Qwen3.8-Max
- Made by
- Alibaba
- Released
- Announced in
- Qwen3.8-Max: A New Bar for Coding and Coworkqwen.ai
- Event
- Qwen3.8-Max
- API record
- /api/v1/models/qwen3-8-max
Benchmark results
| Benchmark | Score | Source check |
|---|---|---|
| Humanity's Last ExamNo tools · full or text-only set not stated | 43.6% | CheckedA person checked this number against its source on 17 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| Humanity's Last ExamWith tools · tools not stated | 56.2% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.CorroboratedThe same number is printed in 1 other lab document: 1 |
| SWE-bench ProClaude Code harness · Run on the lab's own corrected version of the public set | 67.7% | CheckedA person checked this number against its source on 17 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| GPQA Diamond | 92.6% | CheckedA person checked this number against its source on 17 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| AutomationBench600-task public subset; pass@1 | 27.3% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| OSWorld 2.0Offline set, partial score · partial score (19.4 binary) | 46.7% | CheckedA person checked this number against its source on 18 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| DeepSWE v1.1Claude Code harness, the higher of it and mini-SWE-agent | 56.6% | CheckedA person checked this number against its source on 17 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.CorroboratedThe same number is printed in 1 other lab document: 1 |
| Terminal-Bench 2.1Claude Code harness; average of 10 runs; 5h timeout | 86.6% | CheckedA person checked this number against its source on 18 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.CorroboratedThe same number is printed in 1 other lab document: 1 |
| OSWorld-Verified | 86.1% | CheckedA person checked this number against its source on 18 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
Sources
Reported by Alibaba
- Qwen3.8-Max: A New Bar for Coding and Coworkqwen.ai · 3 Aug 2026
Our capture of the source 
Our capture of the source