Up to four models
GLM-5 vs o4-mini
On the index (GPT-4 = 100), GLM-5 scores 142 and o4-mini 141. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
142126–157
WeightsOpen
ReleasedFeb 2026
Price in / out$1.0 / $3.2
Context205K
Core tests taken3 of 9
GLM-5 and o4-mini are too close to call (0 points apart, within the uncertainty), ahead on 1 of 2 shared core tests.
Test by testthird-party results
Every result as a table
| Test | GLM-5 | o4-mini |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 87.8% | 79.6% |
| GPQA Diamond (Vals AI) | 83.3% | 74.5% |
| MMLU Pro | 86.0% | 80.6% |
| SimpleBench | 53.2% | 38.7% |
| Maths | ||
| AIME-style maths (OTIS mock) | 80.0% | 81.7% |
| FrontierMath (2025 set) | 16.4% | 24.8% |
| FrontierMath tier 4 (2025 set) | 2.1% | 6.3% |
| Coding | ||
| LiveCodeBench | 81.9% | 82.2% |
| WeirdML | 48.2% | 52.6% |
| Professional work | ||
| CorpFin v2 | 62.9% | 59.0% |
| LegalBench | 84.1% | 79.2% |
| TaxEval v2 | 70.0% | 74.8% |
| Novel problems | ||
| ARC-AGI-2 | 4.9% | 6.1% |
| ARC-AGI-1 | 44.7% | 58.7% |
Task length · METR38 sec
Tests at least two of these models have taken. Bold rows are the core tests.