Up to four models
Grok 4.3 Beta vs Qwen3.5
On the index (GPT-4 = 100), Grok 4.3 Beta scores 146 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.
144127–161
WeightsOpen
ReleasedFeb 2026
Price in / out$0.45 / $3.0
Context262K
Core tests taken3 of 9
Grok 4.3 Beta and Qwen3.5 are too close to call (2 points apart, within the uncertainty), ahead on 2 of 2 shared core tests.
Test by testthird-party results
Grok 4.3 Beta
Qwen3.5
Every result as a table
| Test | Grok 4.3 Beta | Qwen3.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 88.8% | 86.4% |
| Maths | ||
| FrontierMath (tiers 1-3) | 42.8% | 31.2% |
| AIME-style maths (OTIS mock) | 93.3% | 88.9% |
| Agents | ||
| DTBench | 90.7% | 87.5% |
| LMCA | 38.3% | 37.9% |
Tests at least two of these models have taken. Bold rows are the core tests.