# GLM-5.1 vs GPT-4.5

> GLM-5.1 is the stronger model overall, scoring 47.6 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and GPT-4.5 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 38.2 to 14.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 37.8% for GPT-4.5.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.1 | GPT-4.5 |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.6 | 36.9 |
| Rank | 51 | 200 |
| Context | 200K | — |
| Input $/M | $1.40 | — |
| Output $/M | $4.40 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-5.1: 48.5 (#52)
- GPT-4.5: 41.8 (#102)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| WeirdML | 57.1% | 39.4% |
| LMArena Coding | 1486 | 1397 |
| SWE-bench Verified | 74.2% | — |
| Aider Polyglot | — | 44.9% |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| LiveBench Coding | — | 75.2% |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- GPT-4.5: 27.6 (#92)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Cybench | — | 17.5% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- GPT-4.5: 14.1 (#320)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| SimpleBench | 55.1% | 34.5% |
| LMArena Hard Prompts | 1472 | 1404 |
| Epoch Capabilities Index | 149.86 | 136.74 |
| ARC-AGI-2 | — | 0.8% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 10.3% |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| EnigmaEval | — | 3.2% |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 71.1% |
| LiveBench Data Analysis | — | 64.3% |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |

## Math

- GLM-5.1: 49.0 (#48)
- GPT-4.5: 31.0 (#200)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 37.8% |
| LMArena Math | 1472 | 1412 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- GPT-4.5: 32.4 (#205)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 89.9% | 68.7% |
| LMArena Expert | 1477 | 1394 |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | 34% | — |
| Confabulations | — | 13.6% |

## Multimodal

- GLM-5.1: —
- GPT-4.5: 37.0 (#68)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| LMArena Vision | — | 1195 |
| VPCT | — | 45% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- GPT-4.5: 52.7 (#78)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1448 | 1413 |
| LMArena Chinese | 1516 | 1421 |
| LMArena French | 1478 | 1417 |
| LMArena German | 1466 | 1457 |
| LMArena Japanese | 1436 | 1416 |
| LMArena Korean | 1423 | 1392 |
| LMArena Russian | 1453 | 1419 |
| LMArena Spanish | 1467 | — |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- GPT-4.5: 72.8 (#129)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1404 |
| LiveBench Instruction Following | — | 72.3% |

## Long Context

- GLM-5.1: 44.9 (#51)
- GPT-4.5: 40.4 (#150)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1467 | 1406 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- GPT-4.5: 57.1 (#129)

| Benchmark | GLM-5.1 | GPT-4.5 |
|---|---|---|
| LMArena Text | 1462 | 1417 |
| LMArena Creative Writing | 1454 | 1394 |
| EQ-Bench Creative Writing | 1592 | 1258 |
| LMArena Multi-Turn | 1473 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| LiveBench Language | — | 61.5% |

## FAQ

### Is GLM-5.1 better than GPT-4.5?

GLM-5.1 is the stronger model overall, scoring 47.6 to 36.9 on the Noometry Index.

### Is GLM-5.1 or GPT-4.5 better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 41.8 in the Noometry coding category.

### How many benchmarks do GLM-5.1 and GPT-4.5 share?

22 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-4.5 has 42.