Up to four models
GLM-5.2 vs Mistral Large 4
On the index (GPT-4 = 100), GLM-5.2 scores 154 and Mistral Large 4 148. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
154138–169
WeightsOpen
ReleasedJun 2026
Price in / out$0.0070 / $6.8
Context1.05M
Core tests taken6 of 9
148132–165
WeightsOpen
ReleasedOct 2026
Price in / out$0.70 / $2.1
Context1.05M
Core tests taken3 of 9
GLM-5.2 and Mistral Large 4 are too close to call (6 points apart, within the uncertainty), ahead on 2 of 3 shared core tests, at 1.6× the price.
Test by testthird-party results
Every result as a table
| Test | GLM-5.2 | Mistral Large 4 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 91.9% | 88.1% |
| SimpleQA Verified | 34.2% | 20.0% |
| Maths | ||
| FrontierMath (tiers 1-3) | 59.2% | 58.6% |
| AIME-style maths (OTIS mock) | 86.4% | 98.3% |
| Chess puzzles | 22.0% | 33.0% |
| FrontierMath (tier 4) | 29.3% | 26.8% |
| Surface Evolver Bench | 55.6% | 28.1% |
| Coding | ||
| MirrorCode | 36.7% | 40.0% |
| Agents | ||
| APEX-Agents | 45.2% | 51.6% |
| DTBench | 93.6% | 88.2% |
| LMCA | 45.8% | 35.8% |
| Mystery game puzzles | 19.0% | 17.0% |
Tests at least two of these models have taken. Bold rows are the core tests.