Arena Expert
Experts compare model answers to questions drawn from their professional work. Arena ranks models from their votes.
Arena publishes an expert leaderboard and a dataset of expert comparisons.
- Made by
- Arena
- Released
- November 2025
- Kind
- Expert-written questions
- Level
- Expert
- Scored
- Ranked by votes
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Preference
- Language
- English
- Interaction
- Single turn
- Items from
- Written by experts
- Refresh
- Live
- Run by
- A host
- In views
- Kept fresh
- Strongest model tested
- GPT-5 #71 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 21st, 2026
qwen3-235b-a22b-instruct-2507-invalid tops the leaderboard with 1,223 DeepSeek-V3.2-Exp leads with 1,143 among models released by September 2025
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. Bradley-Terry ratings computed from the 5,128 expert prompt battles in the published dataset. 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. The best model we track is DeepSeek-V3.2-Exp, at 1,143. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2025, 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 16 more
- 1,223 qwen3-235b-a22b-instruct-2507-invalid
- 1,143
DeepSeek-V3.2-Exp
- 1,135
Qwen3-VL-235B-A22B
- 1,134
Qwen3-Max-Preview
- 1,123
Qwen3-235B-A22B-Thinking
- 1,106
Gemini 2.5 Pro
- 1,093
Gemini 2.5 Flash
- 1,093 claude-sonnet-4-5-20250929-thinking-32k
- 1,088 GLM-4.5
- 1,088
Qwen3-VL-235B-A22B-Instruct
- 1,082 GLM-4.5V
- 1,080 Grok 4 Fast
- 1,074 Grok 4
- 1,073 claude-sonnet-4-5-20250929-old
- 1,069 Kimi K2
- 1,066
Qwen3-235B-A22B-Instruct
- 1,063 gpt-5-old
- 1,062
Qwen3-Max
- 1,060 llama-4-maverick-03-26-experimental
- 1,058
Qwen3-30B-A3B-Instruct
- 1,057
DeepSeek-V3.1
- 1,057
Qwen3-Next-80B-A3B-Instruct
- 1,054 claude-opus-4-1-20250805-thinking-16k
- 1,052 Claude Opus 4.1
- 1,051 GPT-4.1
- 1,050
Ling-flash-2.0
- 1,045
Hunyuan-TurboS
- 1,041 Claude Opus 4
- 1,040
LongCat-Flash-Chat
- 1,039 GLM-4.6
- 1,038 GPT-5
- 1,033 mistral-medium-2508
- 1,033 Grok-3 mini
- 1,030
Step 3
- 1,030 o3
- 1,021 gpt-5-high-new-system-prompt
- 1,019 claude-sonnet-4-20250514-thinking-32k
- 1,018
MiniMax-M1-80k
- 1,012 GPT-5 mini
- 1,012 claude-opus-4-20250514-thinking-16k
- 1,009
DeepSeek-R1
- 1,008 chatgpt-4o-latest-20250326-old
- 1,007
Gemini 2.0 Flash Thinking
- 1,004
Qwen3-30B-A3B
- 1,004
Qwen3-Next-80B-A3B
- 1,003 Qwen-VL-Max
- 1,000 mai-1-preview
- 999 qwen3-235b-a22b-no-thinking
- 998
DeepSeek-V3.1-Terminus
- 997 GPT-5 Chat
- 995 o4-mini
- 993 GLM-4.5-Air
- 991 gemini-2.5-flash-lite-preview-09-2025-no-thinking
- 990 GPT-4o
- 988 qwen-max-2025-01-25
- 988
QwQ-32B
- 987 o3-mini
- 976
Qwen3-235B-A22B
- 972 gpt-oss-120b
- 970
Gemini 2.5 Flash-Lite
- 966 Claude Sonnet 4
- 960 gemini-2.0-flash-001
- 956
Hunyuan-T1
- 951 Grok 3
- 950
DeepSeek-V3
- 941 mistral-small-2506
- 941 GPT-4.1 mini
- 940 gpt-oss-20b
- 938 kimi-k2-0711-preview
- 936
Qwen3-Coder-480B-A35B
- 936 Claude 3.5 Sonnet
- 934 claude-3-7-sonnet-20250219-thinking-32k
- 928 mistral-medium-2505
- 919
Gemma 3 27B
- 914 GPT-5 nano
- 911
Llama 4 Maverick
- 904 Claude 3.7 Sonnet
- 890 nvidia-llama-3.3-nemotron-super-49b-v1.5
- 889 step-1o-turbo-202506
- 885 mistral-small-3.1-24b-instruct-2503
- 878 amazon-nova-experimental-chat-05-14
- 865
Llama 4 Scout
- 865 Claude 3.5 Haiku
- 862 command-a-03-2025
- 860
Ring-flash-2.0
- 835
Magistral Medium 1.0
- 834
Gemma 3n E4B
- 818
Llama 3.3 70B Instruct
- 796 amazon.nova-pro-v1:0
- 716 GPT-4o mini
Bars start at 600.
- 1 qwen3-235b-a22b-instruct-2507-invalid 1,223
- 2
DeepSeek-V3.2-Exp thinking 1,143
- 3
Qwen3-VL-235B-A22B thinking 1,135
- 4
Qwen3-Max-Preview 1,134
- 5
Qwen3-235B-A22B-Thinking Jul 2025 1,123
- 6
Gemini 2.5 Pro Jun 2025 1,106
- 7
Gemini 2.5 Flash Sep 2025 1,093
- 8 claude-sonnet-4-5-20250929-thinking-32k 1,093
- 9 GLM-4.5 1,088
- 10
Qwen3-VL-235B-A22B-Instruct 1,088
- 11 GLM-4.5V 1,082
- 12 Grok 4 Fast reasoning 1,080
- 13 Grok 4 1,074
- 14 claude-sonnet-4-5-20250929-old 1,073
- 15 Kimi K2 Sep 2025 1,069
- 16
Qwen3-235B-A22B-Instruct Jul 2025 1,066
- 17 gpt-5-old 1,063
- 18
Qwen3-Max 1,062
- 19 llama-4-maverick-03-26-experimental 1,060
- 20
Qwen3-30B-A3B-Instruct Jul 2025 1,058
- 21
DeepSeek-V3.1 1,057
- 22
Qwen3-Next-80B-A3B-Instruct 1,057
- 23 claude-opus-4-1-20250805-thinking-16k 1,054
- 24 Claude Opus 4.1 1,052
- 25 GPT-4.1 1,051
- 26
Ling-flash-2.0 1,050
- 27
Hunyuan-TurboS 1,045
- 28 Claude Opus 4 1,041
- 29
LongCat-Flash-Chat 1,040
- 30 GLM-4.6 1,039
- 31 GPT-5 high 1,038
- 32 mistral-medium-2508 1,033
- 33 Grok-3 mini 1,033
- 34
Step 3 1,030
- 35 o3 1,030
- 36 gpt-5-high-new-system-prompt 1,021
- 37 claude-sonnet-4-20250514-thinking-32k 1,019
- 38
MiniMax-M1-80k 1,018
- 39 GPT-5 mini high 1,012
- 40 claude-opus-4-20250514-thinking-16k 1,012
- 41
DeepSeek-R1 May 2025 1,009
- 42 chatgpt-4o-latest-20250326-old 1,008
- 43
Gemini 2.0 Flash Thinking Jan 2025 1,007
- 44
Qwen3-30B-A3B 1,004
- 45
Qwen3-Next-80B-A3B thinking 1,004
- 46 Qwen-VL-Max 1,003
- 47 mai-1-preview 1,000
- 48 qwen3-235b-a22b-no-thinking 999
- 49
DeepSeek-V3.1-Terminus thinking 998
- 50 GPT-5 Chat 997
- 51 o4-mini 995
- 52 GLM-4.5-Air 993
- 53 gemini-2.5-flash-lite-preview-09-2025-no-thinking 991
- 54 GPT-4o Nov 2024 990
- 55 qwen-max-2025-01-25 988
- 56
QwQ-32B 988
- 57 o3-mini 987
- 58
Qwen3-235B-A22B 976
- 59 gpt-oss-120b 972
- 60
Gemini 2.5 Flash-Lite Sep 2025, thinking 970
- 61 Claude Sonnet 4 966
- 62 gemini-2.0-flash-001 960
- 63
Hunyuan-T1 956
- 64 Grok 3 951
- 65
DeepSeek-V3 Mar 2025 950
- 66 mistral-small-2506 941
- 67 GPT-4.1 mini 941
- 68 gpt-oss-20b 940
- 69 kimi-k2-0711-preview 938
- 70
Qwen3-Coder-480B-A35B 936
- 71 Claude 3.5 Sonnet 936
- 72 claude-3-7-sonnet-20250219-thinking-32k 934
- 73 mistral-medium-2505 928
- 74
Gemma 3 27B 919
- 75 GPT-5 nano high 914
- 76
Llama 4 Maverick 911
- 77 Claude 3.7 Sonnet 904
- 78 nvidia-llama-3.3-nemotron-super-49b-v1.5 890
- 79 step-1o-turbo-202506 889
- 80 mistral-small-3.1-24b-instruct-2503 885
- 81 amazon-nova-experimental-chat-05-14 878
- 82
Llama 4 Scout 865
- 83 Claude 3.5 Haiku 865
- 84 command-a-03-2025 862
- 85
Ring-flash-2.0 860
- 86
Magistral Medium 1.0 835
- 87
Gemma 3n E4B 834
- 88
Llama 3.3 70B Instruct 818
- 89 amazon.nova-pro-v1:0 796
- 90 GPT-4o mini 716
Source: The Arena Expert paper
- 1,143
DeepSeek-V3.2-Exp
- 1,135
Qwen3-VL-235B-A22B
- 1,134
Qwen3-Max-Preview
- 1,123
Qwen3-235B-A22B-Thinking
- 1,106
Gemini 2.5 Pro
- 1,093
Gemini 2.5 Flash
- 1,088 GLM-4.5
- 1,088
Qwen3-VL-235B-A22B-Instruct
- 1,082 GLM-4.5V
- 1,080 Grok 4 Fast
- 1,074 Grok 4
- 1,069 Kimi K2
- 1,066
Qwen3-235B-A22B-Instruct
- 1,062
Qwen3-Max
- 1,058
Qwen3-30B-A3B-Instruct
- 1,057
DeepSeek-V3.1
- 1,057
Qwen3-Next-80B-A3B-Instruct
- 1,052 Claude Opus 4.1
- 1,051 GPT-4.1
- 1,050
Ling-flash-2.0
- 1,045
Hunyuan-TurboS
- 1,041 Claude Opus 4
- 1,040
LongCat-Flash-Chat
- 1,039 GLM-4.6
- 1,038 GPT-5
- 1,033 Grok-3 mini
- 1,030
Step 3
- 1,030 o3
- 1,018
MiniMax-M1-80k
- 1,012 GPT-5 mini
- 1,009
DeepSeek-R1
- 1,007
Gemini 2.0 Flash Thinking
- 1,004
Qwen3-30B-A3B
- 1,004
Qwen3-Next-80B-A3B
- 1,003 Qwen-VL-Max
- 998
DeepSeek-V3.1-Terminus
- 997 GPT-5 Chat
- 995 o4-mini
- 993 GLM-4.5-Air
- 990 GPT-4o
- 988
QwQ-32B
- 987 o3-mini
- 976
Qwen3-235B-A22B
- 972 gpt-oss-120b
- 970
Gemini 2.5 Flash-Lite
- 966 Claude Sonnet 4
- 956
Hunyuan-T1
- 951 Grok 3
- 950
DeepSeek-V3
- 941 GPT-4.1 mini
- 940 gpt-oss-20b
- 936
Qwen3-Coder-480B-A35B
- 936 Claude 3.5 Sonnet
- 919
Gemma 3 27B
- 914 GPT-5 nano
- 911
Llama 4 Maverick
- 904 Claude 3.7 Sonnet
- 865
Llama 4 Scout
- 865 Claude 3.5 Haiku
- 860
Ring-flash-2.0
- 835
Magistral Medium 1.0
- 834
Gemma 3n E4B
- 818
Llama 3.3 70B Instruct
- 716 GPT-4o mini
Bars start at 700.
- 1
DeepSeek-V3.2-Exp thinking 1,143
- 2
Qwen3-VL-235B-A22B thinking 1,135
- 3
Qwen3-Max-Preview 1,134
- 4
Qwen3-235B-A22B-Thinking Jul 2025 1,123
- 5
Gemini 2.5 Pro Jun 2025 1,106
- 6
Gemini 2.5 Flash Sep 2025 1,093
- 7 GLM-4.5 1,088
- 8
Qwen3-VL-235B-A22B-Instruct 1,088
- 9 GLM-4.5V 1,082
- 10 Grok 4 Fast reasoning 1,080
- 11 Grok 4 1,074
- 12 Kimi K2 Sep 2025 1,069
- 13
Qwen3-235B-A22B-Instruct Jul 2025 1,066
- 14
Qwen3-Max 1,062
- 15
Qwen3-30B-A3B-Instruct Jul 2025 1,058
- 16
DeepSeek-V3.1 1,057
- 17
Qwen3-Next-80B-A3B-Instruct 1,057
- 18 Claude Opus 4.1 1,052
- 19 GPT-4.1 1,051
- 20
Ling-flash-2.0 1,050
- 21
Hunyuan-TurboS 1,045
- 22 Claude Opus 4 1,041
- 23
LongCat-Flash-Chat 1,040
- 24 GLM-4.6 1,039
- 25 GPT-5 high 1,038
- 26 Grok-3 mini 1,033
- 27
Step 3 1,030
- 28 o3 1,030
- 29
MiniMax-M1-80k 1,018
- 30 GPT-5 mini high 1,012
- 31
DeepSeek-R1 May 2025 1,009
- 32
Gemini 2.0 Flash Thinking Jan 2025 1,007
- 33
Qwen3-30B-A3B 1,004
- 34
Qwen3-Next-80B-A3B thinking 1,004
- 35 Qwen-VL-Max 1,003
- 36
DeepSeek-V3.1-Terminus thinking 998
- 37 GPT-5 Chat 997
- 38 o4-mini 995
- 39 GLM-4.5-Air 993
- 40 GPT-4o Nov 2024 990
- 41
QwQ-32B 988
- 42 o3-mini 987
- 43
Qwen3-235B-A22B 976
- 44 gpt-oss-120b 972
- 45
Gemini 2.5 Flash-Lite Sep 2025, thinking 970
- 46 Claude Sonnet 4 966
- 47
Hunyuan-T1 956
- 48 Grok 3 951
- 49
DeepSeek-V3 Mar 2025 950
- 50 GPT-4.1 mini 941
- 51 gpt-oss-20b 940
- 52
Qwen3-Coder-480B-A35B 936
- 53 Claude 3.5 Sonnet 936
- 54
Gemma 3 27B 919
- 55 GPT-5 nano high 914
- 56
Llama 4 Maverick 911
- 57 Claude 3.7 Sonnet 904
- 58
Llama 4 Scout 865
- 59 Claude 3.5 Haiku 865
- 60
Ring-flash-2.0 860
- 61
Magistral Medium 1.0 835
- 62
Gemma 3n E4B 834
- 63
Llama 3.3 70B Instruct 818
- 64 GPT-4o mini 716
Source: The Arena Expert paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | qwen3-235b-a22b-instruct-2507-invalid | 1,223 | Official leaderboard | ||
| 2 | | 1,143 | thinking | Sep 2025 | Official leaderboard |
| 3 | | 1,135 | thinking | Sep 2025 | Official leaderboard |
| 4 | | 1,134 | Sep 2025 | Official leaderboard | |
| 5 | | 1,123 | Jul 2025 | Official leaderboard | |
| 6 | | 1,106 | Jun 2025 | Official leaderboard | |
| 7 | | 1,093 | Sep 2025 | Official leaderboard | |
| 8 | claude-sonnet-4-5-20250929-thinking-32k | 1,093 | Official leaderboard | ||
| 9 | GLM-4.5 | 1,088 | Aug 2025 | Official leaderboard | |
| 10 | | 1,088 | Sep 2025 | Official leaderboard | |
| 11 | GLM-4.5V | 1,082 | Aug 2025 | Official leaderboard | |
| 12 | Grok 4 Fast | 1,080 | reasoning | Sep 2025 | Official leaderboard |
| 13 | Grok 4 | 1,074 | Jul 2025 | Official leaderboard | |
| 14 | claude-sonnet-4-5-20250929-old | 1,073 | Official leaderboard | ||
| 15 | Kimi K2 Sep 2025 | 1,069 | Sep 2025 | Official leaderboard | |
| 16 | | 1,066 | Jul 2025 | Official leaderboard | |
| 17 | gpt-5-old | 1,063 | Official leaderboard | ||
| 18 | | 1,062 | Sep 2025 | Official leaderboard | |
| 19 | llama-4-maverick-03-26-experimental | 1,060 | Official leaderboard | ||
| 20 | | 1,058 | Jul 2025 | Official leaderboard | |
| 21 | | 1,057 | Aug 2025 | Official leaderboard | |
| 22 | | 1,057 | Sep 2025 | Official leaderboard | |
| 23 | claude-opus-4-1-20250805-thinking-16k | 1,054 | Official leaderboard | ||
| 24 | Claude Opus 4.1 | 1,052 | Aug 2025 | Official leaderboard | |
| 25 | GPT-4.1 | 1,051 | Apr 2025 | Official leaderboard | |
| 26 | | 1,050 | Sep 2025 | Official leaderboard | |
| 27 | | 1,045 | Feb 2025 | Official leaderboard | |
| 28 | Claude Opus 4 | 1,041 | May 2025 | Official leaderboard | |
| 29 | | 1,040 | Aug 2025 | Official leaderboard | |
| 30 | GLM-4.6 | 1,039 | Sep 2025 | Official leaderboard | |
| 31 | GPT-5 | 1,038 | high | Aug 2025 | Official leaderboard |
| 32 | mistral-medium-2508 | 1,033 | Official leaderboard | ||
| 33 | Grok-3 mini | 1,033 | Apr 2025 | Official leaderboard | |
| 34 | | 1,030 | Jul 2025 | Official leaderboard | |
| 35 | o3 | 1,030 | Apr 2025 | Official leaderboard | |
| 36 | gpt-5-high-new-system-prompt | 1,021 | Official leaderboard | ||
| 37 | claude-sonnet-4-20250514-thinking-32k | 1,019 | Official leaderboard | ||
| 38 | | 1,018 | Jun 2025 | Official leaderboard | |
| 39 | GPT-5 mini | 1,012 | high | Aug 2025 | Official leaderboard |
| 40 | claude-opus-4-20250514-thinking-16k | 1,012 | Official leaderboard | ||
| 41 | | 1,009 | May 2025 | Official leaderboard | |
| 42 | chatgpt-4o-latest-20250326-old | 1,008 | Official leaderboard | ||
| 43 | | 1,007 | Jan 2025 | Official leaderboard | |
| 44 | | 1,004 | Apr 2025 | Official leaderboard | |
| 45 | | 1,004 | thinking | Sep 2025 | Official leaderboard |
| 46 | Qwen-VL-Max | 1,003 | Jan 2024 | Official leaderboard | |
| 47 | mai-1-preview | 1,000 | Official leaderboard | ||
| 48 | qwen3-235b-a22b-no-thinking | 999 | Official leaderboard | ||
| 49 | | 998 | thinking | Sep 2025 | Official leaderboard |
| 50 | GPT-5 Chat | 997 | Aug 2025 | Official leaderboard | |
| 51 | o4-mini | 995 | Apr 2025 | Official leaderboard | |
| 52 | GLM-4.5-Air | 993 | Jul 2025 | Official leaderboard | |
| 53 | gemini-2.5-flash-lite-preview-09-2025-no-thinking | 991 | Official leaderboard | ||
| 54 | GPT-4o Nov 2024 | 990 | Nov 2024 | Official leaderboard | |
| 55 | qwen-max-2025-01-25 | 988 | Official leaderboard | ||
| 56 | | 988 | Mar 2025 | Official leaderboard | |
| 57 | o3-mini | 987 | Jan 2025 | Official leaderboard | |
| 58 | | 976 | Apr 2025 | Official leaderboard | |
| 59 | gpt-oss-120b | 972 | Aug 2025 | Official leaderboard | |
| 60 | | 970 | thinking | Sep 2025 | Official leaderboard |
| 61 | Claude Sonnet 4 | 966 | May 2025 | Official leaderboard | |
| 62 | gemini-2.0-flash-001 | 960 | Official leaderboard | ||
| 63 | | 956 | Mar 2025 | Official leaderboard | |
| 64 | Grok 3 | 951 | Apr 2025 | Official leaderboard | |
| 65 | | 950 | Mar 2025 | Official leaderboard | |
| 66 | mistral-small-2506 | 941 | Official leaderboard | ||
| 67 | GPT-4.1 mini | 941 | Apr 2025 | Official leaderboard | |
| 68 | gpt-oss-20b | 940 | Aug 2025 | Official leaderboard | |
| 69 | kimi-k2-0711-preview | 938 | Official leaderboard | ||
| 70 | | 936 | Jul 2025 | Official leaderboard | |
| 71 | Claude 3.5 Sonnet | 936 | Jun 2024 | Official leaderboard | |
| 72 | claude-3-7-sonnet-20250219-thinking-32k | 934 | Official leaderboard | ||
| 73 | mistral-medium-2505 | 928 | Official leaderboard | ||
| 74 | | 919 | Mar 2025 | Official leaderboard | |
| 75 | GPT-5 nano | 914 | high | Aug 2025 | Official leaderboard |
| 76 | | 911 | Apr 2025 | Official leaderboard | |
| 77 | Claude 3.7 Sonnet | 904 | Feb 2025 | Official leaderboard | |
| 78 | nvidia-llama-3.3-nemotron-super-49b-v1.5 | 890 | Official leaderboard | ||
| 79 | step-1o-turbo-202506 | 889 | Official leaderboard | ||
| 80 | mistral-small-3.1-24b-instruct-2503 | 885 | Official leaderboard | ||
| 81 | amazon-nova-experimental-chat-05-14 | 878 | Official leaderboard | ||
| 82 | | 865 | Apr 2025 | Official leaderboard | |
| 83 | Claude 3.5 Haiku | 865 | Oct 2024 | Official leaderboard | |
| 84 | command-a-03-2025 | 862 | Official leaderboard | ||
| 85 | | 860 | Sep 2025 | Official leaderboard | |
| 86 | | 835 | Jun 2025 | Official leaderboard | |
| 87 | | 834 | Jun 2025 | Official leaderboard | |
| 88 | | 818 | Dec 2024 | Official leaderboard | |
| 89 | amazon.nova-pro-v1:0 | 796 | Official leaderboard | ||
| 90 | GPT-4o mini | 716 | Jul 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 1,143 | thinking | Sep 2025 | Official leaderboard |
| 2 | | 1,135 | thinking | Sep 2025 | Official leaderboard |
| 3 | | 1,134 | Sep 2025 | Official leaderboard | |
| 4 | | 1,123 | Jul 2025 | Official leaderboard | |
| 5 | | 1,106 | Jun 2025 | Official leaderboard | |
| 6 | | 1,093 | Sep 2025 | Official leaderboard | |
| 7 | GLM-4.5 | 1,088 | Aug 2025 | Official leaderboard | |
| 8 | | 1,088 | Sep 2025 | Official leaderboard | |
| 9 | GLM-4.5V | 1,082 | Aug 2025 | Official leaderboard | |
| 10 | Grok 4 Fast | 1,080 | reasoning | Sep 2025 | Official leaderboard |
| 11 | Grok 4 | 1,074 | Jul 2025 | Official leaderboard | |
| 12 | Kimi K2 Sep 2025 | 1,069 | Sep 2025 | Official leaderboard | |
| 13 | | 1,066 | Jul 2025 | Official leaderboard | |
| 14 | | 1,062 | Sep 2025 | Official leaderboard | |
| 15 | | 1,058 | Jul 2025 | Official leaderboard | |
| 16 | | 1,057 | Aug 2025 | Official leaderboard | |
| 17 | | 1,057 | Sep 2025 | Official leaderboard | |
| 18 | Claude Opus 4.1 | 1,052 | Aug 2025 | Official leaderboard | |
| 19 | GPT-4.1 | 1,051 | Apr 2025 | Official leaderboard | |
| 20 | | 1,050 | Sep 2025 | Official leaderboard | |
| 21 | | 1,045 | Feb 2025 | Official leaderboard | |
| 22 | Claude Opus 4 | 1,041 | May 2025 | Official leaderboard | |
| 23 | | 1,040 | Aug 2025 | Official leaderboard | |
| 24 | GLM-4.6 | 1,039 | Sep 2025 | Official leaderboard | |
| 25 | GPT-5 | 1,038 | high | Aug 2025 | Official leaderboard |
| 26 | Grok-3 mini | 1,033 | Apr 2025 | Official leaderboard | |
| 27 | | 1,030 | Jul 2025 | Official leaderboard | |
| 28 | o3 | 1,030 | Apr 2025 | Official leaderboard | |
| 29 | | 1,018 | Jun 2025 | Official leaderboard | |
| 30 | GPT-5 mini | 1,012 | high | Aug 2025 | Official leaderboard |
| 31 | | 1,009 | May 2025 | Official leaderboard | |
| 32 | | 1,007 | Jan 2025 | Official leaderboard | |
| 33 | | 1,004 | Apr 2025 | Official leaderboard | |
| 34 | | 1,004 | thinking | Sep 2025 | Official leaderboard |
| 35 | Qwen-VL-Max | 1,003 | Jan 2024 | Official leaderboard | |
| 36 | | 998 | thinking | Sep 2025 | Official leaderboard |
| 37 | GPT-5 Chat | 997 | Aug 2025 | Official leaderboard | |
| 38 | o4-mini | 995 | Apr 2025 | Official leaderboard | |
| 39 | GLM-4.5-Air | 993 | Jul 2025 | Official leaderboard | |
| 40 | GPT-4o Nov 2024 | 990 | Nov 2024 | Official leaderboard | |
| 41 | | 988 | Mar 2025 | Official leaderboard | |
| 42 | o3-mini | 987 | Jan 2025 | Official leaderboard | |
| 43 | | 976 | Apr 2025 | Official leaderboard | |
| 44 | gpt-oss-120b | 972 | Aug 2025 | Official leaderboard | |
| 45 | | 970 | thinking | Sep 2025 | Official leaderboard |
| 46 | Claude Sonnet 4 | 966 | May 2025 | Official leaderboard | |
| 47 | | 956 | Mar 2025 | Official leaderboard | |
| 48 | Grok 3 | 951 | Apr 2025 | Official leaderboard | |
| 49 | | 950 | Mar 2025 | Official leaderboard | |
| 50 | GPT-4.1 mini | 941 | Apr 2025 | Official leaderboard | |
| 51 | gpt-oss-20b | 940 | Aug 2025 | Official leaderboard | |
| 52 | | 936 | Jul 2025 | Official leaderboard | |
| 53 | Claude 3.5 Sonnet | 936 | Jun 2024 | Official leaderboard | |
| 54 | | 919 | Mar 2025 | Official leaderboard | |
| 55 | GPT-5 nano | 914 | high | Aug 2025 | Official leaderboard |
| 56 | | 911 | Apr 2025 | Official leaderboard | |
| 57 | Claude 3.7 Sonnet | 904 | Feb 2025 | Official leaderboard | |
| 58 | | 865 | Apr 2025 | Official leaderboard | |
| 59 | Claude 3.5 Haiku | 865 | Oct 2024 | Official leaderboard | |
| 60 | | 860 | Sep 2025 | Official leaderboard | |
| 61 | | 835 | Jun 2025 | Official leaderboard | |
| 62 | | 834 | Jun 2025 | Official leaderboard | |
| 63 | | 818 | Dec 2024 | Official leaderboard | |
| 64 | GPT-4o mini | 716 | Jul 2024 | Official 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: The Arena Expert paper
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: The Arena Expert paper
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The Arena Expert paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Arena Expert 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 Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for GLM-4.6. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (90 entries).
- Pass Models scored 64 models we track, plus 26 other entries on its leaderboard.
- Warning Newest score The newest came 14 months ago, in September 2025, for GLM-4.6.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
- Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arena.ai: 72 rows for models we track and 26 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.