Qwen3.5 Plus
| Released | 2026-02-16 |
|---|---|
| Price per 1M | $0.40 in · $2.40 out |
| Overall score | 45.0 · rank 157 |
| Context window | 1,000,000 tokens |
| Provider | Alibaba |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 45.0 | 157 | 13 |
| Overall: Coding | 47.8 | 123 | 7 |
| Overall: Reasoning | 51.1 | 103 | 8 |
| Overall: Agentic work | 39.7 | 188 | 6 |
| Overall: Frontend | 44.2 | 145 | 4 |
| Coding | 54.3 | 82 | 2 |
| Agents | 30.6 | 183 | 1 |
| Reasoning | 51.4 | 106 | 3 |
| Math | 51.7 | 97 | 3 |
| Knowledge | 49.7 | 94 | 2 |
| Frontend | 44.0 | 96 | 1 |
| Multimodal | 14.7 | 121 | 1 |
| Value vs price | −2.5 | 145 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 43.0 ±4.2 | 8 |
| Non-reasoning | 52.3 ±12.0 | 1 |
| Thinking | 50.8 ±3.2 | 6 |
Evidence
Coding 54.3 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 71.2% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 85.3% | Vals AI | 2026-09-01 |
Agents 30.6 ±7.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vending-Bench 2 | $1 | Epoch AI | 2026-11-11 |
Reasoning 51.4 ±6.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Chess Puzzles | 9.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 17.0% | Epoch AI | 2026-08-27 |
| GPQA Diamond | 84.9% | Epoch AI | 2026-08-07 |
| GPQA Diamond (Vals run) | 87.4% | Vals AI | 2026-09-01 |
Math 51.7 ±2.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 21.0% | Epoch AI | 2026-05-14 |
| FrontierMath Tier 4 (2025 set) | 2.1% | Epoch AI | 2026-05-15 |
| OTIS Mock AIME 2024-2025 | 86.7% | Epoch AI | 2026-08-07 |
Knowledge 49.7 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 25.4% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 87.2% | Vals AI | 2026-09-01 |
Frontend 44.0 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 15.7% | Vals AI | 2026-11-09 |
Multimodal 14.7 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 22.8% | Vals AI | 2026-09-01 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Mystery Game Puzzles | 16.0% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen3-5-plus