AGI-Eval Community Instruction-Tuned Language Models
Models answer Chinese and English questions across reasoning, knowledge, learning, interaction and instruction following.
The 2026/11 leaderboard reports 142 scored model entries on its primary measure.
- Made by
- AGI-Eval (Meituan)
- Released
- March 2025
- Kind
- Reasoning in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- Kept private
- Measures
- Capability
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- Claude Fable 5 #12 on the capability index
- Last model added
- July 2026
- Scores refreshed
- November 21st, 2026
GPT-5.5 leads with 0.86 among models released by July 2026 GPT-5.5 leads with 0.86 among models released by July 2026
Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in July 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 15 more
- 0.86 GPT-5.5
- 0.85 Claude Fable 5
- 0.84
Gemini 3.1 Pro
- 0.84 Kimi K3
- 0.83
Gemini 3.5 Flash
- 0.83
Doubao Seed 2.1 Pro
- 0.82 Claude Opus 4.8
- 0.82 GPT-5.4
- 0.82
Qwen3.7-Max
- 0.81
Seed2.0 Pro
- 0.81
DeepSeek-V4-Pro
- 0.81 Kimi K2.6
- 0.81 Claude Opus 4.6
- 0.80 Claude Sonnet 5
- 0.80 GLM-5.2
- 0.80
DeepSeek-V4-Flash
- 0.80 Claude Opus 4.5
- 0.79 GPT-5.1
- 0.79
Gemini 3 Flash
- 0.79
Gemini 3 Pro
- 0.79 GPT-5-Thinking (High)
- 0.78
Tencent Hy3
- 0.78
Qwen3.5 397B-A17B
- 0.77 o3-pro
- 0.77 GLM-5.1
- 0.77 Kimi K2.5
- 0.77 DeepSeek-V3.2-Thinking-Speciale
- 0.76
Tencent Hy3 preview
- 0.76
Qwen3-Max
- 0.75
Qwen 3.6 Plus
- 0.74 Doubao-Seed-1.8
- 0.74 o3
- 0.74 GLM-5
- 0.74 gpt-oss-120b
- 0.73 Doubao-Seed-1.6-Thinking-2507
- 0.73
Qwen3-Max-Preview
- 0.73
DeepSeek-V3.2
- 0.73
MiniMax-M3
- 0.72 Kimi K2 Thinking
- 0.72
Gemini 2.5 Pro
- 0.72 GLM-4.7
- 0.71
Qwen3-235B-A22B-Thinking
- 0.71 Grok 4
- 0.71 o4-mini
- 0.71 o3-mini
- 0.70 gpt-oss-20b
- 0.70
LongCat-2.0
- 0.70 Grok 4.1
- 0.70
ERNIE 5.0
- 0.69
DeepSeek-R1
- 0.69
DeepSeek-V3.1
- 0.69
Doubao-Seed-1.6
- 0.69 Ernie-5.0-Thinking-Preview
- 0.69
DeepSeek-V3.2-Exp
- 0.69 Claude Sonnet 4.5
- 0.69
DeepSeek-V3.1-Terminus
- 0.68 Doubao-Seed-1.6-Auto
- 0.68 Claude-Opus-4.5-no-reasoning
- 0.68 o1
- 0.68 Doubao-Seed-1.6-On
- 0.68
LongCat-Flash-Thinking-2601
- 0.67
MiniMax-M2
- 0.67 LongCat-Flash-Thinking-2509
- 0.67
Qwen3-Next-80B-A3B
- 0.67
Gemini 2.5 Flash
- 0.67 Doubao-1.5-Thinking-Pro-2504
- 0.67 Kimi-K2.5-Chat
- 0.66 Qwen3-Max-Instruct
- 0.65 Qwen3-Max-no-Thinking
- 0.65 GPT-5.2
- 0.65 GLM-4.5
- 0.65 GLM-4.6
- 0.64
Qwen3-235B-A22B
- 0.64
Ring-1T
- 0.64 Claude Opus 4
- 0.64 LongCat-Flash-2512
- 0.63
Qwen3-235B-A22B-Instruct
- 0.62 LongCat-Flash-2510
- 0.62 GPT-5.1 Instant
- 0.62 Kimi K2
- 0.62
Qwen3-32B
- 0.62
Step 3
- 0.62
Qwen3-Next-80B-A3B-Instruct
- 0.61 Doubao-Seed-1.6-Off
- 0.61 LongCat-Flash-2508
- 0.60 GPT-5
- 0.60 Claude Sonnet 4
- 0.60
Qwen3-30B-A3B-Thinking
- 0.59
QwQ-32B
- 0.59
DeepSeek-V3
- 0.59
MiniMax-M1-80k
- 0.59
Qwen3-14B
- 0.58
Hunyuan-T1
- 0.58 GPT-4.5
- 0.55 Doubao-Seed-1.6-Flash
- 0.55 Claude 3.7 Sonnet
- 0.55 GPT-4.1
- 0.55 Step-r1-v-mini
- 0.55
Qwen3-8B
- 0.55 Doubao-1.5-Pro-32k
- 0.53
ERNIE-4.5-300B-A47B
- 0.52 Grok 3
- 0.50
Llama 4 Maverick
- 0.48
Qwen3-30B-A3B
- 0.48
Qwen3-4B
- 0.48 Claude-3.5-Sonnet-1022
- 0.46 GPT-4o-1120
- 0.46 GLM4-Plus
- 0.45
Qwen2.5-72B
- 0.44 Qwen2.5-32B-Instruct
- 0.43
Gemma 3 27B
- 0.41
Llama 4 Scout
- 0.41 Llama3.1-405B-Instruct
- 0.40 Qwen2.5-14B-Instruct
- 0.38
Qwen3-1.7B
- 0.37
Gemma 3 12B
- 0.35 abab6.5
- 0.34 Qwen2.5-7B-Instruct
- 0.31 GLM-4-9B
- 0.27
Gemma 3 4B
- 0.23
Qwen3-0.6B
- 0.15
Gemma 3 1B
- 1 GPT-5.5 0.86
- 2 Claude Fable 5 0.85
- 3
Gemini 3.1 Pro 0.84
- 4 Kimi K3 0.84
- 5
Gemini 3.5 Flash 0.83
- 6
Doubao Seed 2.1 Pro 0.83
- 7 Claude Opus 4.8 0.82
- 8 GPT-5.4 0.82
- 9
Qwen3.7-Max 0.82
- 10
Seed2.0 Pro 0.81
- 11
DeepSeek-V4-Pro max 0.81
- 12 Kimi K2.6 0.81
- 13 Claude Opus 4.6 0.81
- 14 Claude Sonnet 5 0.80
- 15 GLM-5.2 0.80
- 16
DeepSeek-V4-Flash max 0.80
- 17 Claude Opus 4.5 0.80
- 18 GPT-5.1 0.79
- 19
Gemini 3 Flash 0.79
- 20
Gemini 3 Pro 0.79
- 21 GPT-5-Thinking (High) 0.79
- 22
Tencent Hy3 0.78
- 23
Qwen3.5 397B-A17B thinking 0.78
- 24 o3-pro 0.77
- 25 GLM-5.1 0.77
- 26 Kimi K2.5 thinking 0.77
- 27 DeepSeek-V3.2-Thinking-Speciale 0.77
- 28
Tencent Hy3 preview 0.76
- 29
Qwen3-Max 0.76
- 30
Qwen 3.6 Plus 0.75
- 31 Doubao-Seed-1.8 0.74
- 32 o3 0.74
- 33 GLM-5 0.74
- 34 gpt-oss-120b high 0.74
- 35 Doubao-Seed-1.6-Thinking-2507 0.73
- 36
Qwen3-Max-Preview thinking 0.73
- 37
DeepSeek-V3.2 0.73
- 38
MiniMax-M3 0.73
- 39 Kimi K2 Thinking 0.72
- 40
Gemini 2.5 Pro Jun 2025 0.72
- 41 GLM-4.7 0.72
- 42
Qwen3-235B-A22B-Thinking Jul 2025 0.71
- 43 Grok 4 0.71
- 44 o4-mini 0.71
- 45 o3-mini high 0.71
- 46 gpt-oss-20b high 0.70
- 47
LongCat-2.0 0.70
- 48 Grok 4.1 0.70
- 49
ERNIE 5.0 0.70
- 50
DeepSeek-R1 May 2025 0.69
- 51
DeepSeek-V3.1 0.69
- 52
Doubao-Seed-1.6 thinking 0.69
- 53 Ernie-5.0-Thinking-Preview 0.69
- 54
DeepSeek-V3.2-Exp thinking 0.69
- 55 Claude Sonnet 4.5 thinking 0.69
- 56
DeepSeek-V3.1-Terminus thinking 0.69
- 57 Doubao-Seed-1.6-Auto 0.68
- 58 Claude-Opus-4.5-no-reasoning 0.68
- 59 o1 0.68
- 60 Doubao-Seed-1.6-On 0.68
- 61
LongCat-Flash-Thinking-2601 0.68
- 62
MiniMax-M2 0.67
- 63 LongCat-Flash-Thinking-2509 0.67
- 64
Qwen3-Next-80B-A3B thinking 0.67
- 65
Gemini 2.5 Flash Sep 2025 0.67
- 66 Doubao-1.5-Thinking-Pro-2504 0.67
- 67 Kimi-K2.5-Chat 0.67
- 68 Qwen3-Max-Instruct 0.66
- 69 Qwen3-Max-no-Thinking 0.65
- 70 GPT-5.2 0.65
- 71 GLM-4.5 0.65
- 72 GLM-4.6 0.65
- 73
Qwen3-235B-A22B thinking 0.64
- 74
Ring-1T 0.64
- 75 Claude Opus 4 thinking 0.64
- 76 LongCat-Flash-2512 0.64
- 77
Qwen3-235B-A22B-Instruct Jul 2025 0.63
- 78 LongCat-Flash-2510 0.62
- 79 GPT-5.1 Instant 0.62
- 80 Kimi K2 Jul 2025 0.62
- 81
Qwen3-32B thinking 0.62
- 82
Step 3 0.62
- 83
Qwen3-Next-80B-A3B-Instruct 0.62
- 84 Doubao-Seed-1.6-Off 0.61
- 85 LongCat-Flash-2508 0.61
- 86 GPT-5 0.60
- 87 Claude Sonnet 4 thinking 0.60
- 88
Qwen3-30B-A3B-Thinking Jul 2025 0.60
- 89
QwQ-32B 0.59
- 90
DeepSeek-V3 Mar 2025 0.59
- 91
MiniMax-M1-80k 0.59
- 92
Qwen3-14B thinking 0.59
- 93
Hunyuan-T1 0.58
- 94 GPT-4.5 0.58
- 95 Doubao-Seed-1.6-Flash 0.55
- 96 Claude 3.7 Sonnet thinking 0.55
- 97 GPT-4.1 0.55
- 98 Step-r1-v-mini 0.55
- 99
Qwen3-8B thinking 0.55
- 100 Doubao-1.5-Pro-32k 0.55
- 101
ERNIE-4.5-300B-A47B 0.53
- 102 Grok 3 0.52
- 103
Llama 4 Maverick 0.50
- 104
Qwen3-30B-A3B 0.48
- 105
Qwen3-4B thinking 0.48
- 106 Claude-3.5-Sonnet-1022 0.48
- 107 GPT-4o-1120 0.46
- 108 GLM4-Plus 0.46
- 109
Qwen2.5-72B 0.45
- 110 Qwen2.5-32B-Instruct 0.44
- 111
Gemma 3 27B 0.43
- 112
Llama 4 Scout 0.41
- 113 Llama3.1-405B-Instruct 0.41
- 114 Qwen2.5-14B-Instruct 0.40
- 115
Qwen3-1.7B thinking 0.38
- 116
Gemma 3 12B 0.37
- 117 abab6.5 0.35
- 118 Qwen2.5-7B-Instruct 0.34
- 119 GLM-4-9B 0.31
- 120
Gemma 3 4B 0.27
- 121
Qwen3-0.6B thinking 0.23
- 122
Gemma 3 1B 0.15
Source: Official AGI-Eval Community Instruction-Tuned Language Models leaderboard
- 0.86 GPT-5.5
- 0.85 Claude Fable 5
- 0.84
Gemini 3.1 Pro
- 0.84 Kimi K3
- 0.83
Gemini 3.5 Flash
- 0.83
Doubao Seed 2.1 Pro
- 0.82 Claude Opus 4.8
- 0.82 GPT-5.4
- 0.82
Qwen3.7-Max
- 0.81
Seed2.0 Pro
- 0.81
DeepSeek-V4-Pro
- 0.81 Kimi K2.6
- 0.81 Claude Opus 4.6
- 0.80 Claude Sonnet 5
- 0.80 GLM-5.2
- 0.80
DeepSeek-V4-Flash
- 0.80 Claude Opus 4.5
- 0.79 GPT-5.1
- 0.79
Gemini 3 Flash
- 0.79
Gemini 3 Pro
- 0.78
Tencent Hy3
- 0.78
Qwen3.5 397B-A17B
- 0.77 o3-pro
- 0.77 GLM-5.1
- 0.77 Kimi K2.5
- 0.76
Tencent Hy3 preview
- 0.76
Qwen3-Max
- 0.75
Qwen 3.6 Plus
- 0.74 o3
- 0.74 GLM-5
- 0.74 gpt-oss-120b
- 0.73
Qwen3-Max-Preview
- 0.73
DeepSeek-V3.2
- 0.73
MiniMax-M3
- 0.72 Kimi K2 Thinking
- 0.72
Gemini 2.5 Pro
- 0.72 GLM-4.7
- 0.71
Qwen3-235B-A22B-Thinking
- 0.71 Grok 4
- 0.71 o4-mini
- 0.71 o3-mini
- 0.70 gpt-oss-20b
- 0.70
LongCat-2.0
- 0.70 Grok 4.1
- 0.70
ERNIE 5.0
- 0.69
DeepSeek-R1
- 0.69
DeepSeek-V3.1
- 0.69
Doubao-Seed-1.6
- 0.69
DeepSeek-V3.2-Exp
- 0.69 Claude Sonnet 4.5
- 0.69
DeepSeek-V3.1-Terminus
- 0.68 o1
- 0.68
LongCat-Flash-Thinking-2601
- 0.67
MiniMax-M2
- 0.67
Qwen3-Next-80B-A3B
- 0.67
Gemini 2.5 Flash
- 0.65 GPT-5.2
- 0.65 GLM-4.5
- 0.65 GLM-4.6
- 0.64
Qwen3-235B-A22B
- 0.64
Ring-1T
- 0.64 Claude Opus 4
- 0.63
Qwen3-235B-A22B-Instruct
- 0.62 GPT-5.1 Instant
- 0.62 Kimi K2
- 0.62
Qwen3-32B
- 0.62
Step 3
- 0.62
Qwen3-Next-80B-A3B-Instruct
- 0.60 GPT-5
- 0.60 Claude Sonnet 4
- 0.60
Qwen3-30B-A3B-Thinking
- 0.59
QwQ-32B
- 0.59
DeepSeek-V3
- 0.59
MiniMax-M1-80k
- 0.59
Qwen3-14B
- 0.58
Hunyuan-T1
- 0.58 GPT-4.5
- 0.55 Claude 3.7 Sonnet
- 0.55 GPT-4.1
- 0.55
Qwen3-8B
- 0.53
ERNIE-4.5-300B-A47B
- 0.52 Grok 3
- 0.50
Llama 4 Maverick
- 0.48
Qwen3-30B-A3B
- 0.48
Qwen3-4B
- 0.45
Qwen2.5-72B
- 0.43
Gemma 3 27B
- 0.41
Llama 4 Scout
- 0.38
Qwen3-1.7B
- 0.37
Gemma 3 12B
- 0.31 GLM-4-9B
- 0.27
Gemma 3 4B
- 0.23
Qwen3-0.6B
- 0.15
Gemma 3 1B
- 1 GPT-5.5 0.86
- 2 Claude Fable 5 0.85
- 3
Gemini 3.1 Pro 0.84
- 4 Kimi K3 0.84
- 5
Gemini 3.5 Flash 0.83
- 6
Doubao Seed 2.1 Pro 0.83
- 7 Claude Opus 4.8 0.82
- 8 GPT-5.4 0.82
- 9
Qwen3.7-Max 0.82
- 10
Seed2.0 Pro 0.81
- 11
DeepSeek-V4-Pro max 0.81
- 12 Kimi K2.6 0.81
- 13 Claude Opus 4.6 0.81
- 14 Claude Sonnet 5 0.80
- 15 GLM-5.2 0.80
- 16
DeepSeek-V4-Flash max 0.80
- 17 Claude Opus 4.5 0.80
- 18 GPT-5.1 0.79
- 19
Gemini 3 Flash 0.79
- 20
Gemini 3 Pro 0.79
- 21
Tencent Hy3 0.78
- 22
Qwen3.5 397B-A17B thinking 0.78
- 23 o3-pro 0.77
- 24 GLM-5.1 0.77
- 25 Kimi K2.5 thinking 0.77
- 26
Tencent Hy3 preview 0.76
- 27
Qwen3-Max 0.76
- 28
Qwen 3.6 Plus 0.75
- 29 o3 0.74
- 30 GLM-5 0.74
- 31 gpt-oss-120b high 0.74
- 32
Qwen3-Max-Preview thinking 0.73
- 33
DeepSeek-V3.2 0.73
- 34
MiniMax-M3 0.73
- 35 Kimi K2 Thinking 0.72
- 36
Gemini 2.5 Pro Jun 2025 0.72
- 37 GLM-4.7 0.72
- 38
Qwen3-235B-A22B-Thinking Jul 2025 0.71
- 39 Grok 4 0.71
- 40 o4-mini 0.71
- 41 o3-mini high 0.71
- 42 gpt-oss-20b high 0.70
- 43
LongCat-2.0 0.70
- 44 Grok 4.1 0.70
- 45
ERNIE 5.0 0.70
- 46
DeepSeek-R1 May 2025 0.69
- 47
DeepSeek-V3.1 0.69
- 48
Doubao-Seed-1.6 thinking 0.69
- 49
DeepSeek-V3.2-Exp thinking 0.69
- 50 Claude Sonnet 4.5 thinking 0.69
- 51
DeepSeek-V3.1-Terminus thinking 0.69
- 52 o1 0.68
- 53
LongCat-Flash-Thinking-2601 0.68
- 54
MiniMax-M2 0.67
- 55
Qwen3-Next-80B-A3B thinking 0.67
- 56
Gemini 2.5 Flash Sep 2025 0.67
- 57 GPT-5.2 0.65
- 58 GLM-4.5 0.65
- 59 GLM-4.6 0.65
- 60
Qwen3-235B-A22B thinking 0.64
- 61
Ring-1T 0.64
- 62 Claude Opus 4 thinking 0.64
- 63
Qwen3-235B-A22B-Instruct Jul 2025 0.63
- 64 GPT-5.1 Instant 0.62
- 65 Kimi K2 Jul 2025 0.62
- 66
Qwen3-32B thinking 0.62
- 67
Step 3 0.62
- 68
Qwen3-Next-80B-A3B-Instruct 0.62
- 69 GPT-5 0.60
- 70 Claude Sonnet 4 thinking 0.60
- 71
Qwen3-30B-A3B-Thinking Jul 2025 0.60
- 72
QwQ-32B 0.59
- 73
DeepSeek-V3 Mar 2025 0.59
- 74
MiniMax-M1-80k 0.59
- 75
Qwen3-14B thinking 0.59
- 76
Hunyuan-T1 0.58
- 77 GPT-4.5 0.58
- 78 Claude 3.7 Sonnet thinking 0.55
- 79 GPT-4.1 0.55
- 80
Qwen3-8B thinking 0.55
- 81
ERNIE-4.5-300B-A47B 0.53
- 82 Grok 3 0.52
- 83
Llama 4 Maverick 0.50
- 84
Qwen3-30B-A3B 0.48
- 85
Qwen3-4B thinking 0.48
- 86
Qwen2.5-72B 0.45
- 87
Gemma 3 27B 0.43
- 88
Llama 4 Scout 0.41
- 89
Qwen3-1.7B thinking 0.38
- 90
Gemma 3 12B 0.37
- 91 GLM-4-9B 0.31
- 92
Gemma 3 4B 0.27
- 93
Qwen3-0.6B thinking 0.23
- 94
Gemma 3 1B 0.15
Source: Official AGI-Eval Community Instruction-Tuned Language Models leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-5.5 | 0.86 | Apr 2026 | May 2026 | Official leaderboard | |
| 2 | Claude Fable 5 | 0.85 | Jun 2026 | Jul 2026 | Official leaderboard | |
| 3 | | 0.84 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 4 | Kimi K3 | 0.84 | Jul 2026 | Jul 2026 | Official leaderboard | |
| 5 | | 0.83 | May 2026 | May 2026 | Official leaderboard | |
| 6 | | 0.83 | Jun 2026 | Jul 2026 | Official leaderboard | |
| 7 | Claude Opus 4.8 | 0.82 | May 2026 | Jun 2026 | Official leaderboard | |
| 8 | GPT-5.4 | 0.82 | Mar 2026 | Apr 2026 | Official leaderboard | |
| 9 | | 0.82 | May 2026 | May 2026 | Official leaderboard | |
| 10 | | 0.81 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 11 | | 0.81 | max | Apr 2026 | May 2026 | Official leaderboard |
| 12 | Kimi K2.6 | 0.81 | Apr 2026 | May 2026 | Official leaderboard | |
| 13 | Claude Opus 4.6 | 0.81 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 14 | Claude Sonnet 5 | 0.80 | Jun 2026 | Jul 2026 | Official leaderboard | |
| 15 | GLM-5.2 | 0.80 | Jun 2026 | Jul 2026 | Official leaderboard | |
| 16 | | 0.80 | max | Apr 2026 | May 2026 | Official leaderboard |
| 17 | Claude Opus 4.5 | 0.80 | Nov 2025 | Feb 2026 | Official leaderboard | |
| 18 | GPT-5.1 | 0.79 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 19 | | 0.79 | Dec 2025 | Dec 2025 | Official leaderboard | |
| 20 | | 0.79 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 21 | GPT-5-Thinking (High) | 0.79 | Feb 2026 | Official leaderboard | ||
| 22 | | 0.78 | Jul 2026 | Jul 2026 | Official leaderboard | |
| 23 | | 0.78 | thinking | Feb 2026 | Mar 2026 | Official leaderboard |
| 24 | o3-pro | 0.77 | Jun 2025 | Feb 2026 | Official leaderboard | |
| 25 | GLM-5.1 | 0.77 | Apr 2026 | Jun 2026 | Official leaderboard | |
| 26 | Kimi K2.5 | 0.77 | thinking | Jan 2026 | Feb 2026 | Official leaderboard |
| 27 | DeepSeek-V3.2-Thinking-Speciale | 0.77 | Mar 2026 | Official leaderboard | ||
| 28 | | 0.76 | Apr 2026 | May 2026 | Official leaderboard | |
| 29 | | 0.76 | Sep 2025 | Feb 2026 | Official leaderboard | |
| 30 | | 0.75 | Mar 2026 | Jun 2026 | Official leaderboard | |
| 31 | Doubao-Seed-1.8 | 0.74 | Jan 2026 | Official leaderboard | ||
| 32 | o3 | 0.74 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 33 | GLM-5 | 0.74 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 34 | gpt-oss-120b | 0.74 | high | Aug 2025 | Mar 2026 | Official leaderboard |
| 35 | Doubao-Seed-1.6-Thinking-2507 | 0.73 | Mar 2026 | Official leaderboard | ||
| 36 | | 0.73 | thinking | Sep 2025 | Nov 2025 | Official leaderboard |
| 37 | | 0.73 | Dec 2025 | Dec 2025 | Official leaderboard | |
| 38 | | 0.73 | Jun 2026 | Jun 2026 | Official leaderboard | |
| 39 | Kimi K2 Thinking | 0.72 | Nov 2025 | Nov 2025 | Official leaderboard | |
| 40 | | 0.72 | Jun 2025 | Mar 2026 | Official leaderboard | |
| 41 | GLM-4.7 | 0.72 | Dec 2025 | Dec 2025 | Official leaderboard | |
| 42 | | 0.71 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 43 | Grok 4 | 0.71 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 44 | o4-mini | 0.71 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 45 | o3-mini | 0.71 | high | Jan 2025 | Mar 2026 | Official leaderboard |
| 46 | gpt-oss-20b | 0.70 | high | Aug 2025 | Mar 2026 | Official leaderboard |
| 47 | | 0.70 | Jul 2026 | Jul 2026 | Official leaderboard | |
| 48 | Grok 4.1 | 0.70 | Nov 2025 | Mar 2026 | Official leaderboard | |
| 49 | | 0.70 | Jan 2026 | Feb 2026 | Official leaderboard | |
| 50 | | 0.69 | May 2025 | Mar 2026 | Official leaderboard | |
| 51 | | 0.69 | Aug 2025 | Mar 2026 | Official leaderboard | |
| 52 | | 0.69 | thinking | Jun 2025 | Mar 2026 | Official leaderboard |
| 53 | Ernie-5.0-Thinking-Preview | 0.69 | Jan 2026 | Official leaderboard | ||
| 54 | | 0.69 | thinking | Sep 2025 | Mar 2026 | Official leaderboard |
| 55 | Claude Sonnet 4.5 | 0.69 | thinking | Sep 2025 | Mar 2026 | Official leaderboard |
| 56 | | 0.69 | thinking | Sep 2025 | Mar 2026 | Official leaderboard |
| 57 | Doubao-Seed-1.6-Auto | 0.68 | Mar 2026 | Official leaderboard | ||
| 58 | Claude-Opus-4.5-no-reasoning | 0.68 | Feb 2026 | Official leaderboard | ||
| 59 | o1 | 0.68 | Dec 2024 | Mar 2026 | Official leaderboard | |
| 60 | Doubao-Seed-1.6-On | 0.68 | Mar 2026 | Official leaderboard | ||
| 61 | | 0.68 | Jan 2026 | Feb 2026 | Official leaderboard | |
| 62 | | 0.67 | Oct 2025 | Nov 2025 | Official leaderboard | |
| 63 | LongCat-Flash-Thinking-2509 | 0.67 | Sep 2025 | Official leaderboard | ||
| 64 | | 0.67 | thinking | Sep 2025 | Mar 2026 | Official leaderboard |
| 65 | | 0.67 | Sep 2025 | Mar 2026 | Official leaderboard | |
| 66 | Doubao-1.5-Thinking-Pro-2504 | 0.67 | Jan 2026 | Official leaderboard | ||
| 67 | Kimi-K2.5-Chat | 0.67 | Feb 2026 | Official leaderboard | ||
| 68 | Qwen3-Max-Instruct | 0.66 | Dec 2025 | Official leaderboard | ||
| 69 | Qwen3-Max-no-Thinking | 0.65 | Feb 2026 | Official leaderboard | ||
| 70 | GPT-5.2 | 0.65 | Dec 2025 | Mar 2026 | Official leaderboard | |
| 71 | GLM-4.5 | 0.65 | Aug 2025 | Mar 2026 | Official leaderboard | |
| 72 | GLM-4.6 | 0.65 | Sep 2025 | Mar 2026 | Official leaderboard | |
| 73 | | 0.64 | thinking | Apr 2025 | Mar 2026 | Official leaderboard |
| 74 | | 0.64 | Oct 2025 | Mar 2026 | Official leaderboard | |
| 75 | Claude Opus 4 | 0.64 | thinking | May 2025 | Mar 2026 | Official leaderboard |
| 76 | LongCat-Flash-2512 | 0.64 | Dec 2025 | Official leaderboard | ||
| 77 | | 0.63 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 78 | LongCat-Flash-2510 | 0.62 | Mar 2026 | Official leaderboard | ||
| 79 | GPT-5.1 Instant | 0.62 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 80 | Kimi K2 Jul 2025 | 0.62 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 81 | | 0.62 | thinking | Apr 2025 | Mar 2026 | Official leaderboard |
| 82 | | 0.62 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 83 | | 0.62 | Sep 2025 | Jan 2026 | Official leaderboard | |
| 84 | Doubao-Seed-1.6-Off | 0.61 | Feb 2026 | Official leaderboard | ||
| 85 | LongCat-Flash-2508 | 0.61 | Sep 2025 | Official leaderboard | ||
| 86 | GPT-5 | 0.60 | Aug 2025 | Mar 2026 | Official leaderboard | |
| 87 | Claude Sonnet 4 | 0.60 | thinking | May 2025 | Feb 2026 | Official leaderboard |
| 88 | | 0.60 | Jul 2025 | Feb 2026 | Official leaderboard | |
| 89 | | 0.59 | Mar 2025 | Feb 2026 | Official leaderboard | |
| 90 | | 0.59 | Mar 2025 | Feb 2026 | Official leaderboard | |
| 91 | | 0.59 | Jun 2025 | Sep 2025 | Official leaderboard | |
| 92 | | 0.59 | thinking | Apr 2025 | Mar 2026 | Official leaderboard |
| 93 | | 0.58 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 94 | GPT-4.5 | 0.58 | Feb 2025 | Jan 2026 | Official leaderboard | |
| 95 | Doubao-Seed-1.6-Flash | 0.55 | Feb 2026 | Official leaderboard | ||
| 96 | Claude 3.7 Sonnet | 0.55 | thinking | Feb 2025 | Feb 2026 | Official leaderboard |
| 97 | GPT-4.1 | 0.55 | Apr 2025 | Feb 2026 | Official leaderboard | |
| 98 | Step-r1-v-mini | 0.55 | Sep 2025 | Official leaderboard | ||
| 99 | | 0.55 | thinking | Apr 2025 | Feb 2026 | Official leaderboard |
| 100 | Doubao-1.5-Pro-32k | 0.55 | Mar 2026 | Official leaderboard | ||
| 101 | | 0.53 | Jun 2025 | Mar 2026 | Official leaderboard | |
| 102 | Grok 3 | 0.52 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 103 | | 0.50 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 104 | | 0.48 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 105 | | 0.48 | thinking | Apr 2025 | Jan 2026 | Official leaderboard |
| 106 | Claude-3.5-Sonnet-1022 | 0.48 | Mar 2026 | Official leaderboard | ||
| 107 | GPT-4o-1120 | 0.46 | Mar 2026 | Official leaderboard | ||
| 108 | GLM4-Plus | 0.46 | Mar 2026 | Official leaderboard | ||
| 109 | | 0.45 | Sep 2024 | Mar 2026 | Official leaderboard | |
| 110 | Qwen2.5-32B-Instruct | 0.44 | Mar 2026 | Official leaderboard | ||
| 111 | | 0.43 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 112 | | 0.41 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 113 | Llama3.1-405B-Instruct | 0.41 | Mar 2026 | Official leaderboard | ||
| 114 | Qwen2.5-14B-Instruct | 0.40 | Mar 2026 | Official leaderboard | ||
| 115 | | 0.38 | thinking | Apr 2025 | Feb 2026 | Official leaderboard |
| 116 | | 0.37 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 117 | abab6.5 | 0.35 | Jun 2026 | Official leaderboard | ||
| 118 | Qwen2.5-7B-Instruct | 0.34 | Mar 2026 | Official leaderboard | ||
| 119 | GLM-4-9B | 0.31 | Jun 2024 | Mar 2026 | Official leaderboard | |
| 120 | | 0.27 | Mar 2025 | Feb 2026 | Official leaderboard | |
| 121 | | 0.23 | thinking | Apr 2025 | Mar 2026 | Official leaderboard |
| 122 | | 0.15 | Mar 2025 | Mar 2026 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-5.5 | 0.86 | Apr 2026 | May 2026 | Official leaderboard | |
| 2 | Claude Fable 5 | 0.85 | Jun 2026 | Jul 2026 | Official leaderboard | |
| 3 | | 0.84 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 4 | Kimi K3 | 0.84 | Jul 2026 | Jul 2026 | Official leaderboard | |
| 5 | | 0.83 | May 2026 | May 2026 | Official leaderboard | |
| 6 | | 0.83 | Jun 2026 | Jul 2026 | Official leaderboard | |
| 7 | Claude Opus 4.8 | 0.82 | May 2026 | Jun 2026 | Official leaderboard | |
| 8 | GPT-5.4 | 0.82 | Mar 2026 | Apr 2026 | Official leaderboard | |
| 9 | | 0.82 | May 2026 | May 2026 | Official leaderboard | |
| 10 | | 0.81 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 11 | | 0.81 | max | Apr 2026 | May 2026 | Official leaderboard |
| 12 | Kimi K2.6 | 0.81 | Apr 2026 | May 2026 | Official leaderboard | |
| 13 | Claude Opus 4.6 | 0.81 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 14 | Claude Sonnet 5 | 0.80 | Jun 2026 | Jul 2026 | Official leaderboard | |
| 15 | GLM-5.2 | 0.80 | Jun 2026 | Jul 2026 | Official leaderboard | |
| 16 | | 0.80 | max | Apr 2026 | May 2026 | Official leaderboard |
| 17 | Claude Opus 4.5 | 0.80 | Nov 2025 | Feb 2026 | Official leaderboard | |
| 18 | GPT-5.1 | 0.79 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 19 | | 0.79 | Dec 2025 | Dec 2025 | Official leaderboard | |
| 20 | | 0.79 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 21 | | 0.78 | Jul 2026 | Jul 2026 | Official leaderboard | |
| 22 | | 0.78 | thinking | Feb 2026 | Mar 2026 | Official leaderboard |
| 23 | o3-pro | 0.77 | Jun 2025 | Feb 2026 | Official leaderboard | |
| 24 | GLM-5.1 | 0.77 | Apr 2026 | Jun 2026 | Official leaderboard | |
| 25 | Kimi K2.5 | 0.77 | thinking | Jan 2026 | Feb 2026 | Official leaderboard |
| 26 | | 0.76 | Apr 2026 | May 2026 | Official leaderboard | |
| 27 | | 0.76 | Sep 2025 | Feb 2026 | Official leaderboard | |
| 28 | | 0.75 | Mar 2026 | Jun 2026 | Official leaderboard | |
| 29 | o3 | 0.74 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 30 | GLM-5 | 0.74 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 31 | gpt-oss-120b | 0.74 | high | Aug 2025 | Mar 2026 | Official leaderboard |
| 32 | | 0.73 | thinking | Sep 2025 | Nov 2025 | Official leaderboard |
| 33 | | 0.73 | Dec 2025 | Dec 2025 | Official leaderboard | |
| 34 | | 0.73 | Jun 2026 | Jun 2026 | Official leaderboard | |
| 35 | Kimi K2 Thinking | 0.72 | Nov 2025 | Nov 2025 | Official leaderboard | |
| 36 | | 0.72 | Jun 2025 | Mar 2026 | Official leaderboard | |
| 37 | GLM-4.7 | 0.72 | Dec 2025 | Dec 2025 | Official leaderboard | |
| 38 | | 0.71 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 39 | Grok 4 | 0.71 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 40 | o4-mini | 0.71 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 41 | o3-mini | 0.71 | high | Jan 2025 | Mar 2026 | Official leaderboard |
| 42 | gpt-oss-20b | 0.70 | high | Aug 2025 | Mar 2026 | Official leaderboard |
| 43 | | 0.70 | Jul 2026 | Jul 2026 | Official leaderboard | |
| 44 | Grok 4.1 | 0.70 | Nov 2025 | Mar 2026 | Official leaderboard | |
| 45 | | 0.70 | Jan 2026 | Feb 2026 | Official leaderboard | |
| 46 | | 0.69 | May 2025 | Mar 2026 | Official leaderboard | |
| 47 | | 0.69 | Aug 2025 | Mar 2026 | Official leaderboard | |
| 48 | | 0.69 | thinking | Jun 2025 | Mar 2026 | Official leaderboard |
| 49 | | 0.69 | thinking | Sep 2025 | Mar 2026 | Official leaderboard |
| 50 | Claude Sonnet 4.5 | 0.69 | thinking | Sep 2025 | Mar 2026 | Official leaderboard |
| 51 | | 0.69 | thinking | Sep 2025 | Mar 2026 | Official leaderboard |
| 52 | o1 | 0.68 | Dec 2024 | Mar 2026 | Official leaderboard | |
| 53 | | 0.68 | Jan 2026 | Feb 2026 | Official leaderboard | |
| 54 | | 0.67 | Oct 2025 | Nov 2025 | Official leaderboard | |
| 55 | | 0.67 | thinking | Sep 2025 | Mar 2026 | Official leaderboard |
| 56 | | 0.67 | Sep 2025 | Mar 2026 | Official leaderboard | |
| 57 | GPT-5.2 | 0.65 | Dec 2025 | Mar 2026 | Official leaderboard | |
| 58 | GLM-4.5 | 0.65 | Aug 2025 | Mar 2026 | Official leaderboard | |
| 59 | GLM-4.6 | 0.65 | Sep 2025 | Mar 2026 | Official leaderboard | |
| 60 | | 0.64 | thinking | Apr 2025 | Mar 2026 | Official leaderboard |
| 61 | | 0.64 | Oct 2025 | Mar 2026 | Official leaderboard | |
| 62 | Claude Opus 4 | 0.64 | thinking | May 2025 | Mar 2026 | Official leaderboard |
| 63 | | 0.63 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 64 | GPT-5.1 Instant | 0.62 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 65 | Kimi K2 Jul 2025 | 0.62 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 66 | | 0.62 | thinking | Apr 2025 | Mar 2026 | Official leaderboard |
| 67 | | 0.62 | Jul 2025 | Mar 2026 | Official leaderboard | |
| 68 | | 0.62 | Sep 2025 | Jan 2026 | Official leaderboard | |
| 69 | GPT-5 | 0.60 | Aug 2025 | Mar 2026 | Official leaderboard | |
| 70 | Claude Sonnet 4 | 0.60 | thinking | May 2025 | Feb 2026 | Official leaderboard |
| 71 | | 0.60 | Jul 2025 | Feb 2026 | Official leaderboard | |
| 72 | | 0.59 | Mar 2025 | Feb 2026 | Official leaderboard | |
| 73 | | 0.59 | Mar 2025 | Feb 2026 | Official leaderboard | |
| 74 | | 0.59 | Jun 2025 | Sep 2025 | Official leaderboard | |
| 75 | | 0.59 | thinking | Apr 2025 | Mar 2026 | Official leaderboard |
| 76 | | 0.58 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 77 | GPT-4.5 | 0.58 | Feb 2025 | Jan 2026 | Official leaderboard | |
| 78 | Claude 3.7 Sonnet | 0.55 | thinking | Feb 2025 | Feb 2026 | Official leaderboard |
| 79 | GPT-4.1 | 0.55 | Apr 2025 | Feb 2026 | Official leaderboard | |
| 80 | | 0.55 | thinking | Apr 2025 | Feb 2026 | Official leaderboard |
| 81 | | 0.53 | Jun 2025 | Mar 2026 | Official leaderboard | |
| 82 | Grok 3 | 0.52 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 83 | | 0.50 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 84 | | 0.48 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 85 | | 0.48 | thinking | Apr 2025 | Jan 2026 | Official leaderboard |
| 86 | | 0.45 | Sep 2024 | Mar 2026 | Official leaderboard | |
| 87 | | 0.43 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 88 | | 0.41 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 89 | | 0.38 | thinking | Apr 2025 | Feb 2026 | Official leaderboard |
| 90 | | 0.37 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 91 | GLM-4-9B | 0.31 | Jun 2024 | Mar 2026 | Official leaderboard | |
| 92 | | 0.27 | Mar 2025 | Feb 2026 | Official leaderboard | |
| 93 | | 0.23 | thinking | Apr 2025 | Mar 2026 | Official leaderboard |
| 94 | | 0.15 | Mar 2025 | Mar 2026 | Official leaderboard |
Rankings by part
We read 15 parts from the benchmark’s own leaderboard in 2 groups: skill and language. Each ranks models on one part of the test. GPT-5.5 leads 5 of them, and 5 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Algorithm reasoning
94 models we track have a score here.
- 1 GPT-5.5 0.88
- 2 Claude Fable 5 0.86
- 3 Kimi K3 ↑1 0.81
- 4
Gemini 3.1 Pro ↓1 0.79
- 5 Claude Sonnet 5 ↑9 0.73
- 6
Doubao Seed 2.1 Pro 0.72
- 7
DeepSeek-V4-Pro ↑4 0.72
- 8
Gemini 3.5 Flash ↓3 0.71
- 9 GPT-5.4 ↓1 0.71
- 10
Gemini 3 Pro ↑10 0.70
Code reasoning Chinese
92 models we track have a score here.
- 1 GPT-5.5 0.88
- 2 Claude Fable 5 0.86
- 3 Kimi K3 ↑1 0.81
- 4
Gemini 3.1 Pro ↓1 0.79
- 5 Claude Sonnet 5 ↑9 0.73
- 6
Doubao Seed 2.1 Pro 0.72
- 7
DeepSeek-V4-Pro ↑4 0.72
- 8
Gemini 3.5 Flash ↓3 0.71
- 9 GPT-5.4 ↓1 0.71
- 10
Gemini 3 Pro ↑10 0.70
Cognition
94 models we track have a score here.
- 1 Claude Fable 5 ↑1 0.88
- 2
Gemini 3.1 Pro ↑1 0.88
- 3 Claude Opus 4.6 ↑10 0.88
- 4
Gemini 3.5 Flash ↑1 0.87
- 5
Gemini 3 Pro ↑15 0.87
- 6
Gemini 3 Flash ↑13 0.87
- 7 Claude Opus 4.8 0.86
- 8 GPT-5.5 ↓7 0.86
- 9 Claude Opus 4.5 ↑8 0.86
- 10 Grok 4 ↑29 0.86
General reasoning
94 models we track have a score here.
- 1 Claude Fable 5 ↑1 0.98
- 2
Gemini 3.1 Pro ↑1 0.98
- 3
Tencent Hy3 preview ↑23 0.98
- 4 Claude Opus 4.6 ↑9 0.98
- 5
Qwen3.7-Max ↑4 0.98
- 6
Gemini 3 Pro ↑14 0.98
- 7 Kimi K3 ↓3 0.97
- 8
Ring-1T ↑53 0.97
- 9
Doubao Seed 2.1 Pro ↓3 0.97
- 10
Tencent Hy3 ↑11 0.97
Interaction
94 models we track have a score here.
- 1 Claude Opus 4.8 ↑6 0.91
- 2 Claude Fable 5 0.91
- 3 GPT-5.5 ↓2 0.91
- 4 Claude Opus 4.5 ↑13 0.90
- 5 Claude Opus 4.6 ↑8 0.90
- 6
Seed2.0 Pro ↑4 0.90
- 7
Gemini 3.1 Pro ↓4 0.90
- 8 GPT-5.4 0.90
- 9 Kimi K3 ↓5 0.90
- 10
Gemini 3.5 Flash ↓5 0.89
Learning
94 models we track have a score here.
- 1
Gemini 3.1 Pro ↑2 0.95
- 2
Gemini 3 Flash ↑17 0.94
- 3
Gemini 3.5 Flash ↑2 0.92
- 4
Gemini 3 Pro ↑16 0.92
- 5 GLM-5.1 ↑19 0.92
- 6
Qwen3.7-Max ↑3 0.92
- 7 GPT-5.5 ↓6 0.92
- 8 GLM-5.2 ↑7 0.92
- 9
DeepSeek-V4-Pro ↑2 0.92
- 10 GLM-5 ↑20 0.91
Math reasoning
94 models we track have a score here.
- 1 Claude Fable 5 ↑1 0.89
- 2 Claude Opus 4.8 ↑5 0.88
- 3
Qwen3.7-Max ↑6 0.88
- 4 Kimi K2.6 ↑8 0.88
- 5
Seed2.0 Pro ↑5 0.88
- 6 Claude Opus 4.5 ↑11 0.87
- 7 Claude Sonnet 5 ↑7 0.87
- 8
DeepSeek-V4-Flash ↑8 0.87
- 9 Claude Opus 4.6 ↑4 0.87
- 10 Kimi K2.5 ↑15 0.87
Subject knowledge
94 models we track have a score here.
- 1
Seed2.0 Pro ↑9 0.91
- 2
Qwen3.7-Max ↑7 0.91
- 3
Doubao Seed 2.1 Pro ↑3 0.91
- 4
Gemini 3.1 Pro ↓1 0.90
- 5
Gemini 3.5 Flash 0.90
- 6
Tencent Hy3 ↑15 0.90
- 7 Claude Fable 5 ↓5 0.90
- 8 Kimi K2.6 ↑4 0.90
- 9
DeepSeek-V4-Pro ↑2 0.90
- 10
Gemini 3 Pro ↑10 0.90
Instruction following
94 models we track have a score here.
- 1 GPT-5.5 0.71
- 2 GPT-5.4 ↑6 0.69
- 3 GLM-5.2 ↑12 0.69
- 4
Qwen3.7-Max ↑5 0.69
- 5
Gemini 3.5 Flash 0.67
- 6
Doubao Seed 2.1 Pro 0.67
- 7 Kimi K2.6 ↑5 0.66
- 8
Tencent Hy3 ↑13 0.66
- 9 o3-pro ↑14 0.65
- 10 Kimi K3 ↓6 0.64
Instruction following Chinese
92 models we track have a score here.
- 1 GPT-5.5 0.71
- 2 GPT-5.4 ↑6 0.69
- 3 GLM-5.2 ↑12 0.69
- 4
Qwen3.7-Max ↑5 0.69
- 5
Gemini 3.5 Flash 0.67
- 6
Doubao Seed 2.1 Pro 0.67
- 7 Kimi K2.6 ↑5 0.66
- 8
Tencent Hy3 ↑13 0.66
- 9 o3-pro ↑14 0.65
- 10 Kimi K3 ↓6 0.64
Subject reasoning
94 models we track have a score here.
- 1 Claude Opus 4.8 ↑6 0.90
- 2 GPT-5.5 ↓1 0.90
- 3
Seed2.0 Pro ↑7 0.89
- 4 Claude Fable 5 ↓2 0.89
- 5
Gemini 3.5 Flash 0.89
- 6
Tencent Hy3 ↑15 0.89
- 7
Doubao Seed 2.1 Pro ↓1 0.89
- 8
Qwen3.7-Max ↑1 0.89
- 9 Kimi K3 ↓5 0.89
- 10 Claude Opus 4.6 ↑3 0.89
Subject reasoning Chinese
92 models we track have a score here.
- 1
Doubao Seed 2.1 Pro ↑5 0.95
- 2 GPT-5.5 ↓1 0.94
- 3
Seed2.0 Pro ↑7 0.94
- 4 Claude Fable 5 ↓2 0.94
- 5
Gemini 3.1 Pro ↓2 0.93
- 6
Tencent Hy3 ↑15 0.93
- 7 Kimi K3 ↓3 0.93
- 8
Gemini 3 Pro ↑12 0.93
- 9
DeepSeek-V4-Flash ↑7 0.93
- 10
Gemini 3.5 Flash ↓5 0.93
Subject reasoning English
92 models we track have a score here.
- 1 Claude Opus 4.8 ↑6 0.89
- 2 GPT-5.5 ↓1 0.88
- 3 Claude Fable 5 ↓1 0.87
- 4 Claude Opus 4.6 ↑9 0.87
- 5
Gemini 3.5 Flash 0.87
- 6
Seed2.0 Pro ↑4 0.87
- 7
Qwen3.7-Max ↑2 0.87
- 8
Tencent Hy3 ↑13 0.87
- 9 Kimi K2.5 ↑16 0.87
- 10 Kimi K3 ↓6 0.87
Chinese
92 models we track have a score here.
- 1 GPT-5.5 0.85
- 2 Claude Fable 5 0.84
- 3
Gemini 3.1 Pro 0.82
- 4 Kimi K3 0.82
- 5
Gemini 3.5 Flash 0.81
- 6
Doubao Seed 2.1 Pro 0.80
- 7 GPT-5.4 ↑1 0.80
- 8
Qwen3.7-Max ↑1 0.79
- 9 Claude Opus 4.8 ↓2 0.79
- 10
DeepSeek-V4-Pro ↑1 0.79
English
92 models we track have a score here.
- 1 Claude Opus 4.8 ↑6 0.92
- 2 Claude Opus 4.6 ↑11 0.92
- 3
Gemini 3.1 Pro 0.92
- 4
Gemini 3.5 Flash ↑1 0.91
- 5
Seed2.0 Pro ↑5 0.91
- 6 Claude Fable 5 ↓4 0.91
- 7 Kimi K2.6 ↑5 0.91
- 8
Gemini 3 Flash ↑11 0.91
- 9 Kimi K3 ↓5 0.91
- 10
Qwen3.7-Max ↓1 0.91
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official AGI-Eval Community Instruction-Tuned Language Models leaderboard
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official AGI-Eval Community Instruction-Tuned Language Models leaderboard
9 models have held number one on the official leaderboard since its release in March 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official AGI-Eval Community Instruction-Tuned Language Models leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official AGI-Eval Community Instruction-Tuned Language Models leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (122 entries).
- Pass Models scored 94 models we track, plus 28 other entries on its leaderboard.
- Pass Newest score The newest is from July 2026, for Kimi K3.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Fable 5 (#12).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on agi-eval.org: 114 rows for models we track and 28 other entries at the last read.
- Pass Last read November 21st, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.