← Models
Qwen3.7 Max
Alibaba Cloud / Qwen Team · proprietary · qwen3.7-max
Qwen3.7 Max is Alibaba Cloud Qwen Team's proprietary flagship model for agent-driven workflows. It is designed for coding agents, office automation, MCP and multi-agent orchestration, and long-horizon autonomous execution, with a 1 million token context window and up to 65,536 output tokens. Qwen reports strong agentic coding results including 69.7 on Terminal-Bench 2.0-Terminus, 80.4 on SWE-bench Verified, 60.6 on SWE-Pro, and 78.3 on SWE-Multilingual, alongside 92.4 on GPQA Diamond and 97.1 on HMMT 2026 Feb.
Benchmark scores
| Benchmark | Score |
|---|---|
| QwenSVG | 1608.00 |
| QwenWebBench | 1568.00 |
| HMMT Feb 26 | 0.97 |
| Kernel Bench L3 | 0.96 |
| MMLU-Redux | 0.95 |
| IFEval | 0.94 |
| GPQA | 0.92 |
| MMMLU | 0.90 |
| IMO-AnswerBench | 0.90 |
| MMLU-Pro | 0.90 |
| SpreadSheetBench-v1 | 0.87 |
| PolyMATH | 0.86 |
| SWE-Bench Verified | 0.80 |
| SWE-bench Multilingual | 0.78 |
| MCP Atlas | 0.76 |
| BFCL-V4 | 0.75 |
| Humanity's Last Exam | 0.41 |
Pricing
- Novita$1.25 / $3.75
- Together$2.50 / $7.50
- DeepInfra$2.50 / $7.50
Input / output per 1M tokens
AA metrics
No Artificial Analysis link yet.
Arena Elo
- No Arena snapshot linked.