llm leaderboard

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.

451 of 451 ranked models
Ranked models
rankmodelvendorcompositepricein / outbenchmarks%%%%%elo
1
GPT-6.1 Sol (max)openai/gpt-6.1-sol:max
OpenAI82.1$2.00 / $10.004 of 6 benchmarks93.7%100.0%100.0%1498
2
Claude Fable 5 (max)anthropic/claude-fable-5:max
Anthropic81.5$10.00 / $50.004 of 6 benchmarks100.0%87.0%100.0%99.7%
3
Claude Fable 5.1 (max)anthropic/claude-fable-5.1:max
Anthropic81.4$10.00 / $50.004 of 6 benchmarks90.2%87.8%100.0%1525
4
GPT-6 Astra (max)openai/gpt-6-astra:max
OpenAI80.6$10.00 / $50.004 of 6 benchmarks93.7%97.6%100.0%1481
5
Gemini 4 Argon (high)google/gemini-4-argon:high
Google80.0$2.00 / $10.004 of 6 benchmarks86.0%78.0%100.0%1528
6
Claude Fable 5.2 (max)anthropic/claude-fable-5.2:max
Anthropic79.4$8.00 / $40.003 of 6 benchmarks95.1%100.0%99.7%
7
Claude Opus 5.5 (max)anthropic/claude-opus-5.5:max
Anthropic78.7$4.00 / $20.003 of 6 benchmarks91.2%95.0%100.0%
8
GPT-6.1 Terra (max)openai/gpt-6.1-terra:max
OpenAI78.3$1.00 / $5.003 of 6 benchmarks90.9%92.7%100.0%
9
Claude Opus 5 (max)anthropic/claude-opus-5:max
Anthropic78.1$5.00 / $25.004 of 6 benchmarks85.6%73.2%98.9%1515
10
GPT-5.6 Sol (max)openai/gpt-5.6-sol:max
OpenAI77.2$4.00 / $20.003 of 6 benchmarks89.1%82.9%100.0%
11
Muse Wonder (max)meta/muse-wonder:max
Meta76.8$4.00 / $20.004 of 6 benchmarks82.1%70.7%99.4%1495
12
Claude Sonnet 5.5 (max)anthropic/claude-sonnet-5.5:max
Anthropic76.8$2.00 / $10.003 of 6 benchmarks88.8%80.5%100.0%
13
GPT-5.4 (high)openai/gpt-5.4:high
OpenAI75.8$2.50 / $15.004 of 6 benchmarks80.0%50.0%97.8%1491
14
GPT-6 Sol (max)openai/gpt-6-sol:max
OpenAI75.8$2.00 / $10.004 of 6 benchmarks89.8%90.0%100.0%1440
15
Claude Fable 5 (high)anthropic/claude-fable-5:high
Anthropic75.0$10.00 / $50.002 of 6 benchmarks100.0%1521
16
GPT-5.6 Terra (max)openai/gpt-5.6-terra:max
OpenAI74.7$2.00 / $12.003 of 6 benchmarks86.0%70.7%99.7%
17
Kimi K3.1 Pro (max)moonshotai/kimi-k3.1-pro:max
MoonshotAI73.6$2.00 / $10.003 of 6 benchmarks78.3%65.8%100.0%
18
Claude Opus 4.8 (max)anthropic/claude-opus-4.8:max
Anthropic73.3$5.00 / $25.004 of 6 benchmarks47.2%80.0%56.1%98.3%
19
GPT-5.6 Luna (max)openai/gpt-5.6-luna:max
OpenAI72.5$0.20 / $1.203 of 6 benchmarks82.1%61.0%98.3%
20
GPT 5.5 Pro Pre Release (xhigh)openai/gpt-5.5-pro-pre-release:xhigh
OpenAI72.4—3 of 6 benchmarks51.0%39.6%100.0%
21
Kimi K3 (max)moonshotai/kimi-k3:max
MoonshotAI72.2$0.192 / $16.004 of 6 benchmarks72.2%39.0%97.2%1502
22
GPT 5.5 Pre Release (xhigh)openai/gpt-5.5-pre-release:xhigh
OpenAI72.0—3 of 6 benchmarks51.7%35.4%100.0%
23
Gemini 3.7 Flash (high)google/gemini-3.7-flash:high
Google71.9$0.75 / $3.754 of 6 benchmarks71.6%36.6%97.2%1502
24
GPT-6 Luna (max)openai/gpt-6-luna:max
OpenAI71.9$0.10 / $0.504 of 6 benchmarks79.0%56.1%98.9%1450
25
GPT-5.4 Pro (xhigh)openai/gpt-5.4-pro:xhigh
OpenAI71.6$30.00 / $180.003 of 6 benchmarks50.0%82.5%58.5%
26
Muse Spark 1.3 (max)meta/muse-spark-1.3:max
Meta71.5$1.25 / $4.253 of 6 benchmarks74.0%46.3%1507
27
Gemini 3.5 Flash (high)google/gemini-3.5-flash:high
Google71.2$1.50 / $9.005 of 6 benchmarks80.0%62.8%26.8%95.6%1497
28
GPT-5.5 Pro (xhigh)openai/gpt-5.5-pro:xhigh
OpenAI71.1$30.00 / $180.002 of 6 benchmarks87.7%78.0%
29
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview
Google71.1$2.00 / $12.005 of 6 benchmarks88.9%59.6%26.8%95.6%1488
30
Qwen3.8 Max (xhigh)qwen/qwen3.8-max:xhigh
Qwen71.1—3 of 6 benchmarks74.7%46.3%99.4%
31
GPT-5.4 (xhigh)openai/gpt-5.4:xhigh
OpenAI71.1$2.50 / $15.004 of 6 benchmarks47.6%78.6%49.0%95.3%
32
Gemini 3.8 Flash (high)google/gemini-3.8-flash:high
Google70.3$0.75 / $3.754 of 6 benchmarks68.4%21.9%98.9%1519
33
Muse Spark 1.3 (xhigh)meta/muse-spark-1.3:xhigh
Meta70.2$1.25 / $4.253 of 6 benchmarks74.4%41.5%99.2%
34
DeepSeek V4.1 Flash 1017 (max)deepseek/deepseek-v4.1-flash-1017:max
DeepSeek70.1$0.006 / $0.503 of 6 benchmarks71.2%46.3%99.4%
35
DeepSeek V4.1 Flash (max)deepseek/deepseek-v4.1-flash:max
DeepSeek69.6$0.051 / $0.5674 of 6 benchmarks67.4%26.8%98.3%1495
36
GPT-5.5 (xhigh)openai/gpt-5.5:xhigh
OpenAI69.6$5.00 / $30.002 of 6 benchmarks85.3%72.5%
37
Qwen3.7 Maxqwen/qwen3.7-max
Qwen68.0$1.475 / $4.4254 of 6 benchmarks64.6%34.1%95.6%1483
38
GLM 5.3 (max)z-ai/glm-5.3:max
Z.ai68.0$0.0699 / $1.404 of 6 benchmarks68.8%29.3%91.1%1502
39
Qwen3.8 Max (0902) (xhigh)qwen/qwen3.8-max-0902:xhigh
Qwen67.9$2.00 / $6.003 of 6 benchmarks65.6%34.1%100.0%
40
Claude Opus 5 (high)anthropic/claude-opus-5:high
Anthropic67.6$5.00 / $25.001 of 6 benchmarks1521
41
GPT-5.2 (high)openai/gpt-5.2:high
OpenAI67.4$1.75 / $14.004 of 6 benchmarks60.0%18.8%96.1%1457
42
Claude Opus 4.6 (max)anthropic/claude-opus-4.6:max
Anthropic67.4$5.00 / $25.004 of 6 benchmarks90.0%66.0%26.8%91.1%
43
Claude Opus 5.5 (high)anthropic/claude-opus-5.5:high
Anthropic67.3$4.00 / $20.001 of 6 benchmarks1518
44
GPT-5.2 (xhigh)openai/gpt-5.2:xhigh
OpenAI67.1$1.75 / $14.004 of 6 benchmarks40.7%67.4%31.7%96.1%
45
Claude Opus 4.6 (high)anthropic/claude-opus-4.6:high
Anthropic67.1$5.00 / $25.001 of 6 benchmarks1516
46
GPT-6 Astra (high)openai/gpt-6-astra:high
OpenAI66.9$10.00 / $50.001 of 6 benchmarks97.6%
47
GPT-6 Astra (xhigh)openai/gpt-6-astra:xhigh
OpenAI66.9$10.00 / $50.001 of 6 benchmarks97.6%
48
Muse Spark Open (xhigh)meta/muse-spark-open:xhigh
Meta66.8$1.25 / $4.253 of 6 benchmarks69.8%31.7%98.1%
49
Grok 4.6 (xhigh)x-ai/grok-4.6:xhigh
SpaceXAI66.8$2.00 / $6.003 of 6 benchmarks66.0%31.7%99.2%
50
GLM 5.3 Flashz-ai/glm-5.3-flash
Z.ai66.8$0.15 / $0.501 of 6 benchmarks1504
51
Claude Opus 4.6 (64K)anthropic/claude-opus-4.6:64k
Anthropic66.7$5.00 / $25.003 of 6 benchmarks90.0%20.8%94.4%
52
Qwen3.8 Maxqwen/qwen3.8-max
Qwen66.6—1 of 6 benchmarks1504
53
Kimi K2.6moonshotai/kimi-k2.6
MoonshotAI66.6$0.65 / $3.415 of 6 benchmarks39.0%57.2%25.6%96.1%1479
54
GPT 5.5 Pro Pre Release (high)openai/gpt-5.5-pro-pre-release:high
OpenAI66.5—2 of 6 benchmarks52.4%39.6%
55
Claude Opus 4.7 (high)anthropic/claude-opus-4.7:high
Anthropic66.5$5.00 / $25.001 of 6 benchmarks1504
56
GPT-6 Astra (medium)openai/gpt-6-astra:medium
OpenAI66.3$10.00 / $50.001 of 6 benchmarks97.6%
57
Claude Haiku 5.5 (max)anthropic/claude-haiku-5.5:max
Anthropic65.8$0.10 / $0.502 of 6 benchmarks75.1%46.3%
58
GPT-5.5openai/gpt-5.5
OpenAI65.8$5.00 / $30.001 of 6 benchmarks1500
59
Gemini 3.6 Flash (high)google/gemini-3.6-flash:high
Google65.6$0.75 / $3.754 of 6 benchmarks59.0%21.9%94.2%1501
60
GPT-5 (high)openai/gpt-5:high
OpenAI65.3$1.25 / $10.006 of 6 benchmarks32.4%55.4%21.9%91.4%98.1%1435
61
GPT-6 Astra (low)openai/gpt-6-astra:low
OpenAI65.2$10.00 / $50.001 of 6 benchmarks87.8%
62
Claude Opus 4.6 (32K)anthropic/claude-opus-4.6:32k
Anthropic65.2$5.00 / $25.003 of 6 benchmarks80.0%20.8%93.1%
63
GPT-5.6 Sol (xhigh)openai/gpt-5.6-sol:xhigh
OpenAI65.1$4.00 / $20.001 of 6 benchmarks1494
64
Muse Spark 1.1meta/muse-spark-1.1
Meta65.0$1.25 / $4.251 of 6 benchmarks1493
65
Claude Haiku 5.5 (xhigh)anthropic/claude-haiku-5.5:xhigh
Anthropic64.9$0.10 / $0.501 of 6 benchmarks98.9%
66
Claude Opus 4.8 (high)anthropic/claude-opus-4.8:high
Anthropic64.9$5.00 / $25.001 of 6 benchmarks1492
67
Gemini 3 Flash Previewgoogle/gemini-3-flash-preview
Google64.8$0.50 / $3.005 of 6 benchmarks60.0%51.2%17.1%92.8%1475
68
Grok 4.6 (high)x-ai/grok-4.6:high
SpaceXAI64.8$2.00 / $6.002 of 6 benchmarks97.8%1444
69
GPT-5.5 (high)openai/gpt-5.5:high
OpenAI64.8$5.00 / $30.001 of 6 benchmarks1491
70
GPT-6 Astra (none)openai/gpt-6-astra:none
OpenAI64.7$10.00 / $50.001 of 6 benchmarks82.9%
71
Claude Haiku 5.5 (high)anthropic/claude-haiku-5.5:high
Anthropic64.5$0.10 / $0.502 of 6 benchmarks97.2%1448
72
Muse Spark 1.2 (xhigh)meta/muse-spark-1.2:xhigh
Meta64.5$1.25 / $4.251 of 6 benchmarks1491
73
GPT-5.2 Pro (xhigh)openai/gpt-5.2-pro:xhigh
OpenAI64.5$21.00 / $168.002 of 6 benchmarks74.0%46.0%
74
DeepSeek V4 Pro 0813 (max)deepseek/deepseek-v4-pro-0813:max
DeepSeek64.4$0.111 / $4.443 of 6 benchmarks64.6%26.8%98.6%
75
Claude Opus 4.7anthropic/claude-opus-4.7
Anthropic64.4$5.00 / $25.001 of 6 benchmarks1490
76
Claude Sonnet 5.5 (xhigh)anthropic/claude-sonnet-5.5:xhigh
Anthropic64.3$2.00 / $10.001 of 6 benchmarks1489
77
Qwen3.7 Plusqwen/qwen3.7-plus
Qwen64.1$0.32 / $1.282 of 6 benchmarks93.3%1465
78
Hy3tencent/hy3
Tencent63.9$0.0825 / $0.331 of 6 benchmarks1484
79
GLM 5.2 (max)z-ai/glm-5.2:max
Z.ai63.8$0.006 / $6.804 of 6 benchmarks59.2%29.3%86.4%1487
80
DeepSeek V4 Pro 0423 (high)deepseek/deepseek-v4-pro:high
DeepSeek63.8$0.8837 / $1.76752 of 6 benchmarks95.6%1450
81
MiMo-V2.6-Proxiaomi/mimo-v2.6-pro
Xiaomi63.6$0.435 / $0.871 of 6 benchmarks1482
82
GPT-5.2 (medium)openai/gpt-5.2:medium
OpenAI63.5$1.75 / $14.003 of 6 benchmarks60.0%16.7%93.9%
83
Gemini 3.5 Flash (medium)google/gemini-3.5-flash:medium
Google63.5$1.50 / $9.001 of 6 benchmarks1481
84
Claude Opus 4.6anthropic/claude-opus-4.6
Anthropic63.4$5.00 / $25.003 of 6 benchmarks38.3%14.6%1503
85
Mistral Large 4 (high)mistralai/mistral-large-4-0:high
Mistral63.3$0.70 / $2.103 of 6 benchmarks58.6%26.8%98.3%
86
Claude Fable 5 (low)anthropic/claude-fable-5:low
Anthropic63.3$10.00 / $50.001 of 6 benchmarks97.8%
87
Claude Opus 4.8 (low)anthropic/claude-opus-4.8:low
Anthropic63.3$5.00 / $25.001 of 6 benchmarks97.8%
88
Claude Opus 5anthropic/claude-opus-5
Anthropic63.3$5.00 / $25.001 of 6 benchmarks97.8%
89
MiMo-V2.5-Proxiaomi/mimo-v2.5-pro
Xiaomi63.2$0.48 / $1.801 of 6 benchmarks1479
90
Inklingthinkingmachines/inkling
Thinking Machines63.0$1.00 / $4.051 of 6 benchmarks1479
91
GPT-5.6 Terra (xhigh)openai/gpt-5.6-terra:xhigh
OpenAI62.9$2.00 / $12.001 of 6 benchmarks1478
92
Gemini 2.5 Pro Preview 05-06google/gemini-2.5-pro-preview-05-06
Google62.8—1 of 6 benchmarks95.9%
93
Ernie 5.1baidu/ernie-5.1
Baidu62.7—1 of 6 benchmarks1478
94
GPT-5.6 Luna (xhigh)openai/gpt-5.6-luna:xhigh
OpenAI62.6$0.20 / $1.201 of 6 benchmarks1476
95
Claude Opus 4.8anthropic/claude-opus-4.8
Anthropic62.5$5.00 / $25.001 of 6 benchmarks1476
96
Gemini 3 Progoogle/gemini-3-pro
Google62.4—1 of 6 benchmarks1475
97
Seed 2.1 Turbo (high)bytedance-seed/seed-2-1-turbo:high
ByteDance Seed62.2$0.50 / $2.501 of 6 benchmarks96.1%
98
Muse Sparkmeta/muse-spark
Meta62.1—4 of 6 benchmarks39.0%14.6%88.9%1468
99
Claude Opus 4.7 (max)anthropic/claude-opus-4.7:max
Anthropic62.1$5.00 / $25.003 of 6 benchmarks70.2%31.7%86.7%
100
GPT-5 (medium)openai/gpt-5:medium
OpenAI62.0$1.25 / $10.004 of 6 benchmarks27.2%6.3%87.2%97.9%
101
Claude Opus 4.5 (high 32K)anthropic/claude-opus-4.5:high-32k
Anthropic62.0$5.00 / $25.001 of 6 benchmarks1472
102
Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b
Reflection61.9$0.30 / $1.001 of 6 benchmarks1472
103
Qwen3.6 Max Previewqwen/qwen3.6-max-preview
Qwen61.8—4 of 6 benchmarks50.0%4.2%91.1%1472
104
Claude Sonnet 5 (high)anthropic/claude-sonnet-5:high
Anthropic61.8$2.00 / $10.001 of 6 benchmarks1472
105
Grok 4.5 (high)x-ai/grok-4.5:high
SpaceXAI61.5$2.00 / $6.003 of 6 benchmarks57.2%24.4%97.8%
106
Step 5 Previewstepfun/step-5-preview
StepFun61.5$1.00 / $2.701 of 6 benchmarks1471
107
Grok 4.5x-ai/grok-4.5
SpaceXAI61.4$2.00 / $6.001 of 6 benchmarks1470
108
Kimi K2.5 (thinking)moonshotai/kimi-k2.5:thinking
MoonshotAI61.3$0.532 / $3.3251 of 6 benchmarks1470
109
Gemini 3 Flash Preview (high)google/gemini-3-flash-preview:high
Google61.2$0.50 / $3.001 of 6 benchmarks95.6%
110
Gemini 3.1 Pro Preview (high)google/gemini-3.1-pro-preview:high
Google61.2$2.00 / $12.001 of 6 benchmarks95.6%
111
GPT-5.4 (medium)openai/gpt-5.4:medium
OpenAI61.2$2.50 / $15.001 of 6 benchmarks95.6%
112
GPT-5.6 Sol (low)openai/gpt-5.6-sol:low
OpenAI61.2$4.00 / $20.001 of 6 benchmarks95.6%
113
GPT-5 Pro (high)openai/gpt-5-pro:high
OpenAI61.2$15.00 / $120.003 of 6 benchmarks60.0%55.8%19.5%
114
Gemma 4 26B A4B google/gemma-4-26b-a4b-it
Google61.1$0.0765 / $0.2551 of 6 benchmarks1469
115
Qwen3.5 Max Previewqwen/qwen3.5-max-preview
Qwen60.9—1 of 6 benchmarks1468
116
MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash
Xiaomi60.8$0.14 / $0.281 of 6 benchmarks1468
117
Grok 4.7 (xhigh)x-ai/grok-4.7:xhigh
SpaceXAI60.7$2.00 / $6.004 of 6 benchmarks53.0%17.1%98.1%1444
118
Gemma 4 31Bgoogle/gemma-4-31b-it
Google60.6$0.20 / $0.401 of 6 benchmarks1467
119
Claude Sonnet 5 (xhigh)anthropic/claude-sonnet-5:xhigh
Anthropic60.6$2.00 / $10.001 of 6 benchmarks94.7%
120
Grok 4.20 Beta 0309 (reasoning)x-ai/grok-4.20-beta-0309:reasoning
SpaceXAI60.4—1 of 6 benchmarks1464
121
DeepSeek V4 Flash 0731 (max)deepseek/deepseek-v4-flash-0731:max
DeepSeek60.0$0.0434 / $0.303 of 6 benchmarks57.5%24.4%94.4%
122
Claude Sonnet 4.6anthropic/claude-sonnet-4.6
Anthropic60.0$3.00 / $15.001 of 6 benchmarks1461
123
GLM 5.1z-ai/glm-5.1
Z.ai60.0$1.40 / $4.405 of 6 benchmarks33.5%36.8%12.5%93.3%1474
124
Qwen3.6 Plusqwen/qwen3.6-plus
Qwen59.9$0.325 / $1.955 of 6 benchmarks50.0%38.3%8.3%93.3%1452
125
Gemini 3 Pro Previewgoogle/gemini-3-pro-preview
Google59.9—3 of 6 benchmarks37.6%18.8%91.4%
126
GPT-5.4openai/gpt-5.4
OpenAI59.9$2.50 / $15.001 of 6 benchmarks1459
127
Mistral Large 4mistralai/mistral-large-4-0
Mistral59.8$0.70 / $2.101 of 6 benchmarks1459
128
GPT-5.1 (high)openai/gpt-5.1:high
OpenAI59.7$1.25 / $10.004 of 6 benchmarks31.0%12.5%88.6%1458
129
Claude Opus 5 (low)anthropic/claude-opus-5:low
Anthropic59.5$5.00 / $25.001 of 6 benchmarks93.3%
130
Kimi K3 (high)moonshotai/kimi-k3:high
MoonshotAI59.5$0.192 / $16.001 of 6 benchmarks93.3%
131
Grok 4.20 Multi Agent Beta 0309x-ai/grok-4.20-multi-agent-beta-0309
SpaceXAI59.4—1 of 6 benchmarks1455
132
Claude Sonnet 4.5 (high 32K)anthropic/claude-sonnet-4.5:high-32k
Anthropic59.3$3.00 / $15.001 of 6 benchmarks1455
133
Gemini 3 Flash Preview (minimal)google/gemini-3-flash-preview:minimal
Google59.1$0.50 / $3.001 of 6 benchmarks1453
134
GPT-5.2 Chatopenai/gpt-5.2-chat
OpenAI59.0—1 of 6 benchmarks1453
135
GPT-5 Mini (high)openai/gpt-5-mini:high
OpenAI58.8$0.25 / $2.006 of 6 benchmarks27.2%46.7%12.2%86.7%97.8%1407
136
Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b
NVIDIA58.8$0.60 / $2.402 of 6 benchmarks86.7%1443
137
Inkling Smallthinkingmachines/inkling-small
Thinking Machines58.8$0.45 / $1.201 of 6 benchmarks1451
138
Mimo v2 Proxiaomi/mimo-v2-pro
Xiaomi58.6—1 of 6 benchmarks1451
139
Qwen3.8 27Bqwen/qwen3.8-27b
Qwen58.3$0.15 / $1.8751 of 6 benchmarks1450
140
Claude Sonnet 5 (max)anthropic/claude-sonnet-5:max
Anthropic58.0$2.00 / $10.003 of 6 benchmarks65.6%29.3%80.0%
141
Seed-2.0-Lite (high)bytedance-seed/seed-2.0-lite:high
ByteDance Seed58.0$0.25 / $2.001 of 6 benchmarks91.1%
142
Dola Seed 2.0 Probytedance/dola-seed-2.0-pro
ByteDance58.0—1 of 6 benchmarks1449
143
o3openai/o3
OpenAI57.8$2.00 / $8.001 of 6 benchmarks1448
144
GLM 5.3 Flash (max)z-ai/glm-5.3-flash:max
Z.ai57.5$0.15 / $0.503 of 6 benchmarks55.8%17.1%93.9%
145
Claude Opus 4.1 (thinking 16K)anthropic/claude-opus-4.1:thinking-16k
Anthropic57.4$15.00 / $75.001 of 6 benchmarks1444
146
DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro
DeepSeek57.3$0.8837 / $1.76751 of 6 benchmarks1443
147
Gemini 3.5 Flash (low)google/gemini-3.5-flash:low
Google57.1$1.50 / $9.001 of 6 benchmarks88.9%
148
GPT-5.6 Terra (low)openai/gpt-5.6-terra:low
OpenAI57.1$2.00 / $12.001 of 6 benchmarks88.9%
149
gpt-oss-120b (high)openai/gpt-oss-120b:high
OpenAI57.1$0.15 / $0.601 of 6 benchmarks88.9%
150
Grok 4.1 (thinking)x-ai/grok-4.1:thinking
SpaceXAI56.9—1 of 6 benchmarks1443
151
Kimi K2.5 Instantmoonshotai/kimi-k2.5-instant
Moonshot AI56.8—1 of 6 benchmarks1442
152
o4 Mini Highopenai/o4-mini-high
OpenAI56.7—5 of 6 benchmarks24.8%36.1%4.9%81.7%97.8%
153
Muse Glimmer 30Bmeta/muse-glimmer-30b
Meta56.6$0.30 / $1.201 of 6 benchmarks1442
154
Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite
Google56.5$0.30 / $2.501 of 6 benchmarks1442
155
DeepSeek V4 Flash 0423 (high)deepseek/deepseek-v4-flash:high
DeepSeek56.4$0.091 / $0.1821 of 6 benchmarks1441
156
Kimi K2.7 Codemoonshotai/kimi-k2.7-code
MoonshotAI56.1$0.60 / $3.503 of 6 benchmarks54.0%12.2%95.6%
157
GPT-5.4 Mini (high)openai/gpt-5.4-mini:high
OpenAI56.1$0.75 / $4.504 of 6 benchmarks50.0%2.1%87.2%1439
158
Kimi K2 Thinking Turbomoonshotai/kimi-k2-thinking-turbo
Moonshot AI56.1—3 of 6 benchmarks20.0%83.1%1436
159
GPT-5 Mini (medium)openai/gpt-5-mini:medium
OpenAI55.9$0.25 / $2.004 of 6 benchmarks20.3%4.2%78.3%96.8%
160
MiMo-V2.5xiaomi/mimo-v2.5
Xiaomi55.9$0.40 / $2.001 of 6 benchmarks1437
161
GLM 5V Turboz-ai/glm-5v-turbo
Z.ai55.8$1.20 / $4.001 of 6 benchmarks1436
162
Kimi K2p5moonshotai/kimi-k2p5
Moonshot AI55.7—3 of 6 benchmarks27.9%4.2%92.2%
163
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview
Google55.6$0.25 / $1.501 of 6 benchmarks1436
164
Claude Opus 4.7 (xhigh)anthropic/claude-opus-4.7:xhigh
Anthropic55.6$5.00 / $25.003 of 6 benchmarks43.8%0.0%97.8%
165
Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b
Qwen55.5$0.60 / $3.603 of 6 benchmarks29.5%88.9%1450
166
Ernie 5.0 0110baidu/ernie-5.0-0110
Baidu55.3—1 of 6 benchmarks1434
167
Mimo v2 Omnixiaomi/mimo-v2-omni
Xiaomi55.1—1 of 6 benchmarks1433
168
Claude Sonnet 4.6 (32K)anthropic/claude-sonnet-4.6:32k
Anthropic55.0$3.00 / $15.001 of 6 benchmarks85.8%
169
Grok 4.20 0309 (reasoning)x-ai/grok-4.20-0309:reasoning
SpaceXAI55.0—3 of 6 benchmarks44.9%17.1%92.2%
170
GPT-5.2openai/gpt-5.2
OpenAI54.9$1.75 / $14.001 of 6 benchmarks1432
171
GPT-5.3 Chatopenai/gpt-5.3-chat
OpenAI54.8—1 of 6 benchmarks1430
172
Inkling Small (xhigh)thinkingmachines/inkling-small:xhigh
Thinking Machines54.7$0.45 / $1.203 of 6 benchmarks46.3%17.1%90.0%
173
Hy3 previewtencent/hy3-preview
Tencent54.6$0.18 / $0.601 of 6 benchmarks1429
174
Grok 4.3 (high)x-ai/grok-4.3:high
SpaceXAI54.5$1.25 / $2.503 of 6 benchmarks42.8%14.6%93.3%
175
DeepSeek V3.2 (thinking)deepseek/deepseek-v3.2:thinking
DeepSeek54.5$0.26 / $0.381 of 6 benchmarks1429
176
GPT-5.4 Nano (high)openai/gpt-5.4-nano:high
OpenAI54.4$0.20 / $1.255 of 6 benchmarks25.9%44.9%12.2%87.8%1424
177
Claude Opus 4.8 (none)anthropic/claude-opus-4.8:none
Anthropic54.3$5.00 / $25.001 of 6 benchmarks84.4%
178
GPT-5.4 (low)openai/gpt-5.4:low
OpenAI54.3$2.50 / $15.001 of 6 benchmarks84.4%
179
GPT-5.5 (low)openai/gpt-5.5:low
OpenAI54.3$5.00 / $30.001 of 6 benchmarks84.4%
180
Mistral Medium 3.5mistralai/mistral-medium-3-5
Mistral54.3$1.50 / $7.501 of 6 benchmarks1427
181
GPT-5.2 (low)openai/gpt-5.2:low
OpenAI54.1$1.75 / $14.003 of 6 benchmarks40.0%6.3%78.9%
182
Grok 4.1x-ai/grok-4.1
SpaceXAI54.0—1 of 6 benchmarks1426
183
Qwen3.5 Plusqwen/qwen3.5-plus
Qwen54.0$0.30 / $1.803 of 6 benchmarks50.0%2.1%86.7%
184
Qwen3.6 27Bqwen/qwen3.6-27b
Qwen54.0$0.32 / $3.202 of 6 benchmarks35.1%91.1%
185
Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b
Qwen53.5$0.26 / $2.081 of 6 benchmarks1425
186
Claude Sonnet 4.6 (medium)anthropic/claude-sonnet-4.6:medium
Anthropic53.3$3.00 / $15.001 of 6 benchmarks82.2%
187
Gemini 3.6 Flash (low)google/gemini-3.6-flash:low
Google53.3$0.75 / $3.751 of 6 benchmarks82.2%
188
Gemma 4 26B A4B (minimal)google/gemma-4-26b-a4b-it:minimal
Google53.3$0.0765 / $0.2551 of 6 benchmarks82.2%
189
DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash
DeepSeek53.3$0.091 / $0.1821 of 6 benchmarks1424
190
Qwen3 Maxqwen/qwen3-max
Qwen53.1—4 of 6 benchmarks18.9%73.3%97.1%1425
191
Grok 4 Fastx-ai/grok-4-fast
SpaceXAI53.0—1 of 6 benchmarks1424
192
DeepSeek V4 Pro 0423 (max)deepseek/deepseek-v4-pro:max
DeepSeek53.0$0.8837 / $1.76753 of 6 benchmarks45.3%2.4%96.7%
193
GPT-5.4 Mini (xhigh)openai/gpt-5.4-mini:xhigh
OpenAI52.9$0.75 / $4.503 of 6 benchmarks51.2%9.8%88.9%
194
GPT-5.1openai/gpt-5.1
OpenAI52.9$1.25 / $10.001 of 6 benchmarks1423
195
Qwen3.5-27Bqwen/qwen3.5-27b
Qwen52.8$0.26 / $2.601 of 6 benchmarks1423
196
MiniMax M2.7minimax/minimax-m2.7
MiniMax52.6$0.21 / $0.841 of 6 benchmarks1422
197
DeepSeek V3.2 Exp (thinking)deepseek/deepseek-v3.2-exp:thinking
DeepSeek52.5$0.27 / $0.411 of 6 benchmarks1422
198
Claude Opus 4 (thinking 16K)anthropic/claude-opus-4:thinking-16k
Anthropic52.4—1 of 6 benchmarks1421
199
GLM 5.2 (low)z-ai/glm-5.2:low
Z.ai52.3$0.006 / $6.802 of 6 benchmarks54.7%75.6%
200
Gemini 3.5 Flash (minimal)google/gemini-3.5-flash:minimal
Google52.3$1.50 / $9.001 of 6 benchmarks80.0%
201
Gemini 3.6 Flash (minimal)google/gemini-3.6-flash:minimal
Google52.3$0.75 / $3.751 of 6 benchmarks80.0%
202
Grok 4.1 Fast (reasoning)x-ai/grok-4-1-fast:reasoning
SpaceXAI52.3—1 of 6 benchmarks1420
203
GPT-5.1 (medium)openai/gpt-5.1:medium
OpenAI52.3$1.25 / $10.003 of 6 benchmarks26.9%4.2%85.6%
204
o3 (high)openai/o3:high
OpenAI52.2$2.00 / $8.005 of 6 benchmarks18.7%33.3%2.1%83.9%97.8%
205
Grok 4.3x-ai/grok-4.3
SpaceXAI52.1$1.25 / $2.501 of 6 benchmarks1418
206
o4 Miniopenai/o4-mini
OpenAI52.0—1 of 6 benchmarks1418
207
Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl
NVIDIA51.8$0.15 / $0.471 of 6 benchmarks1417
208
MiniMax M3minimax/minimax-m3
MiniMax51.7$0.30 / $1.202 of 6 benchmarks71.1%1425
209
Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507
Qwen51.6$0.14 / $0.801 of 6 benchmarks1416
210
Kimi K2 0905moonshotai/kimi-k2-0905
MoonshotAI51.5$0.60 / $2.501 of 6 benchmarks1416
211
Claude Sonnet 4.6 (16K)anthropic/claude-sonnet-4.6:16k
Anthropic51.4$3.00 / $15.002 of 6 benchmarks80.0%0.0%
212
DeepSeek V3.1 (thinking)deepseek/deepseek-chat-v3.1:thinking
DeepSeek51.4$0.25 / $0.951 of 6 benchmarks1415
213
R1deepseek/deepseek-r1
DeepSeek51.3—3 of 6 benchmarks53.3%93.0%1412
214
Solar Pro 4upstage/solar-pro4
Upstage51.3$0.15 / $0.601 of 6 benchmarks1414
215
Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct
Qwen51.1$0.09 / $1.101 of 6 benchmarks1414
216
LongCat Flash Chatmeituan/longcat-flash-chat
Meituan51.0—1 of 6 benchmarks1414
217
Claude Opus 4.5 (16K)anthropic/claude-opus-4.5:16k
Anthropic50.9$5.00 / $25.003 of 6 benchmarks40.0%2.1%81.7%
218
Claude Sonnet 4.6 (high)anthropic/claude-sonnet-4.6:high
Anthropic50.9$3.00 / $15.001 of 6 benchmarks75.6%
219
DeepSeek V3.1deepseek/deepseek-chat-v3.1
DeepSeek50.9$0.25 / $0.951 of 6 benchmarks1413
220
Grok 4 Fast (reasoning)x-ai/grok-4-fast:reasoning
SpaceXAI50.6—1 of 6 benchmarks1412
221
Ernie 5.0 Preview 1203baidu/ernie-5.0-preview-1203
Baidu50.4—1 of 6 benchmarks1411
222
Claude Opus 4.5 (32K)anthropic/claude-opus-4.5:32k
Anthropic50.3$5.00 / $25.004 of 6 benchmarks20.7%34.4%4.9%86.1%
223
Gemma 4 31B (minimal)google/gemma-4-31b-it:minimal
Google50.3$0.20 / $0.401 of 6 benchmarks73.3%
224
GPT 5 Chatopenai/gpt-5-chat
OpenAI50.3—1 of 6 benchmarks1411
225
Claude Sonnet 4.5 (59K)anthropic/claude-sonnet-4.5:59k
Anthropic50.2$3.00 / $15.002 of 6 benchmarks13.5%77.8%
226
DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp
DeepSeek50.1$0.27 / $0.411 of 6 benchmarks1410
227
Claude Sonnet 4.5 (32K)anthropic/claude-sonnet-4.5:32k
Anthropic50.1$3.00 / $15.005 of 6 benchmarks15.2%23.9%2.4%77.8%97.7%
228
Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct
Qwen49.9$0.21 / $1.901 of 6 benchmarks1409
229
Claude Opus 4.5anthropic/claude-opus-4.5
Anthropic49.9$5.00 / $25.004 of 6 benchmarks20.7%4.2%48.1%1463
230
o3 (medium)openai/o3:medium
OpenAI49.7$2.00 / $8.003 of 6 benchmarks16.9%29.8%84.4%
231
Claude Sonnet 4 (32K)anthropic/claude-sonnet-4:32k
Anthropic49.7—1 of 6 benchmarks71.1%
232
Claude Sonnet 4.5 (16K)anthropic/claude-sonnet-4.5:16k
Anthropic49.7$3.00 / $15.001 of 6 benchmarks71.1%
233
Claude Sonnet 4.6 (max)anthropic/claude-sonnet-4.6:max
Anthropic49.7$3.00 / $15.001 of 6 benchmarks71.1%
234
Step 3.5 Flashstepfun/step-3.5-flash
StepFun49.5$0.10 / $0.301 of 6 benchmarks1406
235
GLM 5z-ai/glm-5
Z.ai49.5$1.00 / $3.204 of 6 benchmarks16.4%2.1%80.0%1443
236
DeepSeek V3.2deepseek/deepseek-v3.2
DeepSeek49.5$0.26 / $0.383 of 6 benchmarks22.1%2.1%1426
237
Gemini 2.5 Progoogle/gemini-2.5-pro
Google49.5$1.25 / $10.006 of 6 benchmarks14.1%24.6%0.0%84.7%95.6%1439
238
Qwen3.7 Plus (none)qwen/qwen3.7-plus:none
Qwen49.4$0.32 / $1.282 of 6 benchmarks34.4%80.0%
239
GPT-5 (low)openai/gpt-5:low
OpenAI49.3$1.25 / $10.001 of 6 benchmarks37.2%
240
Qwen3.5-35B-A3B (none)qwen/qwen3.5-35b-a3b:none
Qwen49.2$0.14 / $1.001 of 6 benchmarks70.0%
241
Hunyuan T1tencent/hunyuan-t1
Tencent49.1—1 of 6 benchmarks1405
242
GPT-5 Nano (medium)openai/gpt-5-nano:medium
OpenAI49.1$0.05 / $0.404 of 6 benchmarks10.0%2.1%74.2%95.2%
243
Seed 1.6bytedance-seed/seed-1.6
ByteDance Seed49.1$0.25 / $2.001 of 6 benchmarks69.4%
244
Inkling (xhigh)thinkingmachines/inkling:xhigh
Thinking Machines49.0$1.00 / $4.053 of 6 benchmarks33.3%4.9%88.9%
245
Claude Sonnet 4 (thinking 32K)anthropic/claude-sonnet-4:thinking-32k
Anthropic49.0—1 of 6 benchmarks1404
246
Qwen3.5 397B A17B (none)qwen/qwen3.5-397b-a17b:none
Qwen49.0$0.60 / $3.602 of 6 benchmarks31.2%82.2%
247
Chatgpt 4oopenai/chatgpt-4o
OpenAI48.8—1 of 6 benchmarks1403
248
Kimi K3 (low)moonshotai/kimi-k3:low
MoonshotAI48.6$0.192 / $16.001 of 6 benchmarks68.9%
249
GPT-5.6 Sol (none)openai/gpt-5.6-sol:none
OpenAI48.6$4.00 / $20.001 of 6 benchmarks68.9%
250
Mistral Large 3mistralai/mistral-large-3
Mistral AI48.4—1 of 6 benchmarks1401
251
Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking
Qwen48.3—1 of 6 benchmarks1399
252
GPT-5.1 (low)openai/gpt-5.1:low
OpenAI48.0$1.25 / $10.002 of 6 benchmarks17.3%63.9%
253
DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus
DeepSeek47.9$0.27 / $1.001 of 6 benchmarks1396
254
Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview
Google47.9$1.25 / $10.002 of 6 benchmarks30.0%2.1%
255
Mistral Medium 2508mistralai/mistral-medium-2508
Mistral AI47.6—1 of 6 benchmarks1395
256
GPT-5.6 Luna (low)openai/gpt-5.6-luna:low
OpenAI47.5$0.20 / $1.202 of 6 benchmarks41.4%66.7%
257
Ernie 5.0 Preview 1022baidu/ernie-5.0-preview-1022
Baidu47.5—1 of 6 benchmarks1393
258
Qwen3 14Bqwen/qwen3-14b
Qwen47.5$0.12 / $0.241 of 6 benchmarks66.4%
259
Claude Haiku 4.5 (32K)anthropic/claude-haiku-4.5:32k
Anthropic47.4$1.00 / $5.004 of 6 benchmarks5.9%2.1%66.7%96.4%
260
o1 (medium)openai/o1:medium
OpenAI47.4—3 of 6 benchmarks10.2%73.3%94.4%
261
Gemini 3.1 Flash Lite (high)google/gemini-3.1-flash-lite:high
Google47.4$0.25 / $1.502 of 6 benchmarks27.7%80.0%
262
gpt-oss-20b (medium)openai/gpt-oss-20b:medium
OpenAI47.3$0.03 / $0.131 of 6 benchmarks65.3%
263
MiniMax M2.5minimax/minimax-m2.5
MiniMax47.3$0.30 / $1.201 of 6 benchmarks1392
264
Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking
Qwen47.1—1 of 6 benchmarks1391
265
Qwen3.7 Flashqwen/qwen3.7-flash
Qwen47.1$0.03 / $0.132 of 6 benchmarks19.3%86.7%
266
Qwen3 235B A22B (nothinking)qwen/qwen3-235b-a22b:nothinking
Qwen46.9—1 of 6 benchmarks1391
267
Qwen3.6 Plus (none)qwen/qwen3.6-plus:none
Qwen46.8$0.325 / $1.951 of 6 benchmarks32.3%
268
Grok 3 Mini Beta (low)x-ai/grok-3-mini-beta:low
SpaceXAI46.8—3 of 6 benchmarks2.8%62.2%90.9%
269
Grok 4 0709x-ai/grok-4-0709
SpaceXAI46.8—3 of 6 benchmarks19.7%2.1%1425
270
GPT 5.5 Instantopenai/gpt-5.5-instant
OpenAI46.7—4 of 6 benchmarks26.3%2.4%68.1%1462
271
MiniMax M2.1minimax/minimax-m2.1
MiniMax46.7—1 of 6 benchmarks1390
272
o1 (high)openai/o1:high
OpenAI46.6—4 of 6 benchmarks9.3%14.7%73.3%94.7%
273
Llama 3.3 Nemotron Super 49B v1.5nvidia/llama-3.3-nemotron-super-49b-v1.5
NVIDIA46.5—1 of 6 benchmarks1389
274
GPT-5.2 (none)openai/gpt-5.2:none
OpenAI46.4$1.75 / $14.001 of 6 benchmarks62.2%
275
Kimi K2 0711moonshotai/kimi-k2
MoonshotAI46.3$0.57 / $2.301 of 6 benchmarks1388
276
Qwen3 32Bqwen/qwen3-32b
Qwen46.2$0.08 / $0.282 of 6 benchmarks66.9%1398
277
R1 0528deepseek/deepseek-r1-0528
DeepSeek46.2$0.50 / $2.154 of 6 benchmarks0.0%66.4%96.6%1392
278
Qwen3.5-9B (none)qwen/qwen3.5-9b:none
Qwen46.2$0.17 / $0.251 of 6 benchmarks61.7%
279
GLM 4.5 Airz-ai/glm-4.5-air
Z.ai46.2$0.20 / $1.101 of 6 benchmarks1386
280
o3 Mini (medium)openai/o3-mini:medium
OpenAI46.1—4 of 6 benchmarks11.3%10.5%63.9%95.2%
281
Claude 3.7 Sonnet (thinking 32K)anthropic/claude-3-7-sonnet:thinking-32k
Anthropic46.0—1 of 6 benchmarks1386
282
Claude Opus 4 (16K)anthropic/claude-opus-4:16k
Anthropic45.9—1 of 6 benchmarks60.0%
283
Trinity Large Thinkingarcee-ai/trinity-large-thinking
Arcee AI45.9—1 of 6 benchmarks1382
284
Gemini 3.5 Flash Lite (low)google/gemini-3.5-flash-lite:low
Google45.9$0.30 / $2.501 of 6 benchmarks60.0%
285
o3 Miniopenai/o3-mini
OpenAI45.8—1 of 6 benchmarks1382
286
Claude 3.7 Sonnet (32K)anthropic/claude-3-7-sonnet:32k
Anthropic45.8—3 of 6 benchmarks3.5%53.3%90.0%
287
GPT-5 Nano (high)openai/gpt-5-nano:high
OpenAI45.8$0.05 / $0.406 of 6 benchmarks20.0%20.0%2.4%81.1%94.9%1348
288
Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b
Qwen45.7$0.10 / $0.902 of 6 benchmarks17.5%86.7%
289
Qwen3.6 27B (none)qwen/qwen3.6-27b:none
Qwen45.7$0.32 / $3.202 of 6 benchmarks34.0%66.7%
290
Llama 3.1 Nemotron Ultra 253B v1nvidia/llama-3.1-nemotron-ultra-253b-v1
NVIDIA45.6—1 of 6 benchmarks1381
291
gpt-oss-120bopenai/gpt-oss-120b
OpenAI45.5$0.15 / $0.601 of 6 benchmarks1381
292
Qwen3 Coder 480B A35b Instructqwen/qwen3-coder-480b-a35b-instruct
Qwen45.3—1 of 6 benchmarks1376
293
GPT-5.4 (none)openai/gpt-5.4:none
OpenAI45.2$2.50 / $15.001 of 6 benchmarks57.8%
294
GPT-5.5 (none)openai/gpt-5.5:none
OpenAI45.2$5.00 / $30.001 of 6 benchmarks57.8%
295
Mimo v2 Flashxiaomi/mimo-v2-flash
Xiaomi45.1—1 of 6 benchmarks1375
296
Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507
Qwen45.1$0.45 / $3.504 of 6 benchmarks20.0%0.0%86.7%1396
297
Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning-30b-a3b
NVIDIA45.0—1 of 6 benchmarks1375
298
INTELLECT-3prime-intellect/intellect-3
Prime Intellect44.8—1 of 6 benchmarks1374
299
Mimo v2 Flash (thinking)xiaomi/mimo-v2-flash:thinking
Xiaomi44.6—1 of 6 benchmarks1372
300
GLM 5.1 (none)z-ai/glm-5.1:none
Z.ai44.6$1.40 / $4.401 of 6 benchmarks24.9%
301
o3 Mini Highopenai/o3-mini-high
OpenAI44.6—6 of 6 benchmarks12.4%18.6%0.0%76.9%96.5%1405
302
Grok 3 Mini Betax-ai/grok-3-mini-beta
SpaceXAI44.4—1 of 6 benchmarks1370
303
Claude Opus 4.1anthropic/claude-opus-4.1
Anthropic44.3$15.00 / $75.003 of 6 benchmarks5.9%40.0%1433
304
o1openai/o1
OpenAI44.3—3 of 6 benchmarks31.1%81.7%1409
305
Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b
NVIDIA44.3$0.075 / $0.401 of 6 benchmarks1370
306
Claude Sonnet 4 (16K)anthropic/claude-sonnet-4:16k
Anthropic44.3—1 of 6 benchmarks53.3%
307
GPT-5.6 Terra (none)openai/gpt-5.6-terra:none
OpenAI44.3$2.00 / $12.001 of 6 benchmarks53.3%
308
GPT-5.4 Mini (low)openai/gpt-5.4-mini:low
OpenAI44.2$0.75 / $4.501 of 6 benchmarks24.6%
309
Claude 3.7 Sonnet (16K)anthropic/claude-3-7-sonnet:16k
Anthropic44.2—3 of 6 benchmarks4.1%46.7%86.3%
310
MiniMax M1minimax/minimax-m1
MiniMax44.1—1 of 6 benchmarks1370
311
GPT 4.5 Previewopenai/gpt-4.5-preview
OpenAI44.1—3 of 6 benchmarks37.8%78.6%1407
312
Gemini 3.5 Flash Lite (minimal)google/gemini-3.5-flash-lite:minimal
Google43.9$0.30 / $2.501 of 6 benchmarks51.1%
313
Qwen3.7 Flash (none)qwen/qwen3.7-flash:none
Qwen43.9$0.03 / $0.132 of 6 benchmarks19.3%77.8%
314
Gemini 2.5 Flash Lite (thinking)google/gemini-2.5-flash-lite:thinking
Google43.8$0.10 / $0.401 of 6 benchmarks1364
315
gpt-oss-20b (high)openai/gpt-oss-20b:high
OpenAI43.8$0.03 / $0.131 of 6 benchmarks50.8%
316
Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b
Qwen43.6$0.14 / $1.002 of 6 benchmarks54.4%1397
317
Qwen3.6 Flash (none)qwen/qwen3.6-flash:none
Qwen43.4$0.1875 / $1.1251 of 6 benchmarks22.5%
318
Trinity Large Previewarcee-ai/trinity-large-preview
Arcee AI43.4—1 of 6 benchmarks1362
319
Qwen 2.5 (max)qwen/qwen-2.5:max
Qwen43.3—1 of 6 benchmarks1362
320
O1 Miniopenai/o1-mini
OpenAI43.1—1 of 6 benchmarks1361
321
Kimi K2 Thinkingmoonshotai/kimi-k2-thinking
MoonshotAI43.1$0.60 / $2.502 of 6 benchmarks21.4%0.0%
322
O1 Mini (high)openai/o1-mini:high
OpenAI43.1—3 of 6 benchmarks1.4%46.9%89.2%
323
Claude Haiku 4.5anthropic/claude-haiku-4.5
Anthropic43.0$1.00 / $5.004 of 6 benchmarks4.1%35.8%86.9%1402
324
Gemini 2.5 Flash Lite (nothinking)google/gemini-2.5-flash-lite:nothinking
Google43.0$0.10 / $0.401 of 6 benchmarks1361
325
DeepSeek V4 Pro 0423 (none)deepseek/deepseek-v4-pro:none
DeepSeek43.0$0.8837 / $1.76751 of 6 benchmarks46.7%
326
Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507
Qwen43.0$0.10 / $0.302 of 6 benchmarks62.2%1378
327
Claude Opus 4.1 (27K)anthropic/claude-opus-4.1:27k
Anthropic42.9$15.00 / $75.003 of 6 benchmarks7.2%4.2%68.9%
328
GLM 4.5Vz-ai/glm-4.5v
Z.ai42.9$0.60 / $1.801 of 6 benchmarks1360
329
Step 3stepfun/step-3
StepFun42.8—1 of 6 benchmarks1360
330
o4 Mini (medium)openai/o4-mini:medium
OpenAI42.8—4 of 6 benchmarks19.0%28.8%2.1%73.3%
331
Gemini 2.5 Flashgoogle/gemini-2.5-flash
Google42.8$0.30 / $2.504 of 6 benchmarks4.8%4.2%70.8%1405
332
GPT-5.6 Luna (none)openai/gpt-5.6-luna:none
OpenAI42.7$0.20 / $1.202 of 6 benchmarks39.6%40.0%
333
Grok 3 Mini Beta (high)x-ai/grok-3-mini-beta:high
SpaceXAI42.7—5 of 6 benchmarks5.9%0.0%77.8%88.1%1389
334
MiniMax M2minimax/minimax-m2
MiniMax42.5—1 of 6 benchmarks1354
335
GPT-5.4 Nano (low)openai/gpt-5.4-nano:low
OpenAI42.5$0.20 / $1.252 of 6 benchmarks20.4%68.9%
336
Qwen3.6 35B A3B (none)qwen/qwen3.6-35b-a3b:none
Qwen42.5$0.10 / $0.902 of 6 benchmarks20.4%68.9%
337
Qwen3.5-9Bqwen/qwen3.5-9b
Qwen42.1$0.17 / $0.251 of 6 benchmarks42.8%
338
gpt-oss-20b (low)openai/gpt-oss-20b:low
OpenAI41.9$0.03 / $0.131 of 6 benchmarks40.3%
339
Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b
NVIDIA41.8$0.06 / $0.241 of 6 benchmarks1347
340
GLM 5.2 (none)z-ai/glm-5.2:none
Z.ai41.7$0.006 / $6.802 of 6 benchmarks42.5%28.9%
341
Hunyuan TurboStencent/hunyuan-turbos
Tencent41.7—1 of 6 benchmarks1344
342
GLM 4.7z-ai/glm-4.7
Z.ai41.6$0.60 / $2.204 of 6 benchmarks2.4%0.0%83.3%1427
343
Ling Flash 2.0inclusionai/ling-flash-2.0
inclusionAI41.5—1 of 6 benchmarks1344
344
GLM 4.6z-ai/glm-4.6
Z.ai41.4$0.50 / $2.003 of 6 benchmarks3.8%2.1%1418
345
Ring Flash 2.0inclusionai/ring-flash-2.0
inclusionAI41.2—1 of 6 benchmarks1338
346
QwQ 32Bqwen/qwq-32b
Qwen41.1—2 of 6 benchmarks59.2%1363
347
gpt-oss-20bopenai/gpt-oss-20b
OpenAI41.0$0.03 / $0.131 of 6 benchmarks1335
348
Nova 2 Liteamazon/nova-2-lite-v1
Amazon40.9$0.30 / $2.501 of 6 benchmarks1329
349
GLM 4.7 Flashz-ai/glm-4.7-flash
Z.ai40.9$0.0605 / $0.402 of 6 benchmarks58.3%1362
350
O1 Mini (medium)openai/o1-mini:medium
OpenAI40.8—3 of 6 benchmarks1.7%44.7%84.3%
351
Gemini 2.0 Flash Lite Preview 02 05google/gemini-2.0-flash-lite-preview-02-05
Google40.8—1 of 6 benchmarks1327
352
Qwen3 30B A3Bqwen/qwen3-30b-a3b
Qwen40.7$0.12 / $0.502 of 6 benchmarks62.8%1351
353
Claude Opus 4 (27K)anthropic/claude-opus-4:27k
Anthropic40.4—3 of 6 benchmarks4.1%4.2%64.4%
354
Granite 4.1 8Bibm-granite/granite-4.1-8b
IBM40.3—1 of 6 benchmarks1318
355
GPT-5 Mini (low)openai/gpt-5-mini:low
OpenAI40.3$0.25 / $2.001 of 6 benchmarks18.3%
356
Qwen3.5-Flash (none)qwen/qwen3.5-flash-02-23:none
Qwen40.3$0.065 / $0.261 of 6 benchmarks18.3%
357
Qwen3.6 Flashqwen/qwen3.6-flash
Qwen40.2$0.1875 / $1.1254 of 6 benchmarks20.0%17.2%0.0%84.4%
358
Claude 3.7 Sonnet (64K)anthropic/claude-3-7-sonnet:64k
Anthropic40.1—4 of 6 benchmarks3.1%0.0%57.8%91.2%
359
OLMo 3 32B Thinkallenai/olmo-3-32b-think
Allen Institute for AI39.9—1 of 6 benchmarks1311
360
o3 (low)openai/o3:low
OpenAI39.8$2.00 / $8.003 of 6 benchmarks9.7%19.3%60.0%
361
Command A (03-2025)cohere/command-a-03-2025
Cohere39.8—1 of 6 benchmarks1310
362
Claude Sonnet 4.5anthropic/claude-sonnet-4.5
Anthropic39.7$3.00 / $15.004 of 6 benchmarks9.3%2.1%35.6%1427
363
MiniMax M3 (none)minimax/minimax-m3:none
MiniMax39.4$0.30 / $1.201 of 6 benchmarks26.7%
364
Qwen3 14B (none)qwen/qwen3-14b:none
Qwen39.2$0.12 / $0.241 of 6 benchmarks25.8%
365
Qwen3 30B A3B (none)qwen/qwen3-30b-a3b:none
Qwen39.1$0.12 / $0.501 of 6 benchmarks25.6%
366
OLMo 3.1 32B Thinkallenai/olmo-3.1-32b-think
Allen Institute for AI39.0—1 of 6 benchmarks1302
367
GLM 4.7 Flash (none)z-ai/glm-4.7-flash:none
Z.ai39.0$0.0605 / $0.401 of 6 benchmarks25.0%
368
OLMo 3.1 32B Instructallenai/olmo-3.1-32b-instruct
Allen Institute for AI38.8—1 of 6 benchmarks1298
369
Qwen3 32B (none)qwen/qwen3-32b:none
Qwen38.8$0.08 / $0.281 of 6 benchmarks23.1%
370
o4 Mini (low)openai/o4-mini:low
OpenAI38.5—3 of 6 benchmarks10.7%16.1%57.8%
371
Claude Opus 4anthropic/claude-opus-4
Anthropic38.5—5 of 6 benchmarks4.5%0.0%42.2%85.0%1403
372
Gemini 3.1 Flash Lite (low)google/gemini-3.1-flash-lite:low
Google38.4$0.25 / $1.502 of 6 benchmarks22.5%44.4%
373
Step 1o Turbo 202506stepfun/step-1o-turbo-202506
StepFun38.3—1 of 6 benchmarks1295
374
Claude Sonnet 4 (59K)anthropic/claude-sonnet-4:59k
Anthropic38.3—2 of 6 benchmarks0.0%68.9%
375
GPT-4.1 Miniopenai/gpt-4.1-mini
OpenAI38.0$0.40 / $1.605 of 6 benchmarks10.0%6.7%44.7%87.3%1353
376
Grok 3 Betax-ai/grok-3-beta
SpaceXAI38.0—5 of 6 benchmarks3.8%0.0%55.6%88.8%1371
377
Magistral Medium 2506mistralai/magistral-medium-2506
Mistral AI37.8—1 of 6 benchmarks1287
378
Qwen3.5-Flashqwen/qwen3.5-flash-02-23
Qwen37.6$0.065 / $0.265 of 6 benchmarks10.0%9.5%0.0%84.4%1401
379
GPT-4openai/gpt-4
OpenAI37.5$30.00 / $60.001 of 6 benchmarks1285
380
Gemini 3.5 Flash Lite (high)google/gemini-3.5-flash-lite:high
Google37.5$0.30 / $2.503 of 6 benchmarks26.0%0.0%71.1%
381
Qwen3 235B A22Bqwen/qwen3-235b-a22b
Qwen37.4—3 of 6 benchmarks0.0%68.9%1391
382
Hunyuan Large Visiontencent/hunyuan-large-vision
Tencent37.3—1 of 6 benchmarks1280
383
Gemini 3.1 Flash Lite (minimal)google/gemini-3.1-flash-lite:minimal
Google37.2$0.25 / $1.502 of 6 benchmarks21.4%37.8%
384
Qwen2.5 Coder 32B Instructqwen/qwen2.5-coder-32b-instruct
Qwen36.8—1 of 6 benchmarks1269
385
Gemini 1.5 Pro 002google/gemini-1.5-pro-002
Google36.5—3 of 6 benchmarks23.1%70.4%1340
386
GPT-5 (minimal)openai/gpt-5:minimal
OpenAI36.5$1.25 / $10.002 of 6 benchmarks18.3%46.7%
387
Gemma 3 27Bgoogle/gemma-3-27b-it
Google36.5$0.08 / $0.453 of 6 benchmarks22.5%74.0%1323
388
Amazon Nova Pro v1.0amazon/amazon-nova-pro-v1.0
Amazon36.5—1 of 6 benchmarks1269
389
Gemini 2.0 Flash 001google/gemini-2.0-flash-001
Google36.5—4 of 6 benchmarks1.7%31.1%82.2%1356
390
Gemma 3n E4Bgoogle/gemma-3n-e4b-it
Google36.3—1 of 6 benchmarks1260
391
Claude Sonnet 4anthropic/claude-sonnet-4
Anthropic36.0—5 of 6 benchmarks4.1%0.0%28.9%84.4%1390
392
Claude Opus 4.1 (16K)anthropic/claude-opus-4.1:16k
Anthropic36.0$15.00 / $75.002 of 6 benchmarks0.0%64.4%
393
GPT-5.1 (none)openai/gpt-5.1:none
OpenAI36.0$1.25 / $10.002 of 6 benchmarks2.1%37.8%
394
Mistral Largemistralai/mistral-large
Mistral35.8$2.00 / $6.001 of 6 benchmarks1245
395
Amazon Nova Lite v1.0amazon/amazon-nova-lite-v1.0
Amazon35.7—1 of 6 benchmarks1244
396
Claude Opus 4.1 (32K)anthropic/claude-opus-4.1:32k
Anthropic35.4$15.00 / $75.002 of 6 benchmarks12.6%2.4%
397
Command R+ (08-2024)cohere/command-r-plus-08-2024
Cohere35.4$2.50 / $10.001 of 6 benchmarks1232
398
o1 (low)openai/o1:low
OpenAI35.3—2 of 6 benchmarks8.4%53.3%
399
Mistral Small 2506mistralai/mistral-small-2506
Mistral AI35.1—2 of 6 benchmarks30.3%1338
400
GPT-5 Mini (minimal)openai/gpt-5-mini:minimal
OpenAI35.1$0.25 / $2.002 of 6 benchmarks6.0%55.6%
401
OLMo 2 0325 32B Instructallenai/olmo-2-0325-32b-instruct
Allen Institute for AI35.0—1 of 6 benchmarks1227
402
Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct
Qwen34.9$0.10 / $0.201 of 6 benchmarks2.5%
403
Amazon Nova Micro v1.0amazon/amazon-nova-micro-v1.0
Amazon34.9—1 of 6 benchmarks1223
404
Claude 3.7 Sonnetanthropic/claude-3-7-sonnet
Anthropic34.8—4 of 6 benchmarks3.1%21.9%68.2%1364
405
QwQ 32B Previewqwen/qwq-32b-preview
Qwen34.8—1 of 6 benchmarks1209
406
Command R (08-2024)cohere/command-r-08-2024
Cohere34.7$0.15 / $0.601 of 6 benchmarks1208
407
Mistral Nemomistralai/mistral-nemo
Mistral34.5$0.029 / $0.031 of 6 benchmarks10.8%
408
Mistral Medium 2505mistralai/mistral-medium-2505
Mistral AI34.4—4 of 6 benchmarks0.3%32.2%81.6%1347
409
DeepSeek V3 0324deepseek/deepseek-chat-v3-0324
DeepSeek34.1$0.29 / $1.144 of 6 benchmarks0.0%37.8%75.5%1367
410
GPT-5 Nano (low)openai/gpt-5-nano:low
OpenAI33.7$0.05 / $0.402 of 6 benchmarks6.0%46.7%
411
DeepSeek V3deepseek/deepseek-chat
DeepSeek33.6$0.32 / $0.894 of 6 benchmarks1.7%48.9%64.8%1310
412
GPT-5.4 Nano (none)openai/gpt-5.4-nano:none
OpenAI33.3$0.20 / $1.252 of 6 benchmarks4.6%46.7%
413
GPT-5.4 Mini (none)openai/gpt-5.4-mini:none
OpenAI33.1$0.75 / $4.502 of 6 benchmarks17.2%26.7%
414
Gemma 3 12Bgoogle/gemma-3-12b-it
Google33.0$0.05 / $0.152 of 6 benchmarks16.7%1318
415
o3 Mini (low)openai/o3-mini:low
OpenAI32.6—2 of 6 benchmarks3.9%44.4%
416
GPT 4 1106 Previewopenai/gpt-4-1106-preview
OpenAI32.5—2 of 6 benchmarks40.0%1303
417
GPT-4.1openai/gpt-4.1
OpenAI32.4$2.00 / $8.006 of 6 benchmarks5.5%6.0%0.0%38.3%83.0%1374
418
GLM 4.5z-ai/glm-4.5
Z.ai32.3$0.60 / $2.203 of 6 benchmarks0.0%0.0%1411
419
Grok 2 1212x-ai/grok-2-1212
SpaceXAI32.2—3 of 6 benchmarks0.7%11.5%63.5%
420
Llama 4 Maverick 17B 128e Instructmeta-llama/llama-4-maverick-17b-128e-instruct
Meta31.8—4 of 6 benchmarks0.7%20.6%73.0%1317
421
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct
Qwen31.7$0.36 / $0.403 of 6 benchmarks8.1%63.2%1296
422
Qwen-Plusqwen/qwen-plus
Qwen31.6$0.26 / $0.784 of 6 benchmarks1.7%17.8%65.3%1322
423
GPT-5 Nano (minimal)openai/gpt-5-nano:minimal
OpenAI31.1$0.05 / $0.402 of 6 benchmarks1.8%35.6%
424
GPT-4.1 Nanoopenai/gpt-4.1-nano
OpenAI30.8$0.10 / $0.404 of 6 benchmarks1.0%28.9%70.0%1273
425
Magistral Small 2506mistralai/magistral-small-2506
Mistral AI30.7—2 of 6 benchmarks0.0%30.0%
426
GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13
OpenAI29.8$5.00 / $15.003 of 6 benchmarks6.3%51.0%1305
427
Qwen (max)qwen/qwen:max
Qwen29.8—4 of 6 benchmarks1.0%16.1%67.2%1291
428
Gemma 3 4Bgoogle/gemma-3-4b-it
Google28.8—2 of 6 benchmarks7.5%1254
429
Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct
Mistral28.1$2.00 / $6.002 of 6 benchmarks24.2%1228
430
Mistral Large 2407mistralai/mistral-large-2407
Mistral28.0$2.00 / $6.003 of 6 benchmarks8.5%44.8%1288
431
GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20
OpenAI28.0$2.50 / $10.003 of 6 benchmarks0.3%6.3%49.8%
432
Gemini 1.5 Pro 001google/gemini-1.5-pro-001
Google27.4—3 of 6 benchmarks6.8%40.8%1300
433
Gemini 1.5 Flash 8B 001google/gemini-1.5-flash-8b-001
Google27.3—2 of 6 benchmarks4.6%1230
434
Mistral Small 3.1 24B Instruct 2503mistralai/mistral-small-3.1-24b-instruct-2503
Mistral AI27.2—3 of 6 benchmarks3.9%46.8%1277
435
Llama 4 Scout 17B 16e Instructmeta-llama/llama-4-scout-17b-16e-instruct
Meta27.2—4 of 6 benchmarks0.0%7.8%62.3%1310
436
Claude 3 Opusanthropic/claude-3-opus
Anthropic27.0—3 of 6 benchmarks4.7%37.5%1313
437
Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct
Meta26.9$0.59 / $0.793 of 6 benchmarks5.1%41.6%1296
438
Claude 3.5 Sonnetanthropic/claude-3-5-sonnet
Anthropic26.8—5 of 6 benchmarks1.0%0.0%8.5%57.0%1352
439
Claude 2anthropic/claude-2
Anthropic26.5—2 of 6 benchmarks2.5%11.7%
440
Gemini 1.5 Flash 002google/gemini-1.5-flash-002
Google26.5—4 of 6 benchmarks0.0%16.3%61.9%1289
441
Mistral Small 24B Instruct 2501mistralai/mistral-small-24b-instruct-2501
Mistral AI26.5—3 of 6 benchmarks6.7%44.8%1261
442
Mistral Large 2411mistralai/mistral-large-2411
Mistral AI25.5—4 of 6 benchmarks0.3%7.8%50.3%1282
443
GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18
OpenAI24.5$0.15 / $0.604 of 6 benchmarks0.7%6.9%52.6%1275
444
Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct
Meta24.3—3 of 6 benchmarks3.6%36.7%1269
445
GPT-4 Turboopenai/gpt-4-turbo
OpenAI24.0—4 of 6 benchmarks0.7%6.7%46.7%1296
446
Claude 3.5 Haikuanthropic/claude-3-5-haiku
Anthropic23.9—4 of 6 benchmarks0.3%4.3%46.4%1287
447
Gemini 1.5 Flash 001google/gemini-1.5-flash-001
Google23.9—3 of 6 benchmarks3.9%25.1%1259
448
GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06
OpenAI22.9$2.50 / $10.005 of 6 benchmarks0.3%0.3%6.4%53.3%1309
449
Claude 3 Sonnetanthropic/claude-3-sonnet
Anthropic22.6—3 of 6 benchmarks2.5%18.2%1254
450
Claude 3 Haikuanthropic/claude-3-haiku
Anthropic21.9—3 of 6 benchmarks1.8%14.9%1232
451
Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct
Meta21.8$0.02 / $0.043 of 6 benchmarks1.7%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.