Up to four models
GLM-5.1 vs GPT-5.4 Nano
On the index (GPT-4 = 100), GLM-5.1 scores 151 and GPT-5.4 Nano 141. 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
GPT-5.4 Nano
141125–157
WeightsClosed
ReleasedMar 2026
Price in / out$0.20 / $1.25
Context400K
Core tests taken4 of 9
GLM-5.1 leads GPT-5.4 Nano by 9 points, ahead on 2 of 3 shared core tests, at 4.6× the price.
Test by testthird-party results
Every result as a table
| Test | GLM-5.1 | GPT-5.4 Nano |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 89.9% | 78.5% |
| GPQA Diamond (Vals AI) | 84.5% | 77.5% |
| MMLU Pro | 86.9% | 77.2% |
| SimpleQA Verified | 34.0% | 11.7% |
| Maths | ||
| FrontierMath (tiers 1-3) | 36.8% | 44.9% |
| AIME-style maths (OTIS mock) | 93.3% | 87.8% |
| Chess puzzles | 20.0% | 45.0% |
| FrontierMath (2025 set) | 33.5% | 25.9% |
| FrontierMath tier 4 (2025 set) | 12.5% | 6.3% |
| Coding | ||
| Code Migration | 25.8% | 14.5% |
| LiveCodeBench | 81.4% | 84.0% |
| SWE-bench | 76.4% | 69.8% |
| Vibe Code Bench v1.1 | 31.5% | 26.1% |
| WeirdML | 57.1% | 49.2% |
| Professional work | ||
| Finance Agent (v2) | 44.8% | 38.2% |
| CorpFin v2 | 64.5% | 61.2% |
| LegalBench | 84.4% | 77.9% |
| Legal Research Bench | 27.9% | 6.3% |
| MedCode | 41.6% | 41.0% |
| MedScribe | 72.3% | 77.1% |
| TaxEval v2 | 71.2% | 67.4% |
Tests at least two of these models have taken. Bold rows are the core tests.