Claude Sonnet 4.5 vs GLM-5
| Spec | Claude Sonnet 4.5 | GLM-5 |
|---|---|---|
| Respan Index | 31.2 (#76) | 27.7 (#89) |
| Blended price per 1M | $6 | $1.33 |
| Context window | 200K | 200K |
| Input / output per 1M | $3 / $15 | $0.92 / $2.55 |
| Max output | 64K | 131K |
| Input | text, vision | text |
| Released | 2025-09-29 | - |
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 | Claude Sonnet 4.5 | GLM-5 |
|---|---|---|
| Coding | 12.9 Claude Sonnet 4.5 | 10.4 GLM-5 |
| Agents | 41.9 Claude Sonnet 4.5 | 34.9 GLM-5 |
| Reasoning | 27.4 Claude Sonnet 4.5 | 25.3 GLM-5 |
| Knowledge & language | 31.1 Claude Sonnet 4.5 | 22.7* GLM-5 |
| Human preference | 50.5 Claude Sonnet 4.5 | 51.6 GLM-5 |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
GLM-5 leads on 13 of the 16 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Sonnet 4.5 | GLM-5 |
|---|---|---|
| Chess Puzzles (Epoch AI) | 10% | 10% |
| LMArena Elo | 1456 | 1457 |
| LMArena WebDev (LMArena) | 1394 | 1436 |
| GPQA Diamond | 83.4% | 87.8% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 77.8% | 80% |
| SimpleBench (SimpleBench) | 54.3% | 53.2% |
| SWE-bench Verified (Epoch AI) | 71.3% | 72.1% |
| Vending-Bench 2 (Andon Labs) | 3838.74 | 4432.12 |
| WeirdML (Håvard Tveit Ihle) | 47.7% | 48.2% |
| AIME 2025 | 84.2% | 96.7% |
| tau2-bench Airline (Sierra) | 72% | 82.5% |
| tau2-bench Banking Knowledge (Sierra) | 25.3% | 9.8% |
| tau2-bench Retail (Sierra) | 72.4% | 73.7% |
| tau2-bench Telecom (Sierra) | 84.9% | 86.8% |
| SWE-bench Verified | 77.2% | 77.8% |
| Terminal-Bench 2.0 | 51% | 56.2% |
FAQ
Is Claude Sonnet 4.5 better than GLM-5?
Claude Sonnet 4.5 scores 31.2 on the Respan Index (#76), ahead of GLM-5 at 27.7 (#89). GLM-5 leads on 13 of the 16 benchmarks both report.
Which is cheaper, Claude Sonnet 4.5 or GLM-5?
Claude Sonnet 4.5 lists at $3 input and $15 output per 1M tokens; GLM-5 at $0.92 and $2.55. GLM-5 is 4.5x cheaper per token at list price.
Which has the larger context window?
Both accept 200K tokens of context.