GLM-5 vs GLM-5.1
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-5.1 |
|---|---|---|
| Coding | 10.3 GLM-5 | 13.0 GLM-5.1 |
| Agents | 34.5 GLM-5 | 54.0 GLM-5.1 |
| Reasoning | 26.0 GLM-5 | 34.3 GLM-5.1 |
| Knowledge & language | 22.6* GLM-5 | 34.0 GLM-5.1 |
| Human preference | 52.0 GLM-5 | 53.8 GLM-5.1 |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
GLM-5.1 leads on 9 of the 10 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| LMArena Elo | 1457 | 1465 |
| LMArena WebDev (LMArena) | 1435 | 1508 |
| Chess Puzzles (Epoch AI) | 10% | 20% |
| GPQA Diamond | 87.8% | 89.9% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 80% | 93.3% |
| SWE-bench Verified (Epoch AI) | 72.1% | 74.2% |
| Vending-Bench 2 (Andon Labs) | 4432.12 | 5634.41 |
| WeirdML (Håvard Tveit Ihle) | 48.2% | 57.1% |
| AIME 2026 | 96.7% | 95.8% |
| SimpleBench (SimpleBench) | 53.2% | 55.1% |
FAQ
Is GLM-5 better than GLM-5.1?
GLM-5.1 scores 36.8 on the Respan Index (#75), ahead of GLM-5 at 27.8 (#99). GLM-5.1 leads on 9 of the 10 benchmarks both report.
Which is cheaper, GLM-5 or GLM-5.1?
GLM-5 lists at $0.94 input and $2.55 output per 1M tokens; GLM-5.1 at $0.825 and $2.9. Both cost about the same per token at list price.
Which has the larger context window?
Both accept 200K tokens of context.