Qwen3.5 397B-A17B
| Released | 2026-02-15 |
|---|---|
| Price per 1M | $0.60 in · $3.60 out |
| Overall score | 51.6 · rank 101 |
| Context window | 262,144 tokens |
| Provider | Alibaba |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 51.6 | 101 | 17 |
| Overall: Coding | 49.1 | 116 | 10 |
| Overall: Reasoning | 52.1 | 98 | 6 |
| Overall: Agentic work | 51.8 | 103 | 9 |
| Overall: Frontend | 45.3 | 133 | 2 |
| Agents | 51.7 | 97 | 5 |
| Reasoning | 51.9 | 102 | 4 |
| Math | 52.3 | 94 | 2 |
| Frontend | 43.7 | 100 | 1 |
| General | 52.6 | 83 | 4 |
| Multimodal | 54.9 | 52 | 1 |
| Value vs price | +2.9 | 96 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 52.2 ±2.8 | 15 |
| Non-reasoning | 51.2 ±5.9 | 5 |
Evidence
Agents 51.7 ±5.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| APEX-Agents | 24.9% | Epoch AI | 2026-11-11 |
| tau2-bench Banking Knowledge | 9.8% | tau2-bench | 2026-02-27 |
| tau2-bench Airline | 81.5% | tau2-bench | 2026-02-27 |
| tau2-bench Telecom | 97.8% | tau2-bench | 2026-02-27 |
| tau2-bench Retail | 84.4% | tau2-bench | 2026-02-27 |
Reasoning 51.9 ±5.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 58.9% | Lech Mazur | 2026-11-10 |
| GPQA Diamond | 86.4% | Epoch AI | 2026-08-07 |
| CritPt | 0.9% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 18.0% | Epoch AI | 2026-08-27 |
Math 52.3 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 31.2% | Epoch AI | 2026-08-30 |
| OTIS Mock AIME 2024-2025 | 88.9% | Epoch AI | 2026-08-07 |
Frontend 43.7 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena WebDev | 1,400 | LMArena | 2026-11-10 |
General 52.6 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,382 | Lech Mazur | 2026-10-26 |
| EQ-Bench Creative Writing v3 | 1,478 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,441 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 68.3% | EQ-Bench | 2026-11-11 |
Multimodal 54.9 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,246 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 29.5% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 85.9% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 82.2% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen3-5-397b-a17b