15 benchmarks67.0%45.3%
126
GPT-5.3 Chatopenai/gpt-5.3-chat
OpenAI60.8—1 of 15 benchmarks1497
127
Gemini 3 Pro Previewgoogle/gemini-3-pro-preview
Google60.7—1 of 15 benchmarks72.9%
128
GLM 5.3 Flashz-ai/glm-5.3-flash
Z.ai60.7$0.15 / $0.503 of 15 benchmarks18.1%15271609
129
o3openai/o3
OpenAI60.6$2.00 / $8.003 of 15 benchmarks58.4%36.0%1460
130
GPT-5.6 Terra (max)openai/gpt-5.6-terra:max
OpenAI60.6$2.00 / $12.002 of 15 benchmarks69.6%41.3%
131
Claude Opus 5anthropic/claude-opus-5
Anthropic60.4$5.00 / $25.001 of 15 benchmarks52.0%
132
Mistral Large 4mistralai/mistral-large-4-0
Mistral60.4$0.70 / $2.102 of 15 benchmarks14731563
133
GPT-5.4 (high)openai/gpt-5.4:high
OpenAI60.4$2.50 / $15.004 of 15 benchmarks76.9%15.6%15211462
134
Claude Sonnet 5.5 (max)anthropic/claude-sonnet-5.5:max
Anthropic60.3$2.00 / $10.001 of 15 benchmarks46.2%
135
GLM 5 (high)z-ai/glm-5:high
Z.ai60.2$1.00 / $3.201 of 15 benchmarks72.8%
136
GPT-5.5openai/gpt-5.5
OpenAI60.1$5.00 / $30.002 of 15 benchmarks15101455
137
Gemini 3.8 Flash (high)google/gemini-3.8-flash:high
Google60.0$0.75 / $3.756 of 15 benchmarks73.8%38.0%1530158422.1%25.0
138
OpenCodeReasoning Nemotron 1.1 32Bnvidia/opencodereasoning-nemotron-1.1-32b
NVIDIA59.9—1 of 15 benchmarks66.8%
139
Grok 4.1x-ai/grok-4.1
SpaceXAI59.9—1 of 15 benchmarks1492
140
GPT-6 Sol (medium)openai/gpt-6-sol:medium
OpenAI59.8$2.00 / $10.001 of 15 benchmarks45.9%
141
Claude 3.7 Sonnetanthropic/claude-3-7-sonnet
Anthropic59.8—5 of 15 benchmarks61.0%51.7%33.8%31.3%1431
142
Claude Haiku 5.5 (xhigh)anthropic/claude-haiku-5.5:xhigh
Anthropic59.3$0.10 / $0.501 of 15 benchmarks45.8%
143
Ernie 5.0 0110baidu/ernie-5.0-0110
Baidu59.2—1 of 15 benchmarks1489
144
Claude Opus 4.7 (high)anthropic/claude-opus-4.7:high
Anthropic59.1$5.00 / $25.004 of 15 benchmarks35.2%31.1%15511557
145
GPT-5.5 (xhigh)openai/gpt-5.5:xhigh
OpenAI59.1$5.00 / $30.004 of 15 benchmarks67.0%43.0%34.3%1512
146
Kimi K2.5moonshotai/kimi-k2.5
MoonshotAI59.1$0.532 / $3.3252 of 15 benchmarks73.8%67.3%
147
Claude Fable 5anthropic/claude-fable-5
Anthropic59.0$10.00 / $50.001 of 15 benchmarks47.0%
148
Gemini 3.7 Flash (medium)google/gemini-3.7-flash:medium
Google59.0$0.75 / $3.752 of 15 benchmarks65.5%43.6%
149
GPT-5.6 Terra (xhigh)openai/gpt-5.6-terra:xhigh
OpenAI58.9$2.00 / $12.004 of 15 benchmarks60.2%38.8%15171520
150
Claude Sonnet 4.5 (high)anthropic/claude-sonnet-4.5:high
Anthropic58.8$3.00 / $15.001 of 15 benchmarks71.4%
151
Mimo v2 Omnixiaomi/mimo-v2-omni
Xiaomi58.8—1 of 15 benchmarks1488
152
MiniMax M3minimax/minimax-m3
MiniMax58.7$0.30 / $1.202 of 15 benchmarks14941484
153
GPT-6.1 Sol (low)openai/gpt-6.1-sol:low
OpenAI58.6$2.00 / $10.001 of 15 benchmarks45.5%
154
GPT-5.1 (high)openai/gpt-5.1:high
OpenAI58.5$1.25 / $10.002 of 15 benchmarks68.0%1492
155
Muse Spark Open (max)meta/muse-spark-open:max
Meta58.5$1.25 / $4.251 of 15 benchmarks1528
156
GPT-5.6 Luna (high)openai/gpt-5.6-luna:high
OpenAI58.4$0.20 / $1.204 of 15 benchmarks44.3%35.9%41.9%57.0
157
DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash
DeepSeek58.2$0.091 / $0.1821 of 15 benchmarks1484
158
Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b
Reflection58.2$0.30 / $1.002 of 15 benchmarks15051438
159
GPT-6 Luna (max)openai/gpt-6-luna:max
OpenAI58.2$0.10 / $0.504 of 15 benchmarks42.4%26.7%15021577
160
DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro
DeepSeek58.2$0.8837 / $1.76752 of 15 benchmarks15011448
161
Claude Sonnet 4anthropic/claude-sonnet-4
Anthropic58.0—5 of 15 benchmarks57.0%58.3%35.6%47.1%1449
162
Seed 2.1 Pro Previewbytedance/seed-2.1-pro-preview
ByteDance57.8—1 of 15 benchmarks1519
163
Kimi K3 (none)moonshotai/kimi-k3:none
MoonshotAI57.8$0.192 / $16.001 of 15 benchmarks44.2%
164
GLM 5.2 (max)z-ai/glm-5.2:max
Z.ai57.7$0.006 / $6.805 of 15 benchmarks78.7%43.8%9.5%15151608
165
Grok 4.6 (xhigh)x-ai/grok-4.6:xhigh
SpaceXAI57.7$2.00 / $6.003 of 15 benchmarks66.7%41.1%30.5%
166
Kimi K2.5 (high)moonshotai/kimi-k2.5:high
MoonshotAI57.7$0.532 / $3.3251 of 15 benchmarks70.8%
167
Claude Opus 4.7 (max)anthropic/claude-opus-4.7:max
Anthropic57.6$5.00 / $25.003 of 15 benchmarks83.5%38.5%19.1%
168
DeepSeek V4.1 Flash (high)deepseek/deepseek-v4.1-flash:high
DeepSeek57.6$0.051 / $0.5671 of 15 benchmarks43.9%
169
Claude Haiku 5.5anthropic/claude-haiku-5.5
Anthropic57.5$0.10 / $0.501 of 15 benchmarks43.8%
170
Claude Sonnet 4.5 (high 32K)anthropic/claude-sonnet-4.5:high-32k
Anthropic57.4$3.00 / $15.002 of 15 benchmarks15191394
171
Kimi K2.5 (thinking)moonshotai/kimi-k2.5:thinking
MoonshotAI57.3$0.532 / $3.3252 of 15 benchmarks15021436
172
Kimi K2 0905moonshotai/kimi-k2-0905
MoonshotAI57.3$0.60 / $2.502 of 15 benchmarks71.2%1468
173
Claude Opus 4.8 (max)anthropic/claude-opus-4.8:max
Anthropic57.2$5.00 / $25.002 of 15 benchmarks46.5%28.6%
174
DeepSeek V3.2 Exp (thinking)deepseek/deepseek-v3.2-exp:thinking
DeepSeek57.0$0.27 / $0.411 of 15 benchmarks1475
175
GPT-5.2 (high)openai/gpt-5.2:high
OpenAI57.0$1.75 / $14.003 of 15 benchmarks73.8%66.7%1489
176
Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite
Google57.0$0.30 / $2.502 of 15 benchmarks15021435
177
DeepSeek V3.2 (high)deepseek/deepseek-v3.2:high
DeepSeek57.0$0.26 / $0.381 of 15 benchmarks70.0%
178
Claude Sonnet 4 (thinking 32K)anthropic/claude-sonnet-4:thinking-32k
Anthropic56.9—1 of 15 benchmarks1474
179
GPT-5.4openai/gpt-5.4
OpenAI56.9$2.50 / $15.002 of 15 benchmarks15111400
180
Mimo v2 Proxiaomi/mimo-v2-pro
Xiaomi56.8—2 of 15 benchmarks15031434
181
SWE-2 (medium)cognition/swe-2:medium
Cognition56.8—1 of 15 benchmarks43.1%
182
Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b
NVIDIA56.8$0.60 / $2.401 of 15 benchmarks1474
183
Qwen3 Maxqwen/qwen3-max
Qwen56.7—1 of 15 benchmarks1473
184
o4 Mini (low)openai/o4-mini:low
OpenAI56.6—1 of 15 benchmarks65.9%
185
GPT-5.6 Luna (max)openai/gpt-5.6-luna:max
OpenAI56.5$0.20 / $1.202 of 15 benchmarks67.2%39.8%
186
GPT-5.6 Sol (high)openai/gpt-5.6-sol:high
OpenAI56.4$4.00 / $20.003 of 15 benchmarks69.4%45.1%20.0%
187
Gemini 3 Pro Preview (high)google/gemini-3-pro-preview:high
Google56.4—1 of 15 benchmarks69.6%
188
LongCat Flash Chatmeituan/longcat-flash-chat
Meituan56.3—1 of 15 benchmarks1472
189
Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507
Qwen56.2$0.14 / $0.801 of 15 benchmarks1472
190
Kimi K2.5 Instantmoonshotai/kimi-k2.5-instant
Moonshot AI56.2—2 of 15 benchmarks15051406
191
GPT-5.6 Solopenai/gpt-5.6-sol
OpenAI56.1$4.00 / $20.001 of 15 benchmarks32.2%
192
MiMo-V2.5xiaomi/mimo-v2.5
Xiaomi56.1$0.40 / $2.002 of 15 benchmarks14911438
193
GPT-5.6 Luna (xhigh)openai/gpt-5.6-luna:xhigh
OpenAI56.0$0.20 / $1.204 of 15 benchmarks56.9%38.9%15021519
194
Claude Sonnet 5 (high)anthropic/claude-sonnet-5:high
Anthropic55.9$2.00 / $10.004 of 15 benchmarks48.2%39.4%15201539
195
Ernie 5.0 Preview 1203baidu/ernie-5.0-preview-1203
Baidu55.8—1 of 15 benchmarks1471
196
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview
Google55.6$2.00 / $12.003 of 15 benchmarks14.3%15201446
197
Qwen3.8 Max (0902)qwen/qwen3.8-max-0902
Qwen55.4$2.00 / $6.002 of 15 benchmarks17.8%1677
198
Chatgpt 4oopenai/chatgpt-4o
OpenAI55.4—1 of 15 benchmarks1467
199
o3 Mini Highopenai/o3-mini-high
OpenAI55.3—2 of 15 benchmarks67.4%1434
200
Claude Opus 4.8 (xhigh)anthropic/claude-opus-4.8:xhigh
Anthropic55.1$5.00 / $25.002 of 15 benchmarks54.4%45.5%
201
Claude Haiku 4.5 (high)anthropic/claude-haiku-4.5:high
Anthropic55.1$1.00 / $5.001 of 15 benchmarks66.6%
202
SWE-1.7 (none)cognition/swe-1.7:none
Cognition55.0—1 of 15 benchmarks42.0%
203
Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct
Qwen54.9$0.21 / $1.901 of 15 benchmarks1463
204
GPT 5 Chatopenai/gpt-5-chat
OpenAI54.8—1 of 15 benchmarks1462
205
Grok 4.20 Beta 0309 (reasoning)x-ai/grok-4.20-beta-0309:reasoning
SpaceXAI54.7—2 of 15 benchmarks15111376
206
GLM 5.3z-ai/glm-5.3
Z.ai54.6$0.0699 / $1.401 of 15 benchmarks30.2%
207
XBai o4 (medium)metastone/xbai-o4:medium
MetaStoneTec54.6—1 of 15 benchmarks65.0%
208
Grok 4.5 (medium)x-ai/grok-4.5:medium
SpaceXAI54.5$2.00 / $6.001 of 15 benchmarks41.9%
209
GPT-5.1-Codex (medium)openai/gpt-5.1-codex:medium
OpenAI54.5$1.25 / $10.001 of 15 benchmarks66.0%
210
GPT-5 (medium)openai/gpt-5:medium
OpenAI54.4$1.25 / $10.002 of 15 benchmarks71.5%1417
211
GLM 4.7z-ai/glm-4.7
Z.ai54.2$0.60 / $2.202 of 15 benchmarks14841435
212
GPT-5.4 Nano (high)openai/gpt-5.4-nano:high
OpenAI54.2$0.20 / $1.251 of 15 benchmarks1460
213
Qwen3.6 Plusqwen/qwen3.6-plus
Qwen54.1$0.325 / $1.953 of 15 benchmarks57.9%14961462
214
Claude Haiku 5.5 (medium)anthropic/claude-haiku-5.5:medium
Anthropic54.0$0.10 / $0.501 of 15 benchmarks41.6%
215
DeepSeek V3.1 Terminus (thinking)deepseek/deepseek-v3.1-terminus:thinking
DeepSeek54.0$0.27 / $1.001 of 15 benchmarks1460
216
GPT-5.2openai/gpt-5.2
OpenAI54.0$1.75 / $14.003 of 15 benchmarks69.0%14821420
217
Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b
Qwen53.7$0.60 / $3.602 of 15 benchmarks14901400
218
Claude Opus 5 (low)anthropic/claude-opus-5:low
Anthropic53.6$5.00 / $25.002 of 15 benchmarks58.1%42.0%
219
GPT 4.5 Previewopenai/gpt-4.5-preview
OpenAI53.6—1 of 15 benchmarks1458
220
GPT-5 Mini (medium)openai/gpt-5-mini:medium
OpenAI53.5$0.25 / $2.001 of 15 benchmarks64.7%
221
Grok 4 Fastx-ai/grok-4-fast
SpaceXAI53.4—1 of 15 benchmarks1458
222
Qwen3.8 Max (xhigh)qwen/qwen3.8-max:xhigh
Qwen53.4—1 of 15 benchmarks57.5%
223
Grok 4.7x-ai/grok-4.7
SpaceXAI53.2$2.00 / $6.001 of 15 benchmarks29.5%
224
GPT-5.4 (medium)openai/gpt-5.4:medium
OpenAI53.0$2.50 / $15.001 of 15 benchmarks1442
225
Claude 3.5 Haikuanthropic/claude-3-5-haiku
Anthropic53.0—2 of 15 benchmarks41.7%1386
226
Gemma 4 31Bgoogle/gemma-4-31b-it
Google53.0$0.20 / $0.402 of 15 benchmarks15021369
227
DeepSeek V3.1 (thinking)deepseek/deepseek-chat-v3.1:thinking
DeepSeek53.0$0.25 / $0.951 of 15 benchmarks1456
228
GLM 5V Turboz-ai/glm-5v-turbo
Z.ai52.9$1.20 / $4.002 of 15 benchmarks14881399
229
Kimi K2 0711moonshotai/kimi-k2
MoonshotAI52.9$0.57 / $2.302 of 15 benchmarks65.4%1459
230
Kimi K2 Thinkingmoonshotai/kimi-k2-thinking
MoonshotAI52.8$0.60 / $2.501 of 15 benchmarks63.4%
231
Mistral Medium 2508mistralai/mistral-medium-2508
Mistral AI52.7—1 of 15 benchmarks1454
232
Claude Opus 4.6 (high)anthropic/claude-opus-4.6:high
Anthropic52.7$5.00 / $25.005 of 15 benchmarks26.6%1547154626.7%24.0
233
GPT-5.6 Sol (medium)openai/gpt-5.6-sol:medium
OpenAI52.6$4.00 / $20.002 of 15 benchmarks61.1%39.9%
234
Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking
Qwen52.5—1 of 15 benchmarks1452
235
Gemini 3.6 Flash (high)google/gemini-3.6-flash:high
Google52.5$0.75 / $3.754 of 15 benchmarks46.7%33.7%15181538
236
Claude Sonnet 4.5anthropic/claude-sonnet-4.5
Anthropic52.4$3.00 / $15.006 of 15 benchmarks71.3%44.3%67.0%2.4%15121385
237
Claude 3.7 Sonnet (thinking 32K)anthropic/claude-3-7-sonnet:thinking-32k
Anthropic52.4—1 of 15 benchmarks1452
238
DeepSeek V4 Pro 0423 (xhigh)deepseek/deepseek-v4-pro:xhigh
DeepSeek52.3$0.8837 / $1.76752 of 15 benchmarks26.7%30.0
239
Step 3.5 Flashstepfun/step-3.5-flash
StepFun52.1$0.10 / $0.301 of 15 benchmarks1449
240
Gemini 3.5 Flash (high)google/gemini-3.5-flash:high
Google52.1$1.50 / $9.005 of 15 benchmarks79.3%36.1%4.8%15081500
241
o3 (medium)openai/o3:medium
OpenAI52.0$2.00 / $8.001 of 15 benchmarks62.3%
242
Claude Sonnet 5 (max)anthropic/claude-sonnet-5:max
Anthropic52.0$2.00 / $10.002 of 15 benchmarks53.9%42.4%
243
Inkling Smallthinkingmachines/inkling-small
Thinking Machines51.9$0.45 / $1.202 of 15 benchmarks14721407
244
DeepSeek V3.1deepseek/deepseek-chat-v3.1
DeepSeek51.9$0.25 / $0.951 of 15 benchmarks1447
245
Claude Opus 4.8 (high)anthropic/claude-opus-4.8:high
Anthropic51.9$5.00 / $25.006 of 15 benchmarks51.8%41.0%1534155524.4%24.0
246
Kimi K3moonshotai/kimi-k3
MoonshotAI51.7$0.192 / $16.001 of 15 benchmarks25.9%
247
MiniMax M2.7minimax/minimax-m2.7
MiniMax51.5$0.21 / $0.842 of 15 benchmarks14801398
248
Qwen3 235B A22B (nothinking)qwen/qwen3-235b-a22b:nothinking
Qwen51.5—1 of 15 benchmarks1444
249
Gemini 3 Flash Preview (minimal)google/gemini-3-flash-preview:minimal
Google51.5$0.50 / $3.002 of 15 benchmarks14901384
250
Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct
Qwen51.4$0.09 / $1.101 of 15 benchmarks1444
251
R1deepseek/deepseek-r1
DeepSeek51.3—1 of 15 benchmarks1444
252
Qwen3 235B A22Bqwen/qwen3-235b-a22b
Qwen51.2—2 of 15 benchmarks65.9%1432
253
Trinity Large Previewarcee-ai/trinity-large-preview
Arcee AI51.2—1 of 15 benchmarks1443
254
Grok 3 Betax-ai/grok-3-beta
SpaceXAI51.0—1 of 15 benchmarks1442
255
Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507
Qwen50.9$0.45 / $3.501 of 15 benchmarks1442
256
DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus
DeepSeek50.8$0.27 / $1.001 of 15 benchmarks1440
257
o3 Mini (low)openai/o3-mini:low
OpenAI50.6—1 of 15 benchmarks57.0%
258
Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507
Qwen50.6$0.10 / $0.301 of 15 benchmarks1438
259
GPT-5.2 (xhigh)openai/gpt-5.2:xhigh
OpenAI50.3$1.75 / $14.001 of 15 benchmarks23.0%
260
Hunyuan Vision 1.5 (thinking)tencent/hunyuan-vision-1.5:thinking
Tencent50.3—1 of 15 benchmarks1436
261
Muse Spark 1.3meta/muse-spark-1.3
Meta50.3$1.25 / $4.251 of 15 benchmarks25.8%
262
Grok 4.5 (low)x-ai/grok-4.5:low
SpaceXAI50.3$2.00 / $6.001 of 15 benchmarks37.9%
263
Grok 3 Mini Beta (high)x-ai/grok-3-mini-beta:high
SpaceXAI50.2—2 of 15 benchmarks66.7%1392
264
Claude Opus 4.1anthropic/claude-opus-4.1
Anthropic50.1$15.00 / $75.004 of 15 benchmarks73.3%7.9%15051389
265
GPT-6 Sol (low)openai/gpt-6-sol:low
OpenAI50.0$2.00 / $10.001 of 15 benchmarks37.3%
266
Claude Opus 4anthropic/claude-opus-4
Anthropic50.0—3 of 15 benchmarks70.7%46.9%1465
267
Grok 4 0709x-ai/grok-4-0709
SpaceXAI50.0—1 of 15 benchmarks1435
268
GPT-5.3-Codexopenai/gpt-5.3-codex
OpenAI49.8$1.75 / $14.001 of 15 benchmarks1406
269
GPT-6 Luna (high)openai/gpt-6-luna:high
OpenAI49.8$0.10 / $0.501 of 15 benchmarks37.3%
270
Grok 4.3x-ai/grok-4.3
SpaceXAI49.6$1.25 / $2.502 of 15 benchmarks14871357
271
Claude Sonnet 5 (xhigh)anthropic/claude-sonnet-5:xhigh
Anthropic49.6$2.00 / $10.002 of 15 benchmarks49.7%42.7%
272
Gemma 4 26B A4B google/gemma-4-26b-a4b-it
Google49.6$0.0765 / $0.2552 of 15 benchmarks14831359
273
GPT-6 Luna (xhigh)openai/gpt-6-luna:xhigh
OpenAI49.5$0.10 / $0.501 of 15 benchmarks37.1%
274
Gemini 2.5 Progoogle/gemini-2.5-pro
Google49.3$1.25 / $10.004 of 15 benchmarks57.6%73.6%14641228
275
Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl
NVIDIA49.3$0.15 / $0.472 of 15 benchmarks14601399
276
Claude Opus 4 (thinking)anthropic/claude-opus-4:thinking
Anthropic49.3—1 of 15 benchmarks56.6%
277
o4 Miniopenai/o4-mini
OpenAI49.2—3 of 15 benchmarks45.0%33.9%1433
278
Mistral Medium 2505mistralai/mistral-medium-2505
Mistral AI49.2—1 of 15 benchmarks1433
279
GPT-5 Mini (high)openai/gpt-5-mini:high
OpenAI49.1$0.25 / $2.001 of 15 benchmarks1432
280
Devstral Small 2512mistralai/devstral-small-2512
Mistral AI49.0—1 of 15 benchmarks56.4%
281
o1openai/o1
OpenAI49.0—2 of 15 benchmarks64.6%1433
282
GPT-5.1 (medium)openai/gpt-5.1:medium
OpenAI48.9$1.25 / $10.002 of 15 benchmarks66.0%1397
283
Grok 4.6x-ai/grok-4.6
SpaceXAI48.9$2.00 / $6.001 of 15 benchmarks25.3%
284
DeepSeek V4 Flash 0423 (max)deepseek/deepseek-v4-flash:max
DeepSeek48.8$0.091 / $0.1821 of 15 benchmarks53.3%
285
Muse Spark 1.1 (xhigh)meta/muse-spark-1.1:xhigh
Meta48.8$1.25 / $4.251 of 15 benchmarks53.3%
286
MiniMax M2.5minimax/minimax-m2.5
MiniMax48.7$0.30 / $1.203 of 15 benchmarks68.3%14471386
287
Ernie 5.0 Preview 1022baidu/ernie-5.0-preview-1022
Baidu48.6—1 of 15 benchmarks1431
288
Muse Glimmer 30Bmeta/muse-glimmer-30b
Meta48.6$0.30 / $1.202 of 15 benchmarks14801355
289
Claude Sonnet 5.5 (medium)anthropic/claude-sonnet-5.5:medium
Anthropic48.5$2.00 / $10.001 of 15 benchmarks36.5%
290
DeepSeek V3 0324deepseek/deepseek-chat-v3-0324
DeepSeek48.5$0.29 / $1.141 of 15 benchmarks1428
291
GLM 5.3 Flash (max)z-ai/glm-5.3-flash:max
Z.ai48.5$0.15 / $0.502 of 15 benchmarks63.4%31.8%
292
Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning-30b-a3b
NVIDIA48.4—1 of 15 benchmarks1428
293
GLM 4.5 Airz-ai/glm-4.5-air
Z.ai48.3$0.20 / $1.101 of 15 benchmarks1427
294
Claude 3.5 Sonnetanthropic/claude-3-5-sonnet
Anthropic48.3—6 of 15 benchmarks62.8%51.3%24.9%25.3%36.4%1436
295
Claude Sonnet 5anthropic/claude-sonnet-5
Anthropic48.1$2.00 / $10.002 of 15 benchmarks25.6%27.0
296
GLM 4.7 Flashz-ai/glm-4.7-flash
Z.ai48.0$0.0605 / $0.401 of 15 benchmarks1423
297
GPT-6 Luna (medium)openai/gpt-6-luna:medium
OpenAI48.0$0.10 / $0.501 of 15 benchmarks35.5%
298
Claude Sonnet 4 (thinking)anthropic/claude-sonnet-4:thinking
Anthropic47.9—1 of 15 benchmarks56.0%
299
Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking
Qwen47.9—1 of 15 benchmarks1421
300
GPT-5.1openai/gpt-5.1
OpenAI47.8$1.25 / $10.002 of 15 benchmarks14751342
301
Kimi K2 Thinking Turbomoonshotai/kimi-k2-thinking-turbo
Moonshot AI47.7—2 of 15 benchmarks14861322
302
MiniMax M1minimax/minimax-m1
MiniMax47.7—1 of 15 benchmarks1416
303
DeepSeek V3.2 (thinking)deepseek/deepseek-v3.2:thinking
DeepSeek47.6$0.26 / $0.383 of 15 benchmarks60.0%14761363
304
GLM 4.5z-ai/glm-4.5
Z.ai47.6$0.60 / $2.202 of 15 benchmarks54.2%1455
305
GLM 4.6Vz-ai/glm-4.6v
Z.ai47.6$0.30 / $0.901 of 15 benchmarks1416
306
Solar Pro 4upstage/solar-pro4
Upstage47.5$0.15 / $0.602 of 15 benchmarks14621369
307
INTELLECT-3prime-intellect/intellect-3
Prime Intellect47.4—1 of 15 benchmarks1415
308
Gemini 3.7 Flashgoogle/gemini-3.7-flash
Google47.4$0.75 / $3.751 of 15 benchmarks20.3%
309
Claude Opus 4.5 (128K)anthropic/claude-opus-4.5:128k
Anthropic47.4$5.00 / $25.001 of 15 benchmarks14.3%
310
GPT-5.5 (medium)openai/gpt-5.5:medium
OpenAI47.3$5.00 / $30.002 of 15 benchmarks54.0%36.6%
311
Mistral Small 2506mistralai/mistral-small-2506
Mistral AI47.2—1 of 15 benchmarks1412
312
Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct
Qwen47.1$0.15 / $0.601 of 15 benchmarks51.6%
313
Step 3stepfun/step-3
StepFun47.1—1 of 15 benchmarks1409
314
Ling Flash 2.0inclusionai/ling-flash-2.0
inclusionAI47.0—1 of 15 benchmarks1409
315
Grok 4.1 (thinking)x-ai/grok-4.1:thinking
SpaceXAI46.9—2 of 15 benchmarks15001217
316
Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b
NVIDIA46.9$0.075 / $0.401 of 15 benchmarks1407
317
Claude Opus 4.7 (xhigh)anthropic/claude-opus-4.7:xhigh
Anthropic46.8$5.00 / $25.001 of 15 benchmarks34.9%
318
Qwen3 32Bqwen/qwen3-32b
Qwen46.7$0.08 / $0.281 of 15 benchmarks1406
319
Llama 3.3 Nemotron Super 49B v1.5nvidia/llama-3.3-nemotron-super-49b-v1.5
NVIDIA46.6—1 of 15 benchmarks1404
320
GPT-5.4 (xhigh)openai/gpt-5.4:xhigh
OpenAI46.6$2.50 / $15.002 of 15 benchmarks51.8%25.4%
321
Claude Haiku 5.5 (low)anthropic/claude-haiku-5.5:low
Anthropic46.5$0.10 / $0.501 of 15 benchmarks34.8%
322
Gemini 3.7 Flash (low)google/gemini-3.7-flash:low
Google46.5$0.75 / $3.752 of 15 benchmarks53.8%36.9%
323
Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b
Qwen46.5$0.26 / $2.082 of 15 benchmarks14581360
324
GLM 4.5Vz-ai/glm-4.5v
Z.ai46.5$0.60 / $1.801 of 15 benchmarks1403
325
Qwen 2.5 (max)qwen/qwen-2.5:max
Qwen46.4—1 of 15 benchmarks1401
326
GPT-5.6 Terra (high)openai/gpt-5.6-terra:high
OpenAI46.3$2.00 / $12.002 of 15 benchmarks53.8%36.9%
327
Devstral Small 2505mistralai/devstral-small-2505
Mistral AI46.3—1 of 15 benchmarks46.8%
328
GPT-5.5 (low)openai/gpt-5.5:low
OpenAI46.3$5.00 / $30.004 of 15 benchmarks27.0%30.6%32.6%38.0
329
Gemini 3.6 Flash (medium)google/gemini-3.6-flash:medium
Google46.3$0.75 / $3.751 of 15 benchmarks34.4%
330
Hunyuan T1tencent/hunyuan-t1
Tencent46.3—1 of 15 benchmarks1401
331
Hunyuan TurboStencent/hunyuan-turbos
Tencent46.1—1 of 15 benchmarks1399
332
GPT-4.1openai/gpt-4.1
OpenAI46.1$2.00 / $8.003 of 15 benchmarks48.5%31.1%1456
333
Granite 4.2 30Bibm-granite/granite-4.2-30b
IBM46.0—1 of 15 benchmarks1398
334
Gemini 3.8 Flashgoogle/gemini-3.8-flash
Google46.0$0.75 / $3.751 of 15 benchmarks19.6%
335
Gemini 2.5 Flash Lite (nothinking)google/gemini-2.5-flash-lite:nothinking
Google45.9$0.10 / $0.401 of 15 benchmarks1397
336
Qwen3 Coder 480B A35b Instructqwen/qwen3-coder-480b-a35b-instruct
Qwen45.9—3 of 15 benchmarks69.6%14571275
337
Mistral Medium 3.5mistralai/mistral-medium-3-5
Mistral45.8$1.50 / $7.502 of 15 benchmarks14781262
338
Nova 2 Liteamazon/nova-2-lite-v1
Amazon45.8$0.30 / $2.501 of 15 benchmarks1393
339
Kimi K2 Instructmoonshotai/kimi-k2-instruct
Moonshot AI45.6—1 of 15 benchmarks43.8%
340
Llama 3.1 Nemotron Ultra 253B v1nvidia/llama-3.1-nemotron-ultra-253b-v1
NVIDIA45.4—1 of 15 benchmarks1391
341
o3 Miniopenai/o3-mini
OpenAI45.3—4 of 15 benchmarks42.4%32.3%63.0%1417
342
Ring Flash 2.0inclusionai/ring-flash-2.0
inclusionAI45.3—1 of 15 benchmarks1390
343
Hy3 previewtencent/hy3-preview
Tencent45.3$0.18 / $0.602 of 15 benchmarks14521359
344
GPT-5.4 Mini (high)openai/gpt-5.4-mini:high
OpenAI45.1$0.75 / $4.503 of 15 benchmarks23.1%14951398
345
Command A (03-2025)cohere/command-a-03-2025
Cohere45.1—1 of 15 benchmarks1388
346
MiniMax M2.1minimax/minimax-m2.1
MiniMax45.0—2 of 15 benchmarks14371384
347
Nova Premier 1.0amazon/nova-premier-v1
Amazon45.0$2.50 / $12.501 of 15 benchmarks42.4%
348
Kimi K2.7 Code (none)moonshotai/kimi-k2.7-code:none
MoonshotAI45.0$0.60 / $3.501 of 15 benchmarks30.1%
349
Claude Opus 4.6 (max)anthropic/claude-opus-4.6:max
Anthropic45.0$5.00 / $25.001 of 15 benchmarks12.7%
350
Magistral Medium 2506mistralai/magistral-medium-2506
Mistral AI44.9—1 of 15 benchmarks1387
351
GPT-5.2-Codexopenai/gpt-5.2-codex
OpenAI44.8$1.75 / $14.003 of 15 benchmarks72.8%66.3%1338
352
Claude Sonnet 5.5 (low)anthropic/claude-sonnet-5.5:low
Anthropic44.8$2.00 / $10.001 of 15 benchmarks29.3%
353
Qwen3.5-27Bqwen/qwen3.5-27b
Qwen44.8$0.26 / $2.602 of 15 benchmarks14511357
354
Grok 3 Mini Betax-ai/grok-3-mini-beta
SpaceXAI44.7—1 of 15 benchmarks1386
355
O1 Miniopenai/o1-mini
OpenAI44.6—1 of 15 benchmarks1386
356
DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp
DeepSeek44.5$0.27 / $0.412 of 15 benchmarks14671270
357
GPT-5 Nano (high)openai/gpt-5-nano:high
OpenAI44.3$0.05 / $0.401 of 15 benchmarks1385
358
Qwen3 30B A3Bqwen/qwen3-30b-a3b
Qwen44.2$0.12 / $0.501 of 15 benchmarks1385
359
Laguna M.1poolside/laguna-m.1
Poolside44.1—1 of 15 benchmarks1349
360
GPT-5 (high)openai/gpt-5:high
OpenAI44.0$1.25 / $10.004 of 15 benchmarks73.5%4.4%12.7%1471
361
DeepSeek V4 Pro 0813 (high)deepseek/deepseek-v4-pro-0813:high
DeepSeek44.0$0.111 / $4.441 of 15 benchmarks28.6%
362
Grok 4.6 (low)x-ai/grok-4.6:low
SpaceXAI44.0$2.00 / $6.002 of 15 benchmarks41.6%40.1%
363
Gemini 2.5 Flash Lite (thinking)google/gemini-2.5-flash-lite:thinking
Google44.0$0.10 / $0.401 of 15 benchmarks1383
364
QwQ 32Bqwen/qwq-32b
Qwen43.9—1 of 15 benchmarks1382
365
Claude Opus 4.7 (low)anthropic/claude-opus-4.7:low
Anthropic43.8$5.00 / $25.001 of 15 benchmarks27.6%
366
OLMo 3.1 32B Instructallenai/olmo-3.1-32b-instruct
Allen Institute for AI43.7—1 of 15 benchmarks1381
367
Qwen-Plusqwen/qwen-plus
Qwen43.6$0.26 / $0.781 of 15 benchmarks1378
368
Kimi K2.7 Codemoonshotai/kimi-k2.7-code
MoonshotAI43.5$0.60 / $3.502 of 15 benchmarks30.5%1474
369
GPT-5.4 Mini (xhigh)openai/gpt-5.4-mini:xhigh
OpenAI43.5$0.75 / $4.501 of 15 benchmarks27.0%
370
Granite 4.2 3Bibm-granite/granite-4.2-3b
IBM43.5—1 of 15 benchmarks1377
371
GPT-4.1 Nanoopenai/gpt-4.1-nano
OpenAI43.4$0.10 / $0.401 of 15 benchmarks1373
372
Mistral Large 3mistralai/mistral-large-3
Mistral AI43.3—2 of 15 benchmarks14711233
373
Devstral Small 2507mistralai/devstral-small-2507
Mistral AI43.3—1 of 15 benchmarks38.0%
374
DeepSeek V4 Flash 0423 (xhigh)deepseek/deepseek-v4-flash:xhigh
DeepSeek43.2$0.091 / $0.1822 of 15 benchmarks20.9%27.0
375
GPT-5.1-Codexopenai/gpt-5.1-codex
OpenAI43.2$1.25 / $10.001 of 15 benchmarks1338
376
Mimo v2 Flashxiaomi/mimo-v2-flash
Xiaomi43.1—2 of 15 benchmarks14471331
377
gpt-oss-20bopenai/gpt-oss-20b
OpenAI43.0$0.03 / $0.131 of 15 benchmarks1368
378
GPT-5 Nano (medium)openai/gpt-5-nano:medium
OpenAI42.9$0.05 / $0.401 of 15 benchmarks34.8%
379
Granite 4.2 8Bibm-granite/granite-4.2-8b
IBM42.9$0.06 / $0.251 of 15 benchmarks1366
380
Mercuryinception/mercury
Inception42.8—1 of 15 benchmarks1364
381
GPT-6 Luna (low)openai/gpt-6-luna:low
OpenAI42.8$0.10 / $0.501 of 15 benchmarks25.7%
382
GLM 4.6z-ai/glm-4.6
Z.ai42.6$0.50 / $2.003 of 15 benchmarks55.4%14581342
383
Grok 4.1 Fast (reasoning)x-ai/grok-4-1-fast:reasoning
SpaceXAI42.6—2 of 15 benchmarks14611242
384
GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20
OpenAI42.6$2.50 / $10.001 of 15 benchmarks31.0%
385
Composer 2.5 (none)cursor/composer-2.5:none
Cursor42.5—1 of 15 benchmarks25.6%
386
Llama 3.3 Nemotron Super 49B v1nvidia/llama-3.3-nemotron-super-49b-v1
NVIDIA42.4—1 of 15 benchmarks1362
387
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview
Google42.4$0.25 / $1.502 of 15 benchmarks14571256
388
Mistral Small 3.1 24B Instruct 2503mistralai/mistral-small-3.1-24b-instruct-2503
Mistral AI42.3—1 of 15 benchmarks1361
389
GLM 5.2 (none)z-ai/glm-5.2:none
Z.ai42.3$0.006 / $6.801 of 15 benchmarks24.5%
390
Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b
NVIDIA42.2$0.06 / $0.241 of 15 benchmarks1361
391
Laguna XS.2poolside/laguna-xs.2
Poolside42.0—1 of 15 benchmarks1303
392
Claude Sonnet 4.6 (max)anthropic/claude-sonnet-4.6:max
Anthropic42.0$3.00 / $15.001 of 15 benchmarks24.3%
393
OLMo 3 32B Thinkallenai/olmo-3-32b-think
Allen Institute for AI41.9—1 of 15 benchmarks1360
394
Hunyuan Large Visiontencent/hunyuan-large-vision
Tencent41.8—1 of 15 benchmarks1358
395
GPT-5.6 Sol (low)openai/gpt-5.6-sol:low
OpenAI41.7$4.00 / $20.002 of 15 benchmarks45.4%35.4%
396
Gemma 3 27Bgoogle/gemma-3-27b-it
Google41.7$0.08 / $0.451 of 15 benchmarks1358
397
Gemini 1.5 Pro 002google/gemini-1.5-pro-002
Google41.6—1 of 15 benchmarks1356
398
Claude Opus 4.6 (medium)anthropic/claude-opus-4.6:medium
Anthropic41.5$5.00 / $25.001 of 15 benchmarks23.7%
399
GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13
OpenAI41.4$5.00 / $15.004 of 15 benchmarks38.8%31.3%12.0%1369
400
Claude Haiku 4.5anthropic/claude-haiku-4.5
Anthropic41.3$1.00 / $5.003 of 15 benchmarks64.7%14811330
401
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct
Qwen41.3$0.36 / $0.401 of 15 benchmarks1355
402
Mistral Large 2407mistralai/mistral-large-2407
Mistral41.2$2.00 / $6.001 of 15 benchmarks1354
403
Qwen (max)qwen/qwen:max
Qwen41.0—1 of 15 benchmarks1352
404
Step 1o Turbo 202506stepfun/step-1o-turbo-202506
StepFun40.8—1 of 15 benchmarks1351
405
Gemini 3.6 Flash (low)google/gemini-3.6-flash:low
Google40.8$0.75 / $3.751 of 15 benchmarks22.8%
406
KAT-Coder-Pro V1kwaipilot/kat-coder-pro-v1
Kwaipilot40.7—1 of 15 benchmarks1257
407
Gemini 2.5 Flashgoogle/gemini-2.5-flash
Google40.6$0.30 / $2.503 of 15 benchmarks28.7%61.9%1424
408
DeepSeek V3deepseek/deepseek-chat
DeepSeek40.5$0.32 / $0.893 of 15 benchmarks36.7%27.2%1387
409
Claude Sonnet 4.6 (medium)anthropic/claude-sonnet-4.6:medium
Anthropic40.5$3.00 / $15.001 of 15 benchmarks21.1%
410
Gemini 1.5 Pro 001google/gemini-1.5-pro-001
Google40.5—1 of 15 benchmarks1346
411
Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct
Meta40.4$0.59 / $0.791 of 15 benchmarks1346
412
GPT-5.4 Mini (medium)openai/gpt-5.4-mini:medium
OpenAI40.3$0.75 / $4.501 of 15 benchmarks20.8%
413
Mistral Large 2411mistralai/mistral-large-2411
Mistral AI40.3—1 of 15 benchmarks1346
414
Qwen 2.5qwen/qwen-2.5
Qwen40.2—2 of 15 benchmarks40.2%24.7%
415
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp
DeepSeek40.2$0.44 / $1.321 of 15 benchmarks14.8%
416
Amazon Nova Pro v1.0amazon/amazon-nova-pro-v1.0
Amazon40.1—1 of 15 benchmarks1343
417
Mimo v2 Flash (thinking)xiaomi/mimo-v2-flash:thinking
Xiaomi40.1—2 of 15 benchmarks14321292
418
DeepSeek V4 Flash 0731 (high)deepseek/deepseek-v4-flash-0731:high
DeepSeek40.0$0.0434 / $0.301 of 15 benchmarks18.8%
419
Gemini 2.0 Flash Lite Preview 02 05google/gemini-2.0-flash-lite-preview-02-05
Google40.0—1 of 15 benchmarks1342
420
GPT-4.1 Miniopenai/gpt-4.1-mini
OpenAI40.0$0.40 / $1.602 of 15 benchmarks23.9%1433
421
GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini
OpenAI40.0$0.25 / $2.001 of 15 benchmarks1245
422
Claude Opus 4.6 (low)anthropic/claude-opus-4.6:low
Anthropic39.8$5.00 / $25.001 of 15 benchmarks18.3%
423
Claude Sonnet 5 (medium)anthropic/claude-sonnet-5:medium
Anthropic39.7$2.00 / $10.002 of 15 benchmarks39.8%35.2%
424
Claude Opus 4.8 (low)anthropic/claude-opus-4.8:low
Anthropic39.7$5.00 / $25.002 of 15 benchmarks40.8%35.1%
425
OLMo 3.1 32B Thinkallenai/olmo-3.1-32b-think
Allen Institute for AI39.6—1 of 15 benchmarks1339
426
Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b
Qwen39.6$0.14 / $1.002 of 15 benchmarks14351253
427
Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct
Meta39.5—1 of 15 benchmarks1333
428
DeepSeek V4 Pro 0423 (none)deepseek/deepseek-v4-pro:none
DeepSeek39.5$0.8837 / $1.76751 of 15 benchmarks17.6%
429
Qwen3.5-Flashqwen/qwen3.5-flash-02-23
Qwen39.5$0.065 / $0.262 of 15 benchmarks14361244
430
GPT-4openai/gpt-4
OpenAI39.4$30.00 / $60.001 of 15 benchmarks1330
431
Claude 3 Sonnetanthropic/claude-3-sonnet
Anthropic39.3—1 of 15 benchmarks1318
432
Gemini 1.5 Flash 002google/gemini-1.5-flash-002
Google39.2—1 of 15 benchmarks1316
433
Gemma 3 12Bgoogle/gemma-3-12b-it
Google39.1$0.05 / $0.151 of 15 benchmarks1316
434
Claude Sonnet 4.6 (low)anthropic/claude-sonnet-4.6:low
Anthropic39.0$3.00 / $15.001 of 15 benchmarks15.0%
435
Mistral Small 24B Instruct 2501mistralai/mistral-small-24b-instruct-2501
Mistral AI38.9—1 of 15 benchmarks1312
436
Gemini 1.5 Flash 001google/gemini-1.5-flash-001
Google38.8—1 of 15 benchmarks1309
437
MiniMax M3 (none)minimax/minimax-m3:none
MiniMax38.8$0.30 / $1.201 of 15 benchmarks14.7%
438
GPT 4 1106 Previewopenai/gpt-4-1106-preview
OpenAI38.7—4 of 15 benchmarks22.4%28.3%12.5%1340
439
Muse Spark 1.2meta/muse-spark-1.2
Meta38.7$1.25 / $4.251 of 15 benchmarks12.0%
440
Gemma 3n E4Bgoogle/gemma-3n-e4b-it
Google38.7—1 of 15 benchmarks1307
441
Amazon Nova Lite v1.0amazon/amazon-nova-lite-v1.0
Amazon38.6—1 of 15 benchmarks1305
442
Mistral Largemistralai/mistral-large
Mistral38.3$2.00 / $6.001 of 15 benchmarks1296
443
Nemotron 3 Ultra (none)nvidia/nemotron-3-ultra-550b-a55b:none
NVIDIA38.3$0.60 / $2.401 of 15 benchmarks13.6%
444
DeepSeek V3.2deepseek/deepseek-v3.2
DeepSeek38.3$0.26 / $0.383 of 15 benchmarks59.0%14691326
445
Amazon Nova Micro v1.0amazon/amazon-nova-micro-v1.0
Amazon38.2—1 of 15 benchmarks1288
446
Grok 4 Fast (reasoning)x-ai/grok-4-fast:reasoning
SpaceXAI38.2—2 of 15 benchmarks14391162
447
Command R (08-2024)cohere/command-r-08-2024
Cohere38.1$0.15 / $0.601 of 15 benchmarks1281
448
Qwen3.7 Plus (none)qwen/qwen3.7-plus:none
Qwen38.0$0.32 / $1.281 of 15 benchmarks10.2%
449
Command R+ (08-2024)cohere/command-r-plus-08-2024
Cohere38.0$2.50 / $10.001 of 15 benchmarks1280
450
OLMo 2 0325 32B Instructallenai/olmo-2-0325-32b-instruct
Allen Institute for AI37.9—1 of 15 benchmarks1280
451
MiniMax M2minimax/minimax-m2
MiniMax37.8—3 of 15 benchmarks61.0%13831299
452
SWE-1.6 (none)cognition/swe-1.6:none
Cognition37.8—1 of 15 benchmarks9.4%
453
Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct
Mistral37.7$2.00 / $6.001 of 15 benchmarks1278
454
Grok Code Fast 1x-ai/grok-code-fast-1
SpaceXAI37.7—1 of 15 benchmarks1164
455
Gemma 3 4Bgoogle/gemma-3-4b-it
Google37.6—1 of 15 benchmarks1273
456
GPT-5.4 Mini (low)openai/gpt-5.4-mini:low
OpenAI37.5$0.75 / $4.501 of 15 benchmarks9.3%
457
Gemini 1.5 Flash 8B 001google/gemini-1.5-flash-8b-001
Google37.5—1 of 15 benchmarks1271
458
GPT-5.6 Terra (medium)openai/gpt-5.6-terra:medium
OpenAI37.5$2.00 / $12.002 of 15 benchmarks35.1%33.9%
459
Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct
Meta37.4$0.02 / $0.041 of 15 benchmarks1260
460
Devstral Medium 2507mistralai/devstral-medium-2507
Mistral AI37.3—1 of 15 benchmarks1072
461
Mistral Medium 3.5 (none)mistralai/mistral-medium-3-5:none
Mistral37.3$1.50 / $7.501 of 15 benchmarks8.0%
462
GPT-4oopenai/gpt-4o
OpenAI37.3$2.50 / $10.001 of 15 benchmarks12.2%
463
QwQ 32B Previewqwen/qwq-32b-preview
Qwen37.3—1 of 15 benchmarks1174
464
Inklingthinkingmachines/inkling
Thinking Machines37.2$1.00 / $4.054 of 15 benchmarks14.0%4.1%14941414
465
Trinity Large Thinkingarcee-ai/trinity-large-thinking
Arcee AI37.0—2 of 15 benchmarks14121236
466
gpt-oss-120bopenai/gpt-oss-120b
OpenAI37.0$0.15 / $0.602 of 15 benchmarks26.0%1389
467
GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06
OpenAI36.5$2.50 / $10.005 of 15 benchmarks27.0%39.7%30.4%29.5%1360
468
Devstral 2 2512mistralai/devstral-2512
Mistral36.5$0.40 / $2.002 of 15 benchmarks53.8%1196
469
GPT-5 Miniopenai/gpt-5-mini
OpenAI36.5$0.25 / $2.002 of 15 benchmarks56.2%39.7%
470
Claude Opus 4.8 (medium)anthropic/claude-opus-4.8:medium
Anthropic36.1$5.00 / $25.004 of 15 benchmarks48.7%40.5%20.9%19.0
471
Claude Sonnet 5 (low)anthropic/claude-sonnet-5:low
Anthropic35.4$2.00 / $10.002 of 15 benchmarks30.5%28.7%
472
Kimi K3 (low)moonshotai/kimi-k3:low
MoonshotAI34.9$0.192 / $16.002 of 15 benchmarks18.6%22.0
473
Llama 4 Maverick 17B 128e Instructmeta-llama/llama-4-maverick-17b-128e-instruct
Meta34.7—2 of 15 benchmarks21.0%1372
474
Claude 3 Opusanthropic/claude-3-opus
Anthropic34.7—4 of 15 benchmarks15.8%26.3%10.5%1355
475
Mercury 2inception/mercury-2
Inception34.7—2 of 15 benchmarks13921171
476
Gemini 2.0 Flash 001google/gemini-2.0-flash-001
Google33.7—2 of 15 benchmarks13.5%1363
477
GPT-4 Turboopenai/gpt-4-turbo
OpenAI33.5—2 of 15 benchmarks28.7%1347
478
Claude 2anthropic/claude-2
Anthropic33.3—3 of 15 benchmarks4.4%3.0%2.0%
479
Llama 4 Scout 17B 16e Instructmeta-llama/llama-4-scout-17b-16e-instruct
Meta33.3—2 of 15 benchmarks9.1%1363
480
Claude Sonnet 4.6 (high)anthropic/claude-sonnet-4.6:high
Anthropic32.8$3.00 / $15.002 of 15 benchmarks29.9%23.5%
481
GPT-5.6 Luna (medium)openai/gpt-5.6-luna:medium
OpenAI32.6$0.20 / $1.202 of 15 benchmarks11.3%25.7%
482
GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18
OpenAI32.6$0.15 / $0.602 of 15 benchmarks27.5%1348
483
GPT-5.6 Terra (low)openai/gpt-5.6-terra:low
OpenAI32.4$2.00 / $12.002 of 15 benchmarks24.1%24.1%
484
Granite 4.1 8Bibm-granite/granite-4.1-8b
IBM31.5—2 of 15 benchmarks13531193
485
Qwen2.5 Coder 32B Instructqwen/qwen2.5-coder-32b-instruct
Qwen31.1—2 of 15 benchmarks9.0%1342
486
Gemini 3.1 Pro Preview (high)google/gemini-3.1-pro-preview:high
Google30.5$2.00 / $12.002 of 15 benchmarks11.7%8.9%
487
GPT-5.6 Luna (low)openai/gpt-5.6-luna:low
OpenAI29.4$0.20 / $1.202 of 15 benchmarks1.6%15.4%
488
SWE Llamaprinceton-nlp/swe-llama
Princeton NLP28.7—3 of 15 benchmarks1.4%1.3%0.7%
489
GLM 5.2 (high)z-ai/glm-5.2:high
Z.ai27.5$0.006 / $6.803 of 15 benchmarks36.3%17.4%18.0
490
Claude 3 Haikuanthropic/claude-3-haiku
Anthropic27.4—3 of 15 benchmarks40.6%20.2%1301
491
SWE Llama 13Bprinceton-nlp/swe-llama-13b
Princeton NLP27.0—3 of 15 benchmarks1.2%1.0%0.7%
492
Claude Opus 4.7 (medium)anthropic/claude-opus-4.7:medium
Anthropic26.7$5.00 / $25.003 of 15 benchmarks28.9%7.0%7.0
493
GPT 3.5openai/gpt-3.5
OpenAI22.4—3 of 15 benchmarks0.4%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.