# GLM-5.1 vs GPT-5.1-Codex

> Side-by-side benchmark comparison for GLM-5.1 and GPT-5.1-Codex across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/glm-5-1-vs-gpt-5-1-codex
- Last updated: September 4, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: GLM-5.1 and GPT-5.1-Codex share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- GLM-5.1 has the lower published output-token price.
- GPT-5.1-Codex has the larger published context window at 400K.

## Model Snapshot

| Property | GLM-5.1 | GPT-5.1-Codex |
|----------|----------|----------|
| Creator | Z.AI | OpenAI |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 203K | 400K |
| Independent public score (not head-to-head) | 64.41 | 51.62 |
| Benchmarks Covered | 26 | 3 |
| Pricing (input/output) | $1.40 / $4.40 | $1.25 / $10.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GLM-5.1 public-lane score: 50.1 (Estimated · #63/151)
- GPT-5.1-Codex public-lane score: 51.4 (Estimated · #54/151)

| Benchmark | GLM-5.1 | GPT-5.1-Codex | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 63.5% | Coming soon | Coming soon |
| BrowseComp | 68% | Coming soon | Coming soon |
| τ³-bench results | 70.6% | Coming soon | Coming soon |
| MCP Atlas | 71.8% | Coming soon | Coming soon |
| CyberGym | 68.7% | Coming soon | Coming soon |
| Claw-Eval | 62.3% | Coming soon | Coming soon |
| Gert Labs | 60.11% | 49.68% | GLM-5.1 |
| ResearchClawBench | 18.2% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 56.9% | Coming soon | Coming soon |
| JobBench | Coming soon | 26.2% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- GLM-5.1 public-lane score: 56.8 (Supported · #39/183)
- GPT-5.1-Codex public-lane score: 47.4 (Estimated · #89/183)

| Benchmark | GLM-5.1 | GPT-5.1-Codex | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 58.4% | Coming soon | Coming soon |
| NL2Repo | 42.7% | Coming soon | Coming soon |
| SWE-Rebench | 62.7% | Coming soon | Coming soon |
| Vibe Code Bench | 31.46% | 13.12% | GLM-5.1 |
| OpenHarmony Bench | 52.3% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 81.4% | Coming soon | Coming soon |
| SWE-bench (Vals) | 76.4% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- GLM-5.1 public-lane score: Coming soon
- GPT-5.1-Codex public-lane score: 66.8 (Unranked · 1 rankable row)

### Reasoning

- Winner: Insufficient shared evidence
- GLM-5.1 public-lane score: 69.9 (Unranked · 2 rankable rows)
- GPT-5.1-Codex public-lane score: 70.6 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Insufficient shared evidence
- GLM-5.1 public-lane score: 55.4 (Supported · #59/181)
- GPT-5.1-Codex public-lane score: 53.3 (Estimated · #69/181)

| Benchmark | GLM-5.1 | GPT-5.1-Codex | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 86.2% | Coming soon | Coming soon |
| HLE | 52.3% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 84.5% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 86.9% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- GLM-5.1 public-lane score: 93.5 (#5/120)
- GPT-5.1-Codex public-lane score: 85.3 (#42/120)

### Mathematics

- Winner: Insufficient shared evidence
- GLM-5.1 public-lane score: 64.1 (#3/7)
- GPT-5.1-Codex public-lane score: Coming soon

| Benchmark | GLM-5.1 | GPT-5.1-Codex | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 95.3% | Coming soon | Coming soon |
| HMMT Nov 2025 | 94.0% | Coming soon | Coming soon |
| HMMT Feb 2026 | 82.6% | Coming soon | Coming soon |
| MMAnswerBench | 83.8% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 33.448% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 12.500% | Coming soon | Coming soon |

## FAQ

### Is there enough evidence to pick between GLM-5.1 and GPT-5.1-Codex?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [GLM-5.1 vs GLM-5.3](/compare/glm-5-1-vs-glm-5-3)
- [GPT-5.1-Codex vs GLM-5.3](/compare/glm-5-3-vs-gpt-5-1-codex)
- [GLM-5.1 vs GLM-5.2](/compare/glm-5-1-vs-glm-5-2)
- [GPT-5.1-Codex vs GLM-5.2](/compare/glm-5-2-vs-gpt-5-1-codex)

## Explore More

- [GLM-5.1 profile](/models/glm-5-1)
- [GPT-5.1-Codex profile](/models/gpt-5-1-codex)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)