Qwen3.6 Max Preview
| Released | 2026-04-20 |
|---|---|
| Price per 1M | $1.31 in · $7.88 out |
| Overall score | 55.7 · rank 69 |
| Context window | 262,144 tokens |
| Provider | Alibaba |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 55.7 | 69 | 14 |
| Overall: Coding | 54.8 | 72 | 7 |
| Overall: Reasoning | 55.6 | 70 | 8 |
| Overall: Agentic work | 57.1 | 59 | 6 |
| Overall: Frontend | 50.9 | 82 | 2 |
| Coding | 54.8 | 78 | 1 |
| Agents | 58.2 | 51 | 1 |
| Reasoning | 56.6 | 72 | 4 |
| Math | 53.4 | 84 | 3 |
| Knowledge | 57.3 | 46 | 1 |
| Frontend | 49.0 | 77 | 1 |
| General | 56.0 | 59 | 3 |
| Value vs price | +4.7 | 79 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 55.8 ±2.0 | 13 |
| Non-reasoning | 53.4 ±12.0 | 1 |
Evidence
Coding 54.8 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Epoch run) | 76.7% | Epoch AI | 2026-05-28 |
| SWE-bench Verified (Vals run) | 72.8% | Vals AI | 2026-09-01 |
Agents 58.2 ±7.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vending-Bench 2 | $4,254 | Epoch AI | 2026-11-11 |
Reasoning 56.6 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 87.4% | Epoch AI | 2026-08-07 |
| Extended NYT Connections | 74.1% | Lech Mazur | 2026-11-10 |
| SimpleBench | 63.0% | SimpleBench | 2026-05-20 |
| SimpleBench | 63.0% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 19.0% | Epoch AI | 2026-08-27 |
Math 53.4 ±2.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 23.1% | Epoch AI | 2026-05-27 |
| FrontierMath Tier 4 (2025 set) | 4.2% | Epoch AI | 2026-05-28 |
| OTIS Mock AIME 2024-2025 | 91.1% | Epoch AI | 2026-08-07 |
Knowledge 57.3 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 52.0% | Epoch AI | 2026-08-27 |
Frontend 49.0 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena WebDev | 1,482 | LMArena | 2026-11-09 |
General 56.0 ±2.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,460 | LMArena | 2026-11-09 |
| LLM Debate Benchmark | 1,467 | Lech Mazur | 2026-10-26 |
| Creative Story-Writing (Lech Mazur) | 35.0% | Lech Mazur | 2026-10-23 |
Names matched to this model
qwen-3-6-max-preview, qwen3-6-max-preview