# GLM-5.1 vs GPT-4o

> GLM-5.1 is the stronger model overall, scoring 47.8 to 28.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-gpt-4o
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. GLM-5.1 scores higher in 9 categories and GPT-4o in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.7 to 10.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 6.4% for GPT-4o.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- GLM-5.1 accepts more context: 200K tokens versus 128K.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.1 | GPT-4o |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 28.6 |
| Rank | 59 | 324 |
| Context | 200K | 128K |
| Input $/M | $1.40 | $2.50 |
| Output $/M | $4.40 | $10 |
| Weights | Open | Proprietary |

## Coding

- GLM-5.1: 48.7 (#55)
- GPT-4o: 24.8 (#328)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| SWE-bench Verified | 74.2% | 31% |
| WeirdML | 57.1% | 25.1% |
| LMArena Coding | 1485 | 1297 |
| SWE-bench Verified (bash only) | — | 21.6% |
| Aider Polyglot | — | 45.3% |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| GSO | — | 0% |
| BigCodeBench Instruct | — | 51.1% |
| LiveBench Coding | — | 51.4% |
| BigCodeBench Complete | — | 61.1% |
| CadEval | — | 26% |
| ALE-Bench | 887.1 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- GLM-5.1: 24.9 (#113)
- GPT-4o: 21.0 (#141)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| APEX-Agents | 40.9% | — |
| GDPval | — | 9.9% |
| TheAgentCompany | — | 8.6% |
| Cybench | — | 12.5% |
| BALROG | — | 32.3% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| LMArena Search | — | 1006 |
| METR Time Horizons | — | 40.8% |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 39.1 (#60)
- GPT-4o: 9.4 (#343)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| SimpleBench | 55.1% | 17.8% |
| CritPt | 4.6% | 0% |
| Chess Puzzles | 19% | 13% |
| LMArena Hard Prompts | 1472 | 1281 |
| Epoch Capabilities Index | 149.84 | 128.97 |
| ARC-AGI-2 | — | 0% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 4.5% |
| EnigmaEval | — | 0.8% |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 55.8% |
| DTBench | — | 64.5% |
| LiveBench Data Analysis | — | 60.9% |
| LMCA | — | 16.6% |
| ForecastBench | — | 57.7 |
| LiveBench | — | 55.3% |

## Math

- GLM-5.1: 49.7 (#60)
- GPT-4o: 10.6 (#312)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 0.4% |
| OTIS Mock AIME 2024-2025 | 93.3% | 6.4% |
| LMArena Math | 1473 | 1285 |
| FrontierMath (Feb 2025 set) | 33.4% | 0.3% |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 29.3% |
| LiveBench Math | — | 49.5% |
| MATH Level 5 | — | 53.3% |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 54.9 (#50)
- GPT-4o: 28.8 (#242)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| GPQA Diamond | 89.9% | 49.2% |
| SimpleQA Verified | 34% | 26% |
| LMArena Expert | 1476 | 1250 |
| Humanity's Last Exam | — | 2.7% |
| MMLU-Pro | — | 71.3% |
| Confabulations | — | 15.3% |
| Vectara Hallucination Rate | — | 9.6% |
| GPQA (HELM) | — | 52% |
| MMLU | — | 88.1% |

## Multimodal

- GLM-5.1: —
- GPT-4o: 34.5 (#91)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| LMArena Vision | — | 1137 |
| Video-MME | — | 71.9% |
| GeoBench | — | 71% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |

## Multilingual

- GLM-5.1: 55.0 (#36)
- GPT-4o: 43.2 (#186)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| LMArena Non-English | 1447 | 1283 |
| LMArena Chinese | 1515 | 1277 |
| LMArena French | 1474 | 1304 |
| LMArena German | 1465 | 1282 |
| LMArena Japanese | 1434 | 1257 |
| LMArena Korean | 1418 | 1234 |
| LMArena Russian | 1454 | 1286 |
| LMArena Spanish | 1469 | 1292 |

## Instruction Following

- GLM-5.1: 76.3 (#42)
- GPT-4o: 66.6 (#207)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| LMArena Instruction Following | 1451 | 1278 |
| LiveBench Instruction Following | — | 68.6% |
| IFEval | — | 81.7% |

## Long Context

- GLM-5.1: 44.9 (#53)
- GPT-4o: 39.4 (#179)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| LMArena Longer Query | 1466 | 1289 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- GLM-5.1: 66.9 (#31)
- GPT-4o: 52.6 (#166)

| Benchmark | GLM-5.1 | GPT-4o |
|---|---|---|
| LMArena Text | 1461 | 1300 |
| LMArena Creative Writing | 1453 | 1292 |
| LMArena Multi-Turn | 1472 | 1302 |
| Short-Story Creative Writing | — | 81.8% |
| EQ-Bench Creative Writing | 1592 | — |
| WildBench | — | 82.8% |
| LiveBench Language | — | 47.6% |

## FAQ

### Is GLM-5.1 better than GPT-4o?

GLM-5.1 is the stronger model overall, scoring 47.8 to 28.6 on the Noometry Index.

### Which is cheaper, GLM-5.1 or GPT-4o?

GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; GPT-4o lists at $2.50 and $10.

### Is GLM-5.1 or GPT-4o better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 24.8 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.1 does, with 200K tokens against 128K.

### How many benchmarks do GLM-5.1 and GPT-4o share?

28 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-4o has 72.