Up to four models
GPT-5.4 vs GLM-5
On the index (GPT-4 = 100), GPT-5.4 scores 166 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.
GPT-5.4
166150–182
WeightsClosed
ReleasedMar 2026
Price in / out$2.5 / $15
Context1.05M
Core tests taken7 of 9
142126–157
WeightsOpen
ReleasedFeb 2026
Price in / out$1.0 / $3.2
Context205K
Core tests taken3 of 9
GPT-5.4 leads GLM-5 by 24 points, ahead on 3 of 3 shared core tests, at 3.6× the price.
Test by testthird-party results
GPT-5.4
GLM-5
Every result as a table
| Test | GPT-5.4 | GLM-5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 93.3% | 87.8% |
| GPQA Diamond (Vals AI) | 91.7% | 83.3% |
| MMLU Pro | 87.5% | 86.0% |
| CL-bench | 27.9% | 18.7% |
| Maths | ||
| AIME-style maths (OTIS mock) | 97.8% | 80.0% |
| FrontierMath (2025 set) | 47.6% | 16.4% |
| FrontierMath tier 4 (2025 set) | 27.1% | 2.1% |
| Coding | ||
| SWE-bench Verified | 76.9% | 72.1% |
| LiveCodeBench | 84.1% | 81.9% |
| SWE-bench | 78.2% | 71.4% |
| Vibe Code Bench v1.1 | 67.4% | 23.4% |
| WeirdML | 77.7% | 48.2% |
| Professional work | ||
| CorpFin v2 | 65.3% | 62.9% |
| LegalBench | 86.0% | 84.1% |
| TaxEval v2 | 74.0% | 70.0% |
| Novel problems | ||
| ARC-AGI-2 | 74.0% | 4.9% |
| ARC-AGI-1 | 93.7% | 44.7% |
Task length · METR45 sec
Tests at least two of these models have taken. Bold rows are the core tests.