Up to four models
GLM-5 vs DeepSeek-V3.2
On the index (GPT-4 = 100), GLM-5 scores 142 and DeepSeek-V3.2 141. 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
141125–157
WeightsOpen
ReleasedDec 2025
Price in / out$0.26 / $0.38
Context164K
Core tests taken2 of 9
GLM-5 and DeepSeek-V3.2 are too close to call (0 points apart, within the uncertainty), ahead on 1 of 1 shared core tests, at 5.3× the price.
Test by testthird-party results
Every result as a table
| Test | GLM-5 | DeepSeek-V3.2 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 87.8% | 83.4% |
| CL-bench | 18.7% | 12.4% |
| Maths | ||
| AIME-style maths (OTIS mock) | 80.0% | 87.8% |
| FrontierMath (2025 set) | 16.4% | 22.1% |
| FrontierMath tier 4 (2025 set) | 2.1% | 2.1% |
| Coding | ||
| Terminal-Bench 2.0 (Terminus 2 runs) | 52.4% | 39.6% |
Tests at least two of these models have taken. Bold rows are the core tests.