GLM-5 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 | GLM-5.2 |
|---|---|---|
| Coding | 10.3 GLM-5 | 27.9 GLM-5.2 |
| Agents | 34.5 GLM-5 | 55.9 GLM-5.2 |
| Reasoning | 26.0 GLM-5 | 42.0 GLM-5.2 |
| Knowledge & language | 22.6* GLM-5 | 34.6 GLM-5.2 |
| Human preference | 52.0 GLM-5 | 56.4 GLM-5.2 |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
GLM-5.2 leads on 10 of the 11 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GLM-5 | GLM-5.2 |
|---|---|---|
| LMArena Elo | 1457 | 1475 |
| LMArena WebDev (LMArena) | 1435 | 1608 |
| Chess Puzzles (Epoch AI) | 10% | 22% |
| GPQA Diamond | 87.8% | 91.9% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 80% | 86.4% |
| SWE-bench Verified (Epoch AI) | 72.1% | 78.7% |
| Vending-Bench 2 (Andon Labs) | 4432.12 | 8313.78 |
| WeirdML (Håvard Tveit Ihle) | 48.2% | 70.1% |
| AIME 2026 | 96.7% | 90% |
| tau2-bench Banking Knowledge (Sierra) | 9.8% | 37.1% |
| SimpleBench (SimpleBench) | 53.2% | 58.8% |
FAQ
Is GLM-5 better than GLM-5.2?
GLM-5.2 scores 43.4 on the Respan Index (#62), ahead of GLM-5 at 27.8 (#99). GLM-5.2 leads on 10 of the 11 benchmarks both report.
Which is cheaper, GLM-5 or GLM-5.2?
GLM-5 lists at $0.94 input and $2.55 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 accepts 200K tokens and GLM-5.2 1M tokens.