Compare / head-to-head
Claude Sonnet 4vsGLM-5
GLM-5 leads 3 of 3 shared benchmarks. GLM-5 is 4.3x cheaper per token. Both offer a 200K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 3
GLM-5 leads
Cheaper per token
GLM-5
4.3x cheaper, input + output
Larger context
Tie
both 200K tokens
Provider uptime (30d)
100% · —
Anthropic · Z.ai
Claude Sonnet 4
Anthropic · released 2025-05-22
textvision
Quality
Benchmark matrix
3 shared · 1 only Claude Sonnet 4 · 5 only GLM-5| Benchmark | Claude Sonnet 4 | GLM-5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| SWE-bench Verified | 72.7% ↗ | 77.8% ↗ | -5.1 pt | GLM-5 |
| GPQA Diamond | 79.2% ↗epoch | 87.8% ↗epoch | -8.6 pt | GLM-5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 71.1% ↗epoch | 80% ↗epoch | -8.9 pt | GLM-5 |
| Only Claude Sonnet 4 reports · 1 | ||||
| AIME 2024 (no extended thinking) | 33.1% ↗ | not reported | — | — |
| Only GLM-5 reports · 5 | ||||
| AIME 2025 | not reported | 96.7% ↗matharena ⚠ | — | — |
| AIME 2026 | not reported | 96.7% ↗matharena ⚠ | — | — |
| LMArena Elo | not reported | 1446.3 ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 72.1% ↗epoch | — | — |
| Terminal-Bench 2.0 | not reported | 56.2% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Sonnet 4 minus GLM-5 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Claude Sonnet 4 | GLM-5 | Edge |
|---|---|---|---|
| Context window | 200K tokens | 200K tokens | Tie |
| Max output | 64K tokens | 131K tokens | GLM-5 |
| Input price / 1M | $3 ↗ | $1 ↗ | GLM-5 |
| Output price / 1M | $15 ↗ | $3.2 ↗ | GLM-5 |
| Cached input / 1M | $0.3 ↗ | $0.2 ↗ | GLM-5 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $18 | $4.2 | GLM-5 |
| Modalities | text · vision | text | Claude Sonnet 4 |
| Released | 2025-05-22 | — | — |
| Cited benchmark scores | 4 | 8 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Sonnet 4 vs …
Models sharing the most benchmarksMore matchups
GLM-5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Sonnet 4 and GLM-5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.