Qwen 3.6 Max (Preview): benchmark scores, price and ranking
Qwen 3.6 Max (Preview) from Alibaba ranks #27 of 741 LLMs on the LLMs Tiger aggregate benchmark score (54.1), based on 12 benchmark results captured up to 2026-10-05.
- Organisation
- Alibaba
- Type
- Preview release
- Open weights
- No
- Aggregate rank
- #27 of 741 (score 54.1)
Relative to other models, Qwen 3.6 Max (Preview) is strongest on Epoch ECI (#13 of 205) and weakest on Mystery Games (#34 of 57).
Qwen 3.6 Max (Preview) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 149 | #13 of 205 | Epoch AI Benchmarking Hub | 2026-10-05 |
| SWE-bench Verified | 76.7% | #5 of 73 | Epoch AI Benchmarking Hub | 2026-10-05 |
| SimpleBench | 63.0% | #6 of 64 | Epoch AI Benchmarking Hub | 2026-10-05 |
| GPQA Diamond | 87.4% | #57 of 274 | Epoch AI Benchmarking Hub | 2026-10-05 |
| OTIS Mock AIME | 91.1% | #40 of 188 | Epoch AI Benchmarking Hub | 2026-10-05 |
| SimpleQA Verified | 52.0% | #15 of 66 | Epoch AI Benchmarking Hub | 2026-10-05 |
| LMCA | 42.5% | #27 of 111 | Epoch AI Benchmarking Hub | 2026-10-05 |
| DTBench | 87.2% | #37 of 149 | Epoch AI Benchmarking Hub | 2026-10-05 |
| WebDev Arena | 1,479 | #21 of 63 | Epoch AI Benchmarking Hub | 2026-10-05 |
| Chess Puzzles | 20.0% | #50 of 124 | Epoch AI Benchmarking Hub | 2026-10-05 |
| Vending-Bench 2 | $4,254 | #9 of 19 | Epoch AI Benchmarking Hub | 2026-10-05 |
| Mystery Games | 19.0% | #34 of 57 | Epoch AI Benchmarking Hub | 2026-10-05 |
Models ranked nearby
- #24 Claude 3.5-Sonnet-20241022 (54.4)
- #25 DeepSeek V4 Pro 0813 (max) (54.3)
- #26 GPT-5.3 Codex (xhigh) (54.2)
- #28 GPT-6 Astra (pro, max) (54.0)
- #29 Gemini 3.7 Flash (high) (53.9)
- #30 Gemini 3 Pro Preview (53.9)
Compare it on the live leaderboard → · How the aggregate score works