Up to four models
Claude Sonnet 4.5 vs Qwen3.5
On the index (GPT-4 = 100), Claude Sonnet 4.5 scores 144 and Qwen3.5 144. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Sonnet 4.5
144129–160
WeightsClosed
ReleasedSep 2025
Price in / out$3.0 / $15
Context1M
Core tests taken6 of 9
144127–161
WeightsOpen
ReleasedFeb 2026
Price in / out$0.45 / $3.0
Context262K
Core tests taken3 of 9
Claude Sonnet 4.5 and Qwen3.5 are too close to call (1 point apart, within the uncertainty), ahead on 0 of 2 shared core tests, at 5.5× the price.
Test by testthird-party results
Claude Sonnet 4.5
Qwen3.5
Every result as a table
| Test | Claude Sonnet 4.5 | Qwen3.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 82.3% | 86.4% |
| Maths | ||
| FrontierMath (tiers 1-3) | 23.9% | 31.2% |
| AIME-style maths (OTIS mock) | 77.8% | 88.9% |
| Agents | ||
| DTBench | 83.2% | 87.5% |
| LMCA | 38.8% | 37.9% |
| Mystery game puzzles | 17.0% | 18.0% |
Task length · METR40 sec
Tests at least two of these models have taken. Bold rows are the core tests.