Qwen3.7-Max
Alibaba·
Overview
Proprietary flagship in Alibaba's Qwen Max line. Closed weights — the Plus variant is open-sourced while Max stays closed, consistent with Alibaba's Max/Plus split since Qwen2.5-Max. 1M-token context (up from 256K in the Qwen3.6-Max preview), text-only input and output. MoE architecture details are not officially disclosed. Previewed on Arena AI on 2026-05-14, formally launched at the 2026 Alibaba Cloud Summit on 2026-05-20. Alibaba-reported benchmarks (verified post-launch via AA Intelligence Index v4.0 reproduction): GPQA Diamond 92.4, HLE 41.4, SWE-bench Verified 80.4, Terminal-Bench 2.0 69.7. AA Intelligence Index v4.0: 57 (initial Index run reported 56.6).
Capabilities and innovations
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 92.4% | vendor GPQA Diamond 92.4 — Alibaba-reported, consistent with the AA Intelligence Index v4.0 composite reproduction (GPQA is an index component). |
| Humanity’s Last Exam (no tools) | 41.4% | vendor HLE 41.4 — Alibaba-reported. Caveat: high score is partly abstention-driven (~48% attempt rate per AA), the model declines more answers than peers. |
| SWE-bench Verified | 80.4% | vendor SWE-bench Verified 80.4 — Alibaba-reported. Comparable to Opus 4.6 Max (80.8) and DeepSeek-V4-Pro Max (80.6). |
| MMLU-Pro | 89.31% | unsourced |
| Terminal-Bench 2.x | 69.7% | vendor Terminal-Bench 2.0-Terminus 69.7 — Alibaba-reported. |
- SWE-bench Pro: not reported by the vendor
- MMLU: not reported by the vendor
- MMMU-Pro: not reported by the vendor
Reliability
- Function calling (BFCL)
- 75% (higher is better)third party
Links
More from Alibaba
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.