Up to four models
GPT-5.2 vs GLM-4.7
On the index (GPT-4 = 100), GPT-5.2 scores 162 and GLM-4.7 140. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.2
162146–178
WeightsClosed
ReleasedDec 2025
Price in / out$1.75 / $14
Context400K
Core tests taken6 of 9
140123–157
WeightsOpen
ReleasedDec 2025
Price in / out$0.40 / $1.75
Context205K
Core tests taken1 of 9
GPT-5.2 leads GLM-4.7 by 22 points, ahead on 1 of 1 shared core tests, at 6.5× the price.
Test by testthird-party results
GPT-5.2
GLM-4.7
Every result as a table
| Test | GPT-5.2 | GLM-4.7 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 91.4% | 83.3% |
| GPQA Diamond (Vals AI) | 91.7% | 80.0% |
| MMLU Pro | 86.2% | 82.7% |
| CL-bench | 18.2% | 15.9% |
| SimpleBench | 45.8% | 47.7% |
| SimpleQA Verified | 37.1% | 32.2% |
| Maths | ||
| AIME-style maths (OTIS mock) | 96.1% | 83.3% |
| MGSM | 94.0% | 88.2% |
| Chess puzzles | 48.0% | 21.0% |
| FrontierMath (2025 set) | 40.7% | 2.4% |
| FrontierMath tier 4 (2025 set) | 18.8% | 0.0% |
| Coding | ||
| Terminal-Bench 2.0 (Terminus 2 runs) | 54.0% | 33.4% |
| LiveCodeBench | 85.4% | 82.2% |
| SWE-bench | 75.8% | 69.4% |
| Professional work | ||
| CorpFin v2 | 65.9% | 46.4% |
| LegalBench | 82.8% | 83.4% |
| MedCode | 49.8% | 32.8% |
| MedScribe | 84.4% | 68.6% |
| TaxEval v2 | 75.8% | 68.8% |
Task length · METR45 sec
Tests at least two of these models have taken. Bold rows are the core tests.