# GLM-5 vs GPT-4.5

> GLM-5 is the stronger model overall, scoring 46.1 to 37.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-vs-gpt-4-5
- Last updated: 2026-10-11
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GLM-5 scores higher in 9 categories and GPT-4.5 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 32.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 37.8% for GPT-4.5.
- GLM-5 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5 | GPT-4.5 |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 46.1 | 37.2 |
| Rank | 66 | 208 |
| Context | 205K | — |
| Input $/M | $1 | — |
| Output $/M | $3.20 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-5: 49.0 (#52)
- GPT-4.5: 42.2 (#109)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| WeirdML | 48.2% | 39.4% |
| LMArena Coding | 1461 | 1396 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| Aider Polyglot | — | 44.9% |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| LiveBench Coding | — | 75.2% |
| ALE-Bench | 765.62 | — |

## Agentic & Tool Use

- GLM-5: 31.1 (#71)
- GPT-4.5: 27.9 (#97)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Cybench | — | 17.5% |
| Vending-Bench 2 | 4,432 | — |

## Reasoning

- GLM-5: 27.6 (#116)
- GPT-4.5: 13.9 (#330)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| ARC-AGI-2 | 4.9% | 0.8% |
| SimpleBench | 53.2% | 34.5% |
| ARC-AGI-1 | 44.7% | 10.3% |
| LMArena Hard Prompts | 1452 | 1403 |
| Epoch Capabilities Index | 145.83 | 136.74 |
| ForecastBench | 61 | 61.7 |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| Chess Puzzles | 10% | — |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| LiveBench Data Analysis | — | 64.3% |
| LiveBench | — | 69% |

## Math

- GLM-5: 46.4 (#71)
- GPT-4.5: 32.6 (#211)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 37.8% |
| LMArena Math | 1440 | 1412 |
| MathArena Final-Answer Competitions | 65.7% | — |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-5: 52.3 (#64)
- GPT-4.5: 32.5 (#211)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 87.8% | 68.7% |
| LMArena Expert | 1454 | 1394 |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |
| Vectara Hallucination Rate | 10.1% | — |

## Multimodal

- GLM-5: —
- GPT-4.5: 37.6 (#71)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| LMArena Vision | — | 1195 |
| VPCT | — | 45% |

## Multilingual

- GLM-5: 53.7 (#58)
- GPT-4.5: 52.5 (#83)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1430 | 1413 |
| LMArena Chinese | 1511 | 1421 |
| LMArena French | 1455 | 1418 |
| LMArena German | 1445 | 1457 |
| LMArena Japanese | 1416 | 1416 |
| LMArena Korean | 1423 | 1392 |
| LMArena Russian | 1436 | 1419 |
| LMArena Spanish | 1454 | — |

## Instruction Following

- GLM-5: 75.2 (#67)
- GPT-4.5: 72.6 (#134)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1404 |
| LiveBench Instruction Following | — | 72.3% |

## Long Context

- GLM-5: 44.7 (#60)
- GPT-4.5: 40.4 (#155)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1446 | 1406 |
| Fiction.LiveBench | — | 63.9% |
| CL-bench | 18.7% | — |

## Writing & Preference

- GLM-5: 66.0 (#38)
- GPT-4.5: 56.9 (#134)

| Benchmark | GLM-5 | GPT-4.5 |
|---|---|---|
| LMArena Text | 1446 | 1417 |
| LMArena Creative Writing | 1439 | 1394 |
| EQ-Bench Creative Writing | 1601 | 1258 |
| LMArena Multi-Turn | 1456 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| LiveBench Language | — | 61.5% |

## FAQ

### Is GLM-5 better than GPT-4.5?

GLM-5 is the stronger model overall, scoring 46.1 to 37.2 on the Noometry Index.

### Is GLM-5 or GPT-4.5 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 42.2 in the Noometry coding category.

### How many benchmarks do GLM-5 and GPT-4.5 share?

25 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and GPT-4.5 has 42.