Qwen3.8 Max 0902
| Released | 2026-09-02 |
|---|---|
| Price per 1M | $2.00 in · $6.00 out |
| Overall score | 59.6 · rank 33 |
| Context window | 1,000,000 tokens |
| Provider | Alibaba |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 59.6 | 33 | 12 |
| Overall: Coding | 59.7 | 30 | 8 |
| Overall: Reasoning | 60.0 | 35 | 7 |
| Overall: Agentic work | 60.1 | 32 | 7 |
| Overall: Frontend | 60.9 | 16 | 4 |
| Coding | 58.7 | 38 | 3 |
| Agents | 60.4 | 24 | 1 |
| Reasoning | 61.1 | 36 | 3 |
| Math | 61.0 | 24 | 3 |
| Knowledge | 55.8 | 54 | 1 |
| Frontend | 62.0 | 10 | 1 |
| Value vs price | +8.6 | 43 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 59.3 ±4.7 | 3 |
| Max | 60.4 ±5.1 | 1 |
| Extra High | 59.3 ±2.9 | 8 |
Evidence
Coding 58.7 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MirrorCode | 47.8% | Epoch AI | 2026-10-21 |
| FrontierSWE | 17.8% | Epoch AI | 2026-11-11 |
| SciCode | 52.1% | Epoch AI | 2026-11-11 |
Agents 60.4 ±0.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4 | 27.0% | Terminal-Bench | 2026-09-02 |
Reasoning 61.1 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 92.3% | Epoch AI | 2026-09-02 |
| CritPt | 17.7% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 37.0% | Epoch AI | 2026-10-13 |
Math 61.0 ±4.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 65.6% | Epoch AI | 2026-09-02 |
| FrontierMath Tier 4 | 34.2% | Epoch AI | 2026-09-02 |
| OTIS Mock AIME 2024-2025 | 100.0% | Epoch AI | 2026-09-02 |
Knowledge 55.8 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 47.3% | Epoch AI | 2026-09-02 |
Frontend 62.0 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena WebDev | 1,677 | LMArena | 2026-11-09 |
Names matched to this model
qwen3-8-max-0902