Compare / head-to-head
GLM-5.1vsGLM-5.3
GLM-5.3 leads 3 of 4 shared benchmarks. Both list the same combined token price. GLM-5.3 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 3
GLM-5.3 leads
Cheaper per token
Tie
list price, input + output
Larger context
GLM-5.3
1M tokens
Provider uptime (30d)
—
Z.ai
GLM-5.1
Z.ai · released 2026-04-07
text
Quality
Benchmark matrix
4 shared · 3 only GLM-5.1 · 20 only GLM-5.3| Benchmark | GLM-5.1 | GLM-5.3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| GPQA Diamond | 89.9% ↗epoch | 90.9% ↗epoch | -1 pt | GLM-5.3 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 36.8% ↗epoch | 68.8% ↗epoch | -32 pt | GLM-5.3 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 93.3% ↗epoch | 91.1% ↗epoch | +2.2 pt | GLM-5.1 |
| SimpleQA Verified | 34% ↗epoch | 41% ↗epoch | -7 pt | GLM-5.3 |
| Only GLM-5.1 reports · 3 | ||||
| AIME 2026 | 95.8% ↗matharena ⚠ | not reported | — | — |
| LMArena Elo | 1462.4 ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 74.2% ↗epoch | not reported | — | — |
| Only GLM-5.3 reports · 20 | ||||
| Agents' Last Exam | not reported | 28.5% ↗ | — | — |
| Agents' Last Exam (ALE-CLI) | not reported | 28.5% ↗ | — | — |
| AutomationBench v1.0.6 | not reported | 48.2% ↗ | — | — |
| CyberGym | not reported | 84.5% ↗ | — | — |
| DeepSWE v1.1 | not reported | 66.9% ↗ | — | — |
| ExploitBench | not reported | 54.4% ↗ | — | — |
| ExploitGym 2h | not reported | 105 ↗ | — | — |
| ExploitGym 6h | not reported | 130 ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 29.3% ↗epoch | — | — |
| FrontierSWE | not reported | 78.1% ↗ | — | — |
| GDPval-AA v2 | not reported | 1769 ↗ | — | — |
| HLE (with tools) | not reported | 62.5% ↗ | — | — |
| NL2Repo | not reported | 58% ↗ | — | — |
| PostTrainBench | not reported | 39.8% ↗ | — | — |
| ProgramBench (Almost Solved) | not reported | 19% ↗ | — | — |
| SWE-Marathon v1.1 | not reported | 42.5% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 88.2% ↗ | — | — |
| Terminal-Bench 3.0 | not reported | 28.3% ↗ | — | — |
| Toolathlon Verified | not reported | 73% ↗ | — | — |
| Z.ai Code Bench (max effort) | not reported | 34.5% ↗ | — | — |
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 GLM-5.1 minus GLM-5.3 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 | GLM-5.1 | GLM-5.3 | Edge |
|---|---|---|---|
| Context window | 200K tokens | 1M tokens | GLM-5.3 |
| Max output | 131K tokens | 131K tokens | Tie |
| Input price / 1M | $1.4 ↗ | $1.4 ↗ | Tie |
| Output price / 1M | $4.4 ↗ | $4.4 ↗ | Tie |
| Cached input / 1M | $0.26 ↗ | $0.26 ↗ | Tie |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $5.8 | $5.8 | Tie |
| Modalities | text | text | Tie |
| Released | 2026-04-07 | 2026-08-14 | — |
| Cited benchmark scores | 7 | 33 | — |
Reliability
Z.ai status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GLM-5.1 vs …
Models sharing the most benchmarksMore matchups
GLM-5.3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GLM-5.1 and GLM-5.3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.