# GLM-4.5 vs Grok 4

> Grok 4 is the stronger model overall, scoring 47.8 to 41.4 on the Noometry Index.

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

## Summary

- They share 22 benchmarks with published results for both. GLM-4.5 scores higher in 1 category and Grok 4 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 38.2.
- The biggest single-benchmark swing is Fiction.LiveBench: 58.3% for GLM-4.5 and 94.4% for Grok 4.
- GLM-4.5 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.5 | Grok 4 |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 41.4 | 47.8 |
| Rank | 125 | 49 |
| Context | 131K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-4.5: 41.1 (#121)
- Grok 4: 49.9 (#44)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| WeirdML | 40.6% | 45.7% |
| LMArena Coding | 1434 | 1408 |
| SWE-bench Verified (bash only) | 54.2% | — |
| Aider Polyglot | — | 79.6% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- GLM-4.5: —
- Grok 4: 32.1 (#62)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |

## Reasoning

- GLM-4.5: 27.7 (#99)
- Grok 4: 36.9 (#59)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 73.6% |
| LMArena Hard Prompts | 1430 | 1409 |
| ARC-AGI-2 | — | 16% |
| SimpleBench | — | 60.5% |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| Epoch Capabilities Index | — | 146.46 |
| ForecastBench | — | 60.9 |

## Math

- GLM-4.5: 36.3 (#119)
- Grok 4: 46.5 (#58)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| LMArena Math | 1427 | 1422 |
| OTIS Mock AIME 2024-2025 | — | 84% |
| Omni-MATH | — | 60.3% |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- GLM-4.5: 35.5 (#172)
- Grok 4: 53.7 (#50)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| Confabulations | 11.3% | 12.4% |
| LMArena Expert | 1433 | 1417 |
| GPQA Diamond | — | 87% |
| Humanity's Last Exam | 8.3% | — |
| MMLU-Pro | — | 85.1% |
| GPQA (HELM) | — | 72.7% |

## Multimodal

- GLM-4.5: —
- Grok 4: 33.1 (#89)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| LMArena Vision | — | 1211 |
| GeoBench | — | 45% |

## Multilingual

- GLM-4.5: 53.0 (#74)
- Grok 4: 52.0 (#98)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| LMArena Non-English | 1417 | 1403 |
| LMArena Chinese | 1465 | 1428 |
| LMArena French | 1423 | 1418 |
| LMArena German | 1406 | 1429 |
| LMArena Japanese | 1416 | 1396 |
| LMArena Korean | 1382 | 1376 |
| LMArena Russian | 1414 | 1409 |
| LMArena Spanish | 1454 | 1419 |

## Instruction Following

- GLM-4.5: 74.3 (#100)
- Grok 4: 79.4 (#4)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1387 |
| IFEval | — | 94.9% |

## Long Context

- GLM-4.5: 38.2 (#196)
- Grok 4: 63.1 (#4)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| Fiction.LiveBench | 58.3% | 94.4% |
| LMArena Longer Query | 1413 | 1409 |

## Writing & Preference

- GLM-4.5: 57.7 (#121)
- Grok 4: 58.7 (#111)

| Benchmark | GLM-4.5 | Grok 4 |
|---|---|---|
| LMArena Text | 1430 | 1412 |
| LMArena Creative Writing | 1395 | 1397 |
| Short-Story Creative Writing | 73.4% | 76.9% |
| LMArena Multi-Turn | 1415 | 1416 |
| EQ-Bench Creative Writing | 1343 | — |
| WildBench | — | 79.7% |

## FAQ

### Is GLM-4.5 better than Grok 4?

Grok 4 is the stronger model overall, scoring 47.8 to 41.4 on the Noometry Index.

### Is GLM-4.5 or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 49.9 versus 41.1 in the Noometry coding category.

### How many benchmarks do GLM-4.5 and Grok 4 share?

22 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Grok 4 has 48.