Qwen3.7-Plus
- Made by
- Alibaba
- Released
- Announced in
- Qwen3.7-Plus: Multimodal Agent Intelligenceqwen.ai
- Event
- Qwen3.7-Plus
- API record
- /api/v1/models/qwen3-7-plus
Benchmark results
| Benchmark | Score | Source check |
|---|---|---|
| Humanity's Last ExamNo tools · xhigh reasoning effort; full or text-only set not stated | 34.7% | 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.CorroboratedThe same number is printed in 1 other lab document: 1 |
| SWE-bench Prointernal harness with bash and file-edit tools; 200K context · Run on the lab's own corrected version of the public set | 57.6% | 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. |
| Claude Code harness; 256K context · reported later, in Qwen3.8-Flash-Next: A New Architecture, Towards Ultimate Cost-Efficiency · Run on the lab's own corrected version of the public set | 55.8% | CorroboratedThe same number is printed in 1 other lab document: 1 |
| GPQA Diamondxhigh reasoning effort | 90.3% | 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.CorroboratedThe same number is printed in 1 other lab document: 1 |
| DeepSWE v1.1the higher of the Claude Code and mini-SWE-agent harnesses; 256K context · reported later, in Qwen3.8-Flash-Next: A New Architecture, Towards Ultimate Cost-Efficiency | 16.5% | CorroboratedThe same number is printed in 1 other lab document: 1 |
Sources
Reported by Alibaba
- Qwen3.7-Plus: Multimodal Agent Intelligenceqwen.ai · 1 Jun 2026
Our capture of the source - Qwen3.8-Flash-Next: A New Architecture, Towards Ultimate Cost-Efficiencyqwen.ai · 26 Aug 2026
Our capture of the source