Qwen3.8 Max (0902)
Qwen3.8 Max (0902) ranks first on SuperCLUE.
Qwen Released 1 Sep 2026 31
Benchmarks with a score
1
Ranked first, out of five or more models
3
In the top three
Qwen Sep 2026 Qwen3.8 Max (0902)
Closed weights
156.2
#32 of 271
Epoch Capabilities Index
- Terminal-Bench 4.0 27% #13 /23
- CritPt 17.7% #39 /160
- Vals Finance Agent v2 57.9% #12 /80
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 | |
|---|---|---|---|---|
| SimpleQA Verified | 47.3% | #34 of 84 | Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | #6 of 202 | Epoch AI | |
| GPQA Diamond | 92.3% | #26 of 219 | Epoch AI | |
| NatureBench | 17.8% | #3 of 18 | Official leaderboard | |
| CritPt | 17.7% | #39 of 160 | Epoch AI | |
| FrontierMath Tiers 1-3 v2 | 65.6% | #37 of 89 | Epoch AI | |
| FrontierMath Tier 4 v2 | 34.1% | #30 of 71 | Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Code Arena | 1,676 | #12 of 124 | Official leaderboard | |
| Image-to-WebDev Arena | 1,637 | #9 of 55 | Official leaderboard | |
| Vibe Code Bench 1-100 | 24.8% | #7 of 26 | Official leaderboard | |
| Vibe Code Bench | 77.1% | #35 of 115 | Official leaderboard | |
| Code Migration v1.1 | 57.2% | #10 of 29 | Official leaderboard | |
| RSI-Exam | 39.2% | #8 of 18 | Official leaderboard | |
| MirrorCode | 47.8% | #13 of 28 | Epoch AI | |
| FrontierSWE | 17.8% | #18 of 21 | Epoch AI |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Chess Puzzles | 37% | #40 of 83 | Epoch AI | |
| RecreationBench | 34.8% | #5 of 10 | Official leaderboard | |
| Terminal-Bench 4.0 | 27% | #13 of 23 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Tax Agent Bench | 49.7% | #2 of 79 | Official leaderboard | |
| Excel Modeling Benchmark | 72% | #9 of 76 | Official leaderboard | |
| Vals Finance Agent v2 | 57.9% | #12 of 80 | Official leaderboard | |
| Vals Finance Index | 61.7% | #6 of 35 | Official leaderboard | |
| Vals Legal Index | 73.9% | #6 of 33 | Official leaderboard | |
| Legal Research Bench | 46.1% | #18 of 88 | Official leaderboard | |
| Harvey LAB v1.1 (HLAB-Vals-1.1) | 15.4% | #9 of 33 | Official leaderboard | |
| Excel Modeling Benchmark v1.1 | 72% | #11 of 37 | Official leaderboard | |
| Vals Index v2.2 | 59% | #13 of 32 | Official leaderboard | |
| Vals Finance Agent v2.1 | 58.8% | #25 of 35 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScienceVision | 0.38 | #6 of 11 | Official leaderboard | |
| Furniture Assembly Benchmark | 20% | #35 of 35 | Epoch AI |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SuperCLUE | 72.6 | #1 of 18 | Official leaderboard |
Qwen's models over time
Qwen's models in color, against every other model on the Epoch Capabilities Index, by release date.