# GLM-4.6 vs Grok-2 (Dec 2024)

> GLM-4.6 is the stronger model overall, scoring 41.4 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-grok-2
- Last updated: 2026-10-11
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and Grok-2 (Dec 2024) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 39.1 to 20.8.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 41.4 | 33.7 |
| Rank | 135 | 239 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-4.6: 40.1 (#148)
- Grok-2 (Dec 2024): 33.3 (#258)

| Benchmark | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Coding | 1449 | 1287 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| WeirdML | — | 22.2% |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 340.82 | — |

## Agentic & Tool Use

- GLM-4.6: 32.3 (#66)
- Grok-2 (Dec 2024): —

| Benchmark | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |

## Reasoning

- GLM-4.6: 23.7 (#172)
- Grok-2 (Dec 2024): 16.9 (#299)

| Benchmark | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1272 |
| SimpleBench | — | 22.7% |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | — | 54.8% |
| DTBench | — | 65.2% |
| LiveBench Data Analysis | — | 54.5% |
| Epoch Capabilities Index | — | 130.48 |
| LiveBench | — | 54.3% |

## Math

- GLM-4.6: 39.1 (#111)
- Grok-2 (Dec 2024): 20.8 (#284)

| Benchmark | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Math | 1432 | 1283 |
| FrontierMath (Feb 2025 set) | 3.8% | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 11.5% |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 40.2 (#124)
- Grok-2 (Dec 2024): 29.8 (#233)

| Benchmark | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Expert | 1431 | 1254 |
| GPQA Diamond | — | 53.8% |
| Confabulations | — | 20.1% |
| Vectara Hallucination Rate | 9.5% | — |

## Multilingual

- GLM-4.6: 53.5 (#66)
- Grok-2 (Dec 2024): 43.1 (#188)

| Benchmark | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1426 | 1282 |
| LMArena Chinese | 1499 | 1289 |
| LMArena French | 1459 | 1318 |
| LMArena German | 1447 | 1287 |
| LMArena Japanese | 1393 | 1244 |
| LMArena Korean | 1400 | 1237 |
| LMArena Russian | 1419 | 1286 |
| LMArena Spanish | 1436 | 1281 |

## Instruction Following

- GLM-4.6: 74.3 (#98)
- Grok-2 (Dec 2024): 66.9 (#202)

| Benchmark | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1410 | 1270 |
| LiveBench Instruction Following | — | 69.6% |

## Long Context

- GLM-4.6: 43.4 (#94)
- Grok-2 (Dec 2024): 38.8 (#190)

| Benchmark | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1422 | 1276 |

## Writing & Preference

- GLM-4.6: 61.1 (#90)
- Grok-2 (Dec 2024): 48.6 (#198)

| Benchmark | GLM-4.6 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1440 | 1305 |
| LMArena Creative Writing | 1411 | 1284 |
| LMArena Multi-Turn | 1427 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 1411 | — |
| LiveBench Language | — | 45.6% |

## FAQ

### Is GLM-4.6 better than Grok-2 (Dec 2024)?

GLM-4.6 is the stronger model overall, scoring 41.4 to 33.7 on the Noometry Index.

### Is GLM-4.6 or Grok-2 (Dec 2024) better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 33.3 in the Noometry coding category.

### How many benchmarks do GLM-4.6 and Grok-2 (Dec 2024) share?

18 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Grok-2 (Dec 2024) has 34.