Up to four models
GPT-5.2 vs Qwen3.8 Max (0902)
On the index (GPT-4 = 100), GPT-5.2 scores 162 and Qwen3.8 Max (0902) 161. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.2
162146–178
WeightsClosed
ReleasedDec 2025
Price in / out$1.75 / $14
Context400K
Core tests taken6 of 9
161144–178
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $6.0
Context1M
Core tests taken2 of 9
GPT-5.2 and Qwen3.8 Max (0902) are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests, at 1.6× the price.
Test by testthird-party results
GPT-5.2
Qwen3.8 Max (0902)
Every result as a table
| Test | GPT-5.2 | Qwen3.8 Max (0902) |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 91.4% | 92.3% |
| SimpleQA Verified | 37.1% | 47.3% |
| Maths | ||
| FrontierMath (tiers 1-3) | 67.4% | 65.6% |
| AIME-style maths (OTIS mock) | 96.1% | 100.0% |
| Chess puzzles | 48.0% | 37.0% |
| FrontierMath (tier 4) | 31.7% | 34.2% |
| Coding | ||
| MirrorCode | 32.2% | 47.8% |
| Agents | ||
| Furniture assembly | 38.3% | 20.0% |
Task length · METR45 sec
Tests at least two of these models have taken. Bold rows are the core tests.