Compare / head-to-head
GLM-5vs
GPT-5.1-Codex-Max
GPT-5.1-Codex-Max leads 2 of 2 shared benchmarks. GLM-5 is 2.7x cheaper per token. GPT-5.1-Codex-Max has the larger context window (400K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 2
GPT-5.1-Codex-Max leads
Cheaper per token
GLM-5
2.7x cheaper, input + output
Larger context
GPT-5.1-Codex-Max
400K tokens
Providers
2 providers
Z.ai · OpenAI
GPT-5.1-Codex-Max
OpenAI · released 2025-11-19
textvision
Quality
Benchmark matrix
2 shared · 15 only GLM-5 · 1 only GPT-5.1-Codex-Max| Benchmark | GLM-5 | GPT-5.1-Codex-Max | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| SWE-bench Verified | 77.8% ↗ | 77.9% ↗ | -0.1 pt | GPT-5.1-Codex-Max |
| Terminal-Bench 2.0 | 56.2% ↗ | 58.1% ↗ | -1.9 pt | GPT-5.1-Codex-Max |
| Only GLM-5 reports · 15 | ||||
| GPQA Diamond | 87.8% ↗epoch run | not reported | — | — |
| AIME 2025 | 96.7% ↗matharena ⚠ | not reported | — | — |
| AIME 2026 | 96.7% ↗matharena ⚠ | not reported | — | — |
| LMArena Elo | 1446.3 ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 10% ↗epoch run | not reported | — | — |
| LMArena WebDev (LMArena) | 1434 ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 80% ↗epoch run | not reported | — | — |
| SimpleBench (SimpleBench) | 53.2% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 72.1% ↗epoch run | not reported | — | — |
| tau2-bench Airline (Sierra) | 82.5% ↗ | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 9.8% ↗ | not reported | — | — |
| tau2-bench Retail (Sierra) | 73.7% ↗ | not reported | — | — |
| tau2-bench Telecom (Sierra) | 86.8% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 4432.12 ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 48.2% ↗ | not reported | — | — |
| Only GPT-5.1-Codex-Max reports · 1 | ||||
| SWE-Lancer IC SWE | not reported | 79.9% ↗ | — | — |
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 minus GPT-5.1-Codex-Max 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 | GPT-5.1-Codex-Max | Edge |
|---|---|---|---|
| Context window | 200K tokens | 400K tokens | GPT-5.1-Codex-Max |
| Max output | 131K tokens | 128K tokens | GLM-5 |
| Input price / 1M | $1 ↗ | $1.25 ↗ | GLM-5 |
| Output price / 1M | $3.2 ↗ | $10 ↗ | GLM-5 |
| Cached input / 1M | $0.2 ↗ | $0.125 ↗ | GPT-5.1-Codex-Max |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $4.2 | $11.25 | GLM-5 |
| Modalities | text | text · vision | GPT-5.1-Codex-Max |
| Released | — | 2025-11-19 | — |
| Cited benchmark scores | 21 | 3 | — |
Reliability
Provider status
Live from /statusMore matchups
GLM-5 vs …
Models sharing the most benchmarksMore matchups
GPT-5.1-Codex-Max vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GLM-5 and GPT-5.1-Codex-Max on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.