Up to four models
GLM-5.1 vs GLM-5
On the index (GPT-4 = 100), GLM-5.1 scores 151 and GLM-5 142. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
151134–167
WeightsOpen
ReleasedApr 2026
Price in / out$1.4 / $4.4
Context205K
Core tests taken5 of 9
142126–157
WeightsOpen
ReleasedFeb 2026
Price in / out$1.0 / $3.2
Context205K
Core tests taken3 of 9
GLM-5.1 leads GLM-5 by 9 points, ahead on 2 of 2 shared core tests, at 1.4× the price.
Test by testthird-party results
Every result as a table
| Test | GLM-5.1 | GLM-5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 89.9% | 87.8% |
| GPQA Diamond (Vals AI) | 84.5% | 83.3% |
| MMLU Pro | 86.9% | 86.0% |
| SimpleBench | 55.1% | 53.2% |
| Maths | ||
| AIME-style maths (OTIS mock) | 93.3% | 80.0% |
| FrontierMath (2025 set) | 33.5% | 16.4% |
| FrontierMath tier 4 (2025 set) | 12.5% | 2.1% |
| Coding | ||
| SWE-bench Verified | 74.2% | 72.1% |
| LiveCodeBench | 81.4% | 81.9% |
| SWE-bench | 76.4% | 71.4% |
| Vibe Code Bench v1.1 | 31.5% | 23.4% |
| WeirdML | 57.1% | 48.2% |
| Professional work | ||
| CorpFin v2 | 64.5% | 62.9% |
| LegalBench | 84.4% | 84.1% |
| TaxEval v2 | 71.2% | 70.0% |
Tests at least two of these models have taken. Bold rows are the core tests.