# GLM-4.6 vs GPT-5.1-Codex

> GLM-4.6 is the stronger model overall, scoring 41.4 to 38.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-gpt-5-1-codex
- Last updated: 2026-10-11
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. GLM-4.6 scores higher in 1 category and GPT-5.1-Codex in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 39.1 to 30.3.
- The biggest single-benchmark swing is Terminal-Bench: 24.5% for GLM-4.6 and 60.4% for GPT-5.1-Codex.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
- GPT-5.1-Codex accepts more context: 400K tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 38.6 |
| Rank | 135 | 186 |
| Context | 205K | 400K |
| Input $/M | $0.60 | $1.25 |
| Output $/M | $2.20 | $10 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.6: 40.1 (#148)
- GPT-5.1-Codex: 41.9 (#116)

| Benchmark | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | 66% |
| LMArena WebDev | 1340 | 1337 |
| ALE-Bench | 340.82 | 1,245 |
| SciCode | 38.4% | — |
| LMArena Coding | 1449 | — |

## Agentic & Tool Use

- GLM-4.6: 32.3 (#66)
- GPT-5.1-Codex: 38.0 (#33)

| Benchmark | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| Terminal-Bench | 24.5% | 60.4% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| METR Time Horizons | — | 70.8% |

## Reasoning

- GLM-4.6: 23.7 (#172)
- GPT-5.1-Codex: —

| Benchmark | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
| LMArena Hard Prompts | 1440 | — |

## Math

- GLM-4.6: 39.1 (#111)
- GPT-5.1-Codex: 30.3 (#235)

| Benchmark | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| ProofBench | — | 9% |
| LMArena Math | 1432 | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 40.2 (#124)
- GPT-5.1-Codex: —

| Benchmark | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | — |
| LMArena Expert | 1431 | — |

## Multilingual

- GLM-4.6: 53.5 (#66)
- GPT-5.1-Codex: —

| Benchmark | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| LMArena Non-English | 1426 | — |
| LMArena Chinese | 1499 | — |
| LMArena French | 1459 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1393 | — |
| LMArena Korean | 1400 | — |
| LMArena Russian | 1419 | — |
| LMArena Spanish | 1436 | — |

## Instruction Following

- GLM-4.6: 74.3 (#98)
- GPT-5.1-Codex: —

| Benchmark | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| LMArena Instruction Following | 1410 | — |

## Long Context

- GLM-4.6: 43.4 (#94)
- GPT-5.1-Codex: —

| Benchmark | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| LMArena Longer Query | 1422 | — |

## Writing & Preference

- GLM-4.6: 61.1 (#90)
- GPT-5.1-Codex: —

| Benchmark | GLM-4.6 | GPT-5.1-Codex |
|---|---|---|
| LMArena Text | 1440 | — |
| LMArena Creative Writing | 1411 | — |
| EQ-Bench Creative Writing | 1411 | — |
| LMArena Multi-Turn | 1427 | — |

## FAQ

### Is GLM-4.6 better than GPT-5.1-Codex?

GLM-4.6 is the stronger model overall, scoring 41.4 to 38.6 on the Noometry Index.

### Which is cheaper, GLM-4.6 or GPT-5.1-Codex?

GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.

### Is GLM-4.6 or GPT-5.1-Codex better for coding?

GPT-5.1-Codex scores higher on coding benchmarks: 41.9 versus 40.1 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.1-Codex does, with 400K tokens against 205K.

### How many benchmarks do GLM-4.6 and GPT-5.1-Codex share?

4 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-5.1-Codex has 6.