Up to four models
Grok 4.6 vs Qwen3.8-Max
On the index (GPT-4 = 100), Grok 4.6 scores 167 and Qwen3.8-Max 167. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Grok 4.6
167151–183
WeightsClosed
ReleasedAug 2026
Price in / out$2.0 / $6.0
Context500K
Core tests taken6 of 9
Grok 4.6 and Qwen3.8-Max are too close to call (0 points apart, within the uncertainty), ahead on 2 of 3 shared core tests.
Test by testthird-party results
Grok 4.6
Qwen3.8-Max
Every result as a table
| Test | Grok 4.6 | Qwen3.8-Max |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 94.0% | 92.7% |
| SimpleQA Verified | 49.3% | 45.8% |
| Maths | ||
| FrontierMath (tiers 1-3) | 66.0% | 74.7% |
| AIME-style maths (OTIS mock) | 99.2% | 99.4% |
| Chess puzzles | 33.0% | 46.0% |
| FrontierMath (tier 4) | 31.7% | 46.3% |
| Coding | ||
| DeepSWE | 67.5% | 57.5% |
| FrontierSWE | 25.3% | 15.8% |
| MirrorCode | 41.1% | 52.2% |
| Agents | ||
| APEX-Agents | 65.3% | 63.3% |
| DTBench | 97.3% | 92.0% |
| LMCA | 48.4% | 46.2% |
| Mystery game puzzles | 34.0% | 38.0% |
Tests at least two of these models have taken. Bold rows are the core tests.