Up to four models
Qwen3.8 Max (0902) vs Grok 4.5
On the index (GPT-4 = 100), Qwen3.8 Max (0902) scores 161 and Grok 4.5 161. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
161144–178
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $6.0
Context1M
Core tests taken2 of 9
Grok 4.5
161145–177
WeightsClosed
ReleasedJul 2026
Price in / out$2.0 / $6.0
Context500K
Core tests taken6 of 9
Qwen3.8 Max (0902) and Grok 4.5 are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests, at a similar price.
Test by testthird-party results
Every result as a table
| Test | Qwen3.8 Max (0902) | Grok 4.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 92.3% | 93.4% |
| SimpleQA Verified | 47.3% | 48.3% |
| Maths | ||
| FrontierMath (tiers 1-3) | 65.6% | 57.2% |
| AIME-style maths (OTIS mock) | 100.0% | 97.8% |
| Chess puzzles | 37.0% | 35.0% |
| FrontierMath (tier 4) | 34.2% | 24.4% |
| Coding | ||
| MirrorCode | 47.8% | 32.2% |
| Agents | ||
| Furniture assembly | 20.0% | 22.5% |
Tests at least two of these models have taken. Bold rows are the core tests.