- MMLU-Redux 92.7
- GPQA-Diamond 71.1
- C-Eval 89.6
- LiveBench 2024-11-25 77.1
- IFEval strict prompt 83.4
- Arena-Hard 95.6
- AlignBench v1.1 8.94
- Creative Writing v3 84.6
- WritingBench 8.03
- MATH-500 98
- AIME’24 85.7
- AIME’25 81.5
- ZebraLogic 80.3
- AutoLogi 89
- BFCL v3 70.8
- LiveCodeBench v5 70.7
- CodeForces (Rating / Percentile) 2056
- Multi-IF 71.9
- INCLUDE 78.7
- MMMLU 14 languages 84.3
- MT-AIME2024 80.8
- PolyMath 54.7
- MLogiQA 77.1
- Aider (Pass@2)
Qwen3-235B-A22B
Qwen3-235B-A22B ranks first on 3 of the 78 benchmarks it has scores on.
78
Benchmarks with a score
3
Ranked first, out of five or more models
4
In the top three
Qwen Apr 2025 Qwen3-235B-A22B
Open weights Flagship
139.1
#130 of 271
Epoch Capabilities Index
- SWE-Bench Pro 21.4% #18 /24
- MultiChallenge 41.2% #33 /35
- GPQA Diamond 70.7% #108 /219
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Arena-Hard-Auto | 95.6% | #2 of 39 | Model card | |
| AlignBench | 8.94 | #1 of 15 | Model card | |
| MLogiQA | 77.1% | #1 of 8 | Model card | |
| MT-AIME2024 | 80.8% | #1 of 7 | Model card | |
| RULER | 95% | #7 of 38 | Model card | |
| Lech Mazur Creative Writing | 8.30 | #10 of 44 | Epoch AI | |
| Creative Writing v3 | 84.6 | #4 of 12 | Model card | |
| Arena-Hard v2.0 | 58.4% | #8 of 23 | Official leaderboard | |
| Fiction.LiveBench | 67.7% | #20 of 57 | Epoch AI | |
| WritingBench | 74.7 | #17 of 45 | Official leaderboard | |
| LMArena (Elo) | 1,402 | #126 of 333 | Official leaderboard | |
| SuperGPQA | 49.4% | #22 of 58 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 15822.0 | #30 of 76 | Official leaderboard | |
| MMLU-Redux | 92.7% | #15 of 38 | Model card | |
| LLM Confabulation Leaderboard | 15.6% | #24 of 58 | Official leaderboard | |
| LongBench v2 | 50.1% | #14 of 33 | Official leaderboard | |
| MMLU-Pro | 68.2% | #91 of 212 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 9.30% | #48 of 104 | Official leaderboard | |
| C-Eval | 89.6% | #18 of 38 | Model card | |
| EQ-Bench 3 | 1,267 | #40 of 78 | Official leaderboard | |
| INCLUDE | 78.7% | #13 of 25 | Model card | |
| Multi-IF | 71.9% | #15 of 28 | Model card | |
| MMMLU | 84.3% | #34 of 62 | Model card | |
| IFEval | 83.4% | #85 of 126 | Model card | |
| Judgemark v2.1 | 56.2 | #34 of 42 | Official leaderboard | |
| MultiNRC | 17.6% | #32 of 38 | Official leaderboard | |
| BullshitBench V2 | 6.00% | #115 of 122 | Official leaderboard | |
| MultiChallenge | 41.2% | #33 of 35 | Official leaderboard | |
| BullshitBench | 7.27% | #102 of 107 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH-500 | 98% | #7 of 67 | Model card | |
| AIME 2024 | 85.7% | #31 of 87 | Model card | |
| MATH Level 5 | 68.9% | #35 of 94 | Epoch AI | |
| Misguided Attention | 49% | #19 of 45 | Official leaderboard | |
| HiPhO | 57.9% | #15 of 35 | Official leaderboard | |
| PHYBench | 28.7% | #12 of 28 | Official leaderboard | |
| GPQA Diamond | 70.7% | #108 of 219 | Epoch AI | |
| AutoLogi | 89% | #4 of 8 | Model card | |
| ForecastBench | 63.0 | #45 of 86 | Official leaderboard | |
| DTBench | 59.5% | #102 of 178 | Official leaderboard | |
| AIME 2025 | 81.5% | #86 of 143 | Model card | |
| PolyMath | 54.7% | #11 of 18 | Model card | |
| HMMT 2025 | 62.5% | #36 of 53 | Official leaderboard | |
| BRUMO 2025 | 86.7% | #29 of 42 | Official leaderboard | |
| ZebraLogic | 80.3% | #16 of 23 | Model card | |
| SimpleBench | 31% | #76 of 100 | Official leaderboard | |
| SMT 2025 | 76.9% | #33 of 40 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench v5 | 70.7% | #10 of 44 | Model card | |
| Aider Polyglot | 59.6% | #17 of 54 | Epoch AI | |
| AutoCodeBench | 45.9% | #13 of 34 | Official leaderboard | |
| LiveCodeBench v6 | 65.9% | #11 of 21 | Official leaderboard | |
| Codeforces rating | 2,056 | #23 of 41 | Model card | |
| LiveSQLBench | 22.2% | #23 of 36 | Official leaderboard | |
| SWE-Bench Pro | 21.4% | #18 of 24 | Official leaderboard | |
| WeirdML | 37.3% | #88 of 112 | Official leaderboard | |
| ArtifactsBench | 41.1% | #17 of 20 | Official leaderboard | |
| IOI (Vals) | 0% | #55 of 55 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Step Race | 3 | #22 of 59 | Official leaderboard | |
| Berkeley Function Calling Leaderboard (BFCL) | 70.8% | #19 of 47 | Model card | |
| ITBench | 46% | #7 of 13 | Official leaderboard | |
| Elimination Game | 4 | #38 of 56 | Official leaderboard | |
| SnakeBench | 20 | #125 of 183 | Official leaderboard | |
| Meta Agents Research Environments (ARE) / Gaia2 | 11.6% | #10 of 13 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LEXam | 47.3% | #16 of 31 | Official leaderboard | |
| LegalBench | 80.2% | #86 of 138 | Official leaderboard | |
| TaxEval v2 | 70.7% | #83 of 129 | Official leaderboard | |
| EnterpriseClawBench | 27% | #9 of 9 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BaxBench | 32.6% | #15 of 34 | Official leaderboard | |
| Anthropic Red Team | 99% | #38 of 75 | Official leaderboard | |
| SimpleSafetyTests | 98.5% | #44 of 75 | Official leaderboard | |
| HELM Safety | 90.0 | #48 of 75 | Official leaderboard | |
| AIR-Bench 2024 | 56% | #58 of 82 | Official leaderboard | |
| FORTRESS | 61.4% | #63 of 66 | Official leaderboard | |
| CyberGym | 1.86% | #32 of 33 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveBench | 77.1% | #4 of 27 | Model card | |
| HELM Capabilities | 72.6 | #17 of 60 | Official leaderboard | |
| LMCA | 25% | #95 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 36.3 | #105 of 149 | Official leaderboard | |
| ACCoRD | 46.8 | #116 of 150 | Official leaderboard |
Qwen's models over time
Qwen's models in color, against every other model on the Epoch Capabilities Index, by release date.
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 1 of them isn't in the launch post.
Qwen3 Technical Report (arXiv 2505.09388) 14 May 2025
Capabilities
- MMLU-Redux 92.7
- GPQA Diamond 71.1
- C-Eval 89.6
- LiveBench 77.1
- IFEval 83.4
- Arena-Hard-Auto 95.6
- AlignBench 8.94
- Creative Writing v3 84.6
- WritingBench 8.03
- MATH-500 98
- AIME 2024 85.7
- AIME 2025 81.5
- ZebraLogic 80.3
- AutoLogi 89
- Berkeley Function Calling Leaderboard (BFCL) 70.8
- LiveCodeBench v5 70.7
- Codeforces rating 2056
- Multi-IF 71.9
- INCLUDE 78.7
- MMMLU 84.3
- MT-AIME2024 80.8
- PolyMath 54.7
- MLogiQA 77.1
- RULER 95