GLM-5.1 vs GLM-5.2
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | GLM-5.1 | GLM-5.2 |
|---|---|---|
| Coding | 13.0 GLM-5.1 | 27.9 GLM-5.2 |
| Agents | 54.0 GLM-5.1 | 55.9 GLM-5.2 |
| Reasoning | 34.3 GLM-5.1 | 42.0 GLM-5.2 |
| Knowledge & language | 34.0 GLM-5.1 | 34.6 GLM-5.2 |
| Human preference | 53.8 GLM-5.1 | 56.4 GLM-5.2 |
Benchmarks both report
GLM-5.2 leads on 11 of the 13 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GLM-5.1 | GLM-5.2 |
|---|---|---|
| LMArena Elo | 1465 | 1475 |
| LMArena WebDev (LMArena) | 1508 | 1608 |
| Chess Puzzles (Epoch AI) | 20% | 22% |
| APEX-Agents (Mercor) | 40.9% | 45.2% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 36.8% | 59.2% |
| GPQA Diamond | 89.9% | 91.9% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 93.3% | 86.4% |
| SimpleQA Verified | 34% | 34.2% |
| SWE-bench Verified (Epoch AI) | 74.2% | 78.7% |
| Vending-Bench 2 (Andon Labs) | 5634.41 | 8313.78 |
| WeirdML (Håvard Tveit Ihle) | 57.1% | 70.1% |
| AIME 2026 | 95.8% | 90% |
| SimpleBench (SimpleBench) | 55.1% | 58.8% |
FAQ
Is GLM-5.1 better than GLM-5.2?
GLM-5.2 scores 43.4 on the Respan Index (#62), ahead of GLM-5.1 at 36.8 (#75). GLM-5.2 leads on 11 of the 13 benchmarks both report.
Which is cheaper, GLM-5.1 or GLM-5.2?
GLM-5.1 lists at $0.825 input and $2.9 output per 1M tokens; GLM-5.2 at $0.19 and $1.8. GLM-5.2 is 2.3x cheaper per token at list price.
Which has the larger context window?
GLM-5.1 accepts 200K tokens and GLM-5.2 1M tokens.