| Benchmark | Score | Δ vs prior | Rank (current) | Configuration | Source |
|---|---|---|---|---|---|
GPQA Diamond | 91.7% | #5 of 10 | leaderboard | benchlm.ai ↗ | |
Humanity's Last Exam | 35.9% | #11 of 14 | leaderboard | benchlm.ai ↗ |
| Version | Released | $ in / out | Terminal-Bench | SWE-bench | GPQA | HLE | AIME | τ²-bench |
|---|---|---|---|---|---|---|---|---|
| Qwen3.5 397B-A17B | — | — | 76.2% | — | 28.7% | 93.3% | 83.9% | |
| Qwen3.6 Plus | — | 53.2% | 78.8% | — | 28.8% | 95.3% | 97.7% | |
| Qwen3.6 27B | — | — | 77.2% | — | 24% | 94.1% | 94.2% | |
| Qwen3.7 Max | $2.5 / $7.5 | 61% | 80.4% | 92.4% | 41.4% | — | 94.7% | |
| Qwen3.7 Plus | — | 52.8% | 77.7% | 90.3% | 34.7% | — | 93% | |
| Qwen3.8 Max | $2 / $6 | 67.4% | — | 92.6% | 43.6% | — | — | |
| Qwen3.8 27B | — | 58.4% | — | 89.2% | 30.8% | — | — | |
| Qwen3.8 Flash-Next | — | — | — | 91.7% | 35.9% | — | — |