Up to four models
GLM-4.5 vs Grok-3 mini
On the index (GPT-4 = 100), GLM-4.5 scores 132 and Grok-3 mini 131. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
132113–150
WeightsOpen
ReleasedJul 2025
Price in / out$0.60 / $2.2
Context131K
Core tests taken1 of 9
GLM-4.5 and Grok-3 mini are too close to call (1 point apart, within the uncertainty).
Test by testthird-party results
Every result as a table
| Test | GLM-4.5 | Grok-3 mini |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 72.2% | 79.3% |
| MMLU Pro | 81.2% | 81.4% |
| Maths | ||
| MATH 500 | 94.0% | 94.2% |
| MGSM | 90.8% | 90.4% |
| Coding | ||
| LiveCodeBench | 67.5% | 76.2% |
| WeirdML | 40.6% | 42.6% |
| Professional work | ||
| CorpFin v2 | 61.0% | 61.1% |
| LegalBench | 75.6% | 83.1% |
| TaxEval v2 | 72.4% | 73.0% |
Tests at least two of these models have taken. Bold rows are the core tests.