# GLM-4.7-Flash vs GPT-4.5

> GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-7-flash-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.7-Flash scores higher in 4 categories and GPT-4.5 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.5 leads 57.1 to 47.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 37.8% for GPT-4.5.
- GLM-4.7-Flash has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 38.4 | 36.9 |
| Rank | 175 | 200 |
| Context | 200K | — |
| Input $/M | $0.06 | — |
| Output $/M | $0.40 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-4.7-Flash: 40.0 (#133)
- GPT-4.5: 41.8 (#102)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| LMArena Coding | 1383 | 1397 |
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |
| LiveBench Coding | — | 75.2% |

## Agentic & Tool Use

- GLM-4.7-Flash: —
- GPT-4.5: 27.6 (#92)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| Cybench | — | 17.5% |

## Reasoning

- GLM-4.7-Flash: 20.2 (#224)
- GPT-4.5: 14.1 (#320)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1404 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| ARC-AGI-1 | — | 10.3% |
| Chess Puzzles | 0% | — |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| LiveBench Data Analysis | — | 64.3% |
| Epoch Capabilities Index | — | 136.74 |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |

## Math

- GLM-4.7-Flash: 34.4 (#159)
- GPT-4.5: 31.0 (#200)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 58.3% | 37.8% |
| LMArena Math | 1354 | 1412 |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |

## Knowledge

- GLM-4.7-Flash: 35.4 (#177)
- GPT-4.5: 32.4 (#205)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 60.5% | 68.7% |
| LMArena Expert | 1357 | 1394 |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |
| Vectara Hallucination Rate | 9.3% | — |

## Multimodal

- GLM-4.7-Flash: —
- GPT-4.5: 37.0 (#68)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| LMArena Vision | — | 1195 |
| VPCT | — | 45% |

## Multilingual

- GLM-4.7-Flash: 46.8 (#152)
- GPT-4.5: 52.7 (#78)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1331 | 1413 |
| LMArena Chinese | 1403 | 1421 |
| LMArena French | 1332 | 1417 |
| LMArena German | 1336 | 1457 |
| LMArena Korean | 1284 | 1392 |
| LMArena Russian | 1333 | 1419 |
| LMArena Japanese | — | 1416 |
| LMArena Spanish | 1351 | — |

## Instruction Following

- GLM-4.7-Flash: 70.3 (#162)
- GPT-4.5: 72.8 (#129)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1327 | 1404 |
| LiveBench Instruction Following | — | 72.3% |

## Long Context

- GLM-4.7-Flash: 40.9 (#143)
- GPT-4.5: 40.4 (#150)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1345 | 1406 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- GLM-4.7-Flash: 47.7 (#206)
- GPT-4.5: 57.1 (#129)

| Benchmark | GLM-4.7-Flash | GPT-4.5 |
|---|---|---|
| LMArena Text | 1351 | 1417 |
| LMArena Creative Writing | 1297 | 1394 |
| EQ-Bench Creative Writing | 1125 | 1258 |
| LMArena Multi-Turn | 1342 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| LiveBench Language | — | 61.5% |

## FAQ

### Is GLM-4.7-Flash better than GPT-4.5?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 36.9 on the Noometry Index.

### Is GLM-4.7-Flash or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 40.0 in the Noometry coding category.

### How many benchmarks do GLM-4.7-Flash and GPT-4.5 share?

18 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and GPT-4.5 has 42.