Qwen3.7 Max
| Released | 2026-05-21 |
|---|---|
| Price per 1M | $1.80 in · $5.30 out |
| Overall score | 56.3 · rank 64 |
| Context window | 1,000,000 tokens |
| Provider | Alibaba |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 56.3 | 64 | 23 |
| Overall: Coding | 55.6 | 64 | 13 |
| Overall: Reasoning | 58.7 | 52 | 13 |
| Overall: Agentic work | 56.5 | 65 | 11 |
| Overall: Frontend | 53.0 | 71 | 5 |
| Coding | 55.7 | 64 | 3 |
| Agents | 56.0 | 68 | 2 |
| Reasoning | 59.8 | 48 | 6 |
| Math | 57.9 | 45 | 4 |
| Knowledge | 57.4 | 44 | 3 |
| Frontend | 51.7 | 68 | 2 |
| General | 52.5 | 84 | 3 |
| Value vs price | +5.6 | 71 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 56.3 ±1.2 | 23 |
| Non-reasoning | 57.0 ±12.0 | 1 |
Evidence
Coding 55.7 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SciCode | 49.5% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 87.1% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 77.3% | Epoch AI | 2026-06-18 |
| SWE-bench Verified (Vals run) | 68.8% | Vals AI | 2026-09-01 |
Agents 56.0 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.1 (Vals run) | 61.0% | Vals AI | 2026-10-01 |
| Tax Agent Bench | 15.8% | Vals AI | 2026-11-09 |
Reasoning 59.8 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 85.1% | Lech Mazur | 2026-11-10 |
| CritPt | 13.4% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 90.9% | Epoch AI | 2026-08-07 |
| GPQA Diamond (Vals run) | 90.2% | Vals AI | 2026-09-01 |
| Chess Puzzles | 27.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 70.4% | SimpleBench | 2026-05-22 |
| SimpleBench | 70.4% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 32.0% | Epoch AI | 2026-07-28 |
Math 57.9 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 64.6% | Epoch AI | 2026-06-13 |
| FrontierMath Tier 4 | 34.2% | Epoch AI | 2026-06-13 |
| ProofBench | 26.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 95.6% | Epoch AI | 2026-08-07 |
Knowledge 57.4 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 55.8% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 89.3% | Vals AI | 2026-09-01 |
| Legal Research Bench | 25.5% | Vals AI | 2026-11-09 |
Frontend 51.7 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 47.7% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,515 | LMArena | 2026-11-09 |
General 52.5 ±2.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench 4 | 1,100 | EQ-Bench | 2026-10-24 |
| LLM Debate Benchmark | 1,427 | Lech Mazur | 2026-10-26 |
| Creative Story-Writing (Lech Mazur) | 14.0% | Lech Mazur | 2026-10-23 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Mystery Game Puzzles | 26.0% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen-3-7-max, qwen3-7-max