- SuperGPQA Graduate-Level Knowledge 73.9
- AA-Omniscience Index Knowledge Reliability and Hallucination 10
- GDPval-AA Real-World Valuable Task (51.0, scale not stated) 51
- QwenChineseBench Chinese Real-World Knowledge 84
- QwenClawBench Real-World Agent 59
- SkillsBench Agent Skills 55.6
- ToolcallFormatIFBench Real-World Toolcall Following 86.1
- QwenWebBench (Elo Rating) Artifacts 1532
- SciCode Research Coding 47
- NL2Repo Long-Horizon Coding 42.9
- Terminal-Bench 2.0 (Terminus-2) Agentic Terminal Coding 65.4
- SWE-bench Pro Agentic Coding 57.3
Qwen 3.6 Max (Preview)
Qwen 3.6 Max (Preview) ranks first on SuperGPQA.
Qwen Released 20 Apr 2026 33
Benchmarks with a score
1
Ranked first, out of five or more models
2
In the top three
Qwen Apr 2026 Qwen 3.6 Max (Preview)
149.4
#66 of 271
Epoch Capabilities Index
- SWE-bench Verified 76.7% #11 /32
- SciCode 47% #17 /47
- NL2Repo-Bench 42.9% #17 /28
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 | |
|---|---|---|---|---|
| SuperGPQA | 73.9% | #1 of 26 | Model card | |
| LMArena (Elo) | 1,460 | #49 of 333 | Official leaderboard | |
| SimpleQA Verified | 52% | #25 of 84 | Epoch AI | |
| Extended NYT Connections | 74.1% | #50 of 97 | Official leaderboard | |
| Judgemark v4 | 45.1 | #29 of 40 | Official leaderboard | |
| QwenChineseBench | 84% | #1 of 1 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SimpleBench | 63% | #27 of 100 | Official leaderboard | |
| OTIS Mock AIME 2024-2025 | 91.1% | #57 of 202 | Epoch AI | |
| GPQA Diamond | 87.4% | #62 of 219 | Epoch AI | |
| DTBench | 78.7% | #64 of 178 | Official leaderboard | |
| FrontierMath | 23.1% | #26 of 70 | Epoch AI | |
| FrontierMath Tier 4 | 4.17% | #35 of 55 | Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| QwenWebBench | 1,532 | #1 of 4 | Model card | |
| SWE-bench Verified | 76.7% | #11 of 32 | Epoch AI | |
| SciCode | 47% | #17 of 47 | Model card | |
| LiveSQLBench | 26.5% | #15 of 36 | Official leaderboard | |
| WebDev Arena | 1,479 | #48 of 105 | Epoch AI | |
| SWE-Bench Pro | 57.3% | #36 of 77 | Model card | |
| Code Arena | 1,482 | #60 of 124 | Official leaderboard | |
| NL2Repo-Bench | 42.9% | #17 of 28 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 31 | #32 of 183 | Official leaderboard | |
| Terminal-Bench 2.0 | 65.4% | #15 of 61 | Model card | |
| SkillsBench | 55.6% | #6 of 13 | Model card | |
| QwenClawBench | 59% | #3 of 6 | Model card | |
| Mystery Game Puzzles | 19% | #48 of 80 | Epoch AI | |
| ToolcallFormatIFBench | 86.1% | #1 of 1 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CorpFin v2 | 66.5% | #19 of 119 | Official leaderboard | |
| Vals Finance Agent | 52.8% | #22 of 49 | Official leaderboard | |
| Vending-Bench 2 | $4,254 | #39 of 66 | Official leaderboard | |
| CaseLaw v2 | 47.9% | #51 of 53 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ACCoRD | 70.8 | #47 of 150 | Official leaderboard | |
| LMCA | 42.5% | #46 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 55.4 | #52 of 149 | 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.