FlagEval Arena
Models answer the same prompt anonymously. Users compare their responses, and the leaderboard estimates a rating from the votes.
The official ratings feed lists 36 models.
- Kind
- Overall chat quality
- Level
- Everyday
- Scored
- Ranked by votes
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Preference
- Language
- Chinese
- Interaction
- Single turn
- Refresh
- Live
- Run by
- A host
- In views
- Kept fresh
- Strongest model tested
- o3 #84 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 21st, 2026
o4-mini leads with 1,134 among models released by September 2025 o4-mini leads with 1,134 among models released by September 2025
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 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
- 1,134 o4-mini
- 1,118
Magistral Medium 1.0
- 1,107 GPT-4.1 mini
- 1,106 o3
- 1,092
Gemini 2.5 Pro
- 1,063
Qwen3-235B-A22B
- 1,049
Qwen3-235B-A22B-Instruct
- 1,043 Claude 3.7 Sonnet
- 1,042
Doubao-Seed-1.6
- 1,035 Claude Sonnet 4
- 1,032
ERNIE-4.5-300B-A47B
- 1,029
Hunyuan-TurboS
- 1,027 GLM-4.5
- 1,019
DeepSeek-V3
- 1,011
Mistral Medium 3.1
- 1,008
DeepSeek-V3.1
- 1,006
Qwen3-235B-A22B-Thinking
- 1,002 GPT-4.1
- 993
DeepSeek-R1
- 986 Kimi K2
- 983
Gemini 2.5 Flash
- 981
Qwen2.5-Max
- 974 Grok 4
- 973 GPT-4o (2024-11-20)
- 961
Doubao-1.5-pro
- 956
Mistral Medium 3
- 953
Yi-Lightning
- 945 GLM-4-plus
- 927
Qwen2.5-72B
- 909
MiniMax-M1-80k
- 876 GLM-Zero-Preview
Bars start at 800.
- 1 o4-mini 1,134
- 2
Magistral Medium 1.0 1,118
- 3 GPT-4.1 mini 1,107
- 4 o3 1,106
- 5
Gemini 2.5 Pro Jun 2025 1,092
- 6
Qwen3-235B-A22B 1,063
- 7
Qwen3-235B-A22B-Instruct Jul 2025 1,049
- 8 Claude 3.7 Sonnet 1,043
- 9
Doubao-Seed-1.6 1,042
- 10 Claude Sonnet 4 1,035
- 11
ERNIE-4.5-300B-A47B 1,032
- 12
Hunyuan-TurboS 1,029
- 13 GLM-4.5 1,027
- 14
DeepSeek-V3 Mar 2025 1,019
- 15
Mistral Medium 3.1 1,011
- 16
DeepSeek-V3.1 1,008
- 17
Qwen3-235B-A22B-Thinking Jul 2025 1,006
- 18 GPT-4.1 1,002
- 19
DeepSeek-R1 May 2025 993
- 20 Kimi K2 Sep 2025 986
- 21
Gemini 2.5 Flash Sep 2025 983
- 22
Qwen2.5-Max 981
- 23 Grok 4 974
- 24 GPT-4o (2024-11-20) 973
- 25
Doubao-1.5-pro 961
- 26
Mistral Medium 3 956
- 27
Yi-Lightning 953
- 28 GLM-4-plus 945
- 29
Qwen2.5-72B 927
- 30
MiniMax-M1-80k 909
- 31 GLM-Zero-Preview 876
Source: Official FlagEval Arena leaderboard
- 1,134 o4-mini
- 1,118
Magistral Medium 1.0
- 1,107 GPT-4.1 mini
- 1,106 o3
- 1,092
Gemini 2.5 Pro
- 1,063
Qwen3-235B-A22B
- 1,049
Qwen3-235B-A22B-Instruct
- 1,043 Claude 3.7 Sonnet
- 1,042
Doubao-Seed-1.6
- 1,035 Claude Sonnet 4
- 1,032
ERNIE-4.5-300B-A47B
- 1,029
Hunyuan-TurboS
- 1,027 GLM-4.5
- 1,019
DeepSeek-V3
- 1,011
Mistral Medium 3.1
- 1,008
DeepSeek-V3.1
- 1,006
Qwen3-235B-A22B-Thinking
- 1,002 GPT-4.1
- 993
DeepSeek-R1
- 986 Kimi K2
- 983
Gemini 2.5 Flash
- 981
Qwen2.5-Max
- 974 Grok 4
- 961
Doubao-1.5-pro
- 956
Mistral Medium 3
- 953
Yi-Lightning
- 927
Qwen2.5-72B
- 909
MiniMax-M1-80k
Bars start at 900.
- 1 o4-mini 1,134
- 2
Magistral Medium 1.0 1,118
- 3 GPT-4.1 mini 1,107
- 4 o3 1,106
- 5
Gemini 2.5 Pro Jun 2025 1,092
- 6
Qwen3-235B-A22B 1,063
- 7
Qwen3-235B-A22B-Instruct Jul 2025 1,049
- 8 Claude 3.7 Sonnet 1,043
- 9
Doubao-Seed-1.6 1,042
- 10 Claude Sonnet 4 1,035
- 11
ERNIE-4.5-300B-A47B 1,032
- 12
Hunyuan-TurboS 1,029
- 13 GLM-4.5 1,027
- 14
DeepSeek-V3 Mar 2025 1,019
- 15
Mistral Medium 3.1 1,011
- 16
DeepSeek-V3.1 1,008
- 17
Qwen3-235B-A22B-Thinking Jul 2025 1,006
- 18 GPT-4.1 1,002
- 19
DeepSeek-R1 May 2025 993
- 20 Kimi K2 Sep 2025 986
- 21
Gemini 2.5 Flash Sep 2025 983
- 22
Qwen2.5-Max 981
- 23 Grok 4 974
- 24
Doubao-1.5-pro 961
- 25
Mistral Medium 3 956
- 26
Yi-Lightning 953
- 27
Qwen2.5-72B 927
- 28
MiniMax-M1-80k 909
Source: Official FlagEval Arena leaderboard
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o4-mini | 1,134 1127 to 1142.6 | Apr 2025 | Official leaderboard | |
| 2 | | 1,118 1112.2 to 1124 | Jun 2025 | Official leaderboard | |
| 3 | GPT-4.1 mini | 1,107 1100.6 to 1111.8 | Apr 2025 | Official leaderboard | |
| 4 | o3 | 1,106 1097.7 to 1114 | Apr 2025 | Official leaderboard | |
| 5 | | 1,092 1080.8 to 1100.7 | Jun 2025 | Official leaderboard | |
| 6 | | 1,063 1058.8 to 1067.7 | Apr 2025 | Official leaderboard | |
| 7 | | 1,049 1038.3 to 1059.5 | Jul 2025 | Official leaderboard | |
| 8 | Claude 3.7 Sonnet | 1,043 1039.7 to 1047.6 | Feb 2025 | Official leaderboard | |
| 9 | | 1,042 1033.5 to 1049.4 | Jun 2025 | Official leaderboard | |
| 10 | Claude Sonnet 4 | 1,035 ±7.1 | May 2025 | Official leaderboard | |
| 11 | | 1,032 1023.7 to 1040.5 | Jun 2025 | Official leaderboard | |
| 12 | | 1,029 1022.7 to 1037.4 | Feb 2025 | Official leaderboard | |
| 13 | GLM-4.5 | 1,027 1015.9 to 1036.8 | Aug 2025 | Official leaderboard | |
| 14 | | 1,019 1012 to 1027.5 | Mar 2025 | Official leaderboard | |
| 15 | | 1,011 ±12.2 | Aug 2025 | Official leaderboard | |
| 16 | | 1,008 993.2 to 1019 | Aug 2025 | Official leaderboard | |
| 17 | | 1,006 996.7 to 1016.7 | Jul 2025 | Official leaderboard | |
| 18 | GPT-4.1 | 1,002 994.3 to 1009.5 | Apr 2025 | Official leaderboard | |
| 19 | | 993 981.6 to 1006.2 | May 2025 | Official leaderboard | |
| 20 | Kimi K2 Sep 2025 | 986 ±8.8 | Sep 2025 | Official leaderboard | |
| 21 | | 983 975.9 to 991.6 | Sep 2025 | Official leaderboard | |
| 22 | | 981 974.9 to 987.3 | Jan 2025 | Official leaderboard | |
| 23 | Grok 4 | 974 968.3 to 978.2 | Jul 2025 | Official leaderboard | |
| 24 | GPT-4o (2024-11-20) | 973 968.1 to 977.9 | Official leaderboard | ||
| 25 | | 961 ±6.4 | Jan 2025 | Official leaderboard | |
| 26 | | 956 945.3 to 964.7 | May 2025 | Official leaderboard | |
| 27 | | 953 ±4.1 | Dec 2024 | Official leaderboard | |
| 28 | GLM-4-plus | 945 940.7 to 950.1 | Official leaderboard | ||
| 29 | | 927 ±7 | Sep 2024 | Official leaderboard | |
| 30 | | 909 904.7 to 914.4 | Jun 2025 | Official leaderboard | |
| 31 | GLM-Zero-Preview | 876 870.9 to 880.3 | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o4-mini | 1,134 1127 to 1142.6 | Apr 2025 | Official leaderboard | |
| 2 | | 1,118 1112.2 to 1124 | Jun 2025 | Official leaderboard | |
| 3 | GPT-4.1 mini | 1,107 1100.6 to 1111.8 | Apr 2025 | Official leaderboard | |
| 4 | o3 | 1,106 1097.7 to 1114 | Apr 2025 | Official leaderboard | |
| 5 | | 1,092 1080.8 to 1100.7 | Jun 2025 | Official leaderboard | |
| 6 | | 1,063 1058.8 to 1067.7 | Apr 2025 | Official leaderboard | |
| 7 | | 1,049 1038.3 to 1059.5 | Jul 2025 | Official leaderboard | |
| 8 | Claude 3.7 Sonnet | 1,043 1039.7 to 1047.6 | Feb 2025 | Official leaderboard | |
| 9 | | 1,042 1033.5 to 1049.4 | Jun 2025 | Official leaderboard | |
| 10 | Claude Sonnet 4 | 1,035 ±7.1 | May 2025 | Official leaderboard | |
| 11 | | 1,032 1023.7 to 1040.5 | Jun 2025 | Official leaderboard | |
| 12 | | 1,029 1022.7 to 1037.4 | Feb 2025 | Official leaderboard | |
| 13 | GLM-4.5 | 1,027 1015.9 to 1036.8 | Aug 2025 | Official leaderboard | |
| 14 | | 1,019 1012 to 1027.5 | Mar 2025 | Official leaderboard | |
| 15 | | 1,011 ±12.2 | Aug 2025 | Official leaderboard | |
| 16 | | 1,008 993.2 to 1019 | Aug 2025 | Official leaderboard | |
| 17 | | 1,006 996.7 to 1016.7 | Jul 2025 | Official leaderboard | |
| 18 | GPT-4.1 | 1,002 994.3 to 1009.5 | Apr 2025 | Official leaderboard | |
| 19 | | 993 981.6 to 1006.2 | May 2025 | Official leaderboard | |
| 20 | Kimi K2 Sep 2025 | 986 ±8.8 | Sep 2025 | Official leaderboard | |
| 21 | | 983 975.9 to 991.6 | Sep 2025 | Official leaderboard | |
| 22 | | 981 974.9 to 987.3 | Jan 2025 | Official leaderboard | |
| 23 | Grok 4 | 974 968.3 to 978.2 | Jul 2025 | Official leaderboard | |
| 24 | | 961 ±6.4 | Jan 2025 | Official leaderboard | |
| 25 | | 956 945.3 to 964.7 | May 2025 | Official leaderboard | |
| 26 | | 953 ±4.1 | Dec 2024 | Official leaderboard | |
| 27 | | 927 ±7 | Sep 2024 | Official leaderboard | |
| 28 | | 909 904.7 to 914.4 | Jun 2025 | 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: Official FlagEval Arena leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| o4-mini | 1,134 | ||||
| 1,118 | |||||
| GPT-4.1 mini | 1,107 | ||||
| o3 | 1,106 | ||||
| 1,092 | |||||
| 1,063 | |||||
| 1,049 | |||||
| Claude 3.7 Sonnet | 1,043 | ||||
| 1,042 | |||||
| Claude Sonnet 4 | 1,035 | ||||
| 1,032 | |||||
| 1,029 | |||||
| GLM-4.5 | 1,027 | ||||
| 1,019 | |||||
| 1,011 | |||||
| o4-mini | high | 1,011 | |||
| 1,008 | |||||
| 1,006 | |||||
| GPT-4.1 | 1,002 | ||||
| 993 | |||||
| Kimi K2 Sep 2025 | 986 | ||||
| 983 | |||||
| 981 | |||||
| Grok 4 | 974 | ||||
| 962 | |||||
| 961 | |||||
| 956 | |||||
| thinking | 954 | ||||
| 953 | |||||
| 927 | |||||
| thinking | 914 | ||||
| 909 | |||||
| Claude 3.7 Sonnet | thinking | 821 |
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 FlagEval Arena leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| o4-mini | 1,134 | ||||
| 1,118 | |||||
| GPT-4.1 mini | 1,107 | ||||
| o3 | 1,106 | ||||
| 1,092 | |||||
| 1,063 | |||||
| 1,049 | |||||
| Claude 3.7 Sonnet | 1,043 | ||||
| 1,042 | |||||
| Claude Sonnet 4 | 1,035 | ||||
| 1,032 | |||||
| 1,029 | |||||
| GLM-4.5 | 1,027 | ||||
| 1,019 | |||||
| 1,011 | |||||
| o4-mini | high | 1,011 | |||
| 1,008 | |||||
| 1,006 | |||||
| GPT-4.1 | 1,002 | ||||
| 993 | |||||
| Kimi K2 Sep 2025 | 986 | ||||
| 983 | |||||
| 981 | |||||
| Grok 4 | 974 | ||||
| 962 | |||||
| 961 | |||||
| 956 | |||||
| thinking | 954 | ||||
| 953 | |||||
| 927 | |||||
| thinking | 914 | ||||
| 909 | |||||
| Claude 3.7 Sonnet | thinking | 821 |
7 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official FlagEval Arena 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 FlagEval Arena 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 Instructions and chat
- IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy.
Gemma 4 31B IT 98.9%
- IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose). Flint 89.2%
- MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
- Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
- AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics.
MAI-Thinking-1 85%
- MM-IFEval In use Multimodal models follow image-grounded instructions with exact output constraints. Checks mix rule-based verification and a judge model. GPT-4o 64.6%
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 Gemini 2.5 Flash. 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 official leaderboard (31 entries).
- Pass Models scored 28 models we track, plus 3 other entries on its leaderboard.
- Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is o3 (#84).
- Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on flageval.baai.ac.cn: 33 rows for models we track and 3 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.