Qwen3.6-Plus
- Made by
- Alibaba
- Released
- Announced in
- Qwen3.6-Plus: Towards Real World Agentsqwen.ai
- Event
- Qwen3.6-Plus
- API record
- /api/v1/models/qwen3-6-plus
Benchmark results
| Benchmark | Score | Source check |
|---|---|---|
| Humanity's Last ExamNo tools | 28.8% | 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. |
| Humanity's Last ExamWith tools · 256K context with context folding | 50.6% | 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 |
| reported later, in Qwen3.7: The Agent Frontier | 50.2% | 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. |
| SWE-bench Verifiedinternal harness with bash and file-edit tools; 200K context | 78.8% | 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. |
| SWE-bench Prointernal harness with bash and file-edit tools; 200K context · Run on the lab's own corrected version of the public set | 56.6% | 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 |
| GPQA Diamond | 90.4% | 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 |
| Terminal-Bench 2.0Terminus 2 harness on Harbor; 3h timeout; 256K context; average of 5 runs | 61.6% | 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 |
| OSWorld-Verified | 62.5% | 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. |
| MMLU-Pro | 88.5% | 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. |
| HMMT February 2025No tools | 96.7% | 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. |
| LiveCodeBenchLiveCodeBench v6 | 87.1% | 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. |
| MCP Atlaspublic set; Gemini 2.5 Pro judge | 74.1% | 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 |
Sources
Reported by Alibaba
- Qwen3.6-Plus: Towards Real World Agentsqwen.ai · 2 Apr 2026
Our capture of the source 
Our capture of the source - Qwen3.7: The Agent Frontierqwen.ai · 20 May 2026
Our capture of the source