# GLM-5.1 vs Grok-2 (Dec 2024)

> GLM-5.1 is the stronger model overall, scoring 47.6 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-grok-2
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. GLM-5.1 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-5.1 leads 49.0 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 11.5% for Grok-2 (Dec 2024).
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 47.6 | 33.4 |
| Rank | 51 | 233 |
| Context | 200K | — |
| Input $/M | $1.40 | — |
| Output $/M | $4.40 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-5.1: 48.5 (#52)
- Grok-2 (Dec 2024): 32.9 (#254)

| Benchmark | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 57.1% | 22.2% |
| LMArena Coding | 1486 | 1288 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Grok-2 (Dec 2024): —

| Benchmark | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Grok-2 (Dec 2024): 16.4 (#294)

| Benchmark | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 55.1% | 22.7% |
| LMArena Hard Prompts | 1472 | 1272 |
| Epoch Capabilities Index | 149.86 | 130.48 |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 54.8% |
| DTBench | — | 65.2% |
| LiveBench Data Analysis | — | 54.5% |
| LiveBench | — | 54.3% |

## Math

- GLM-5.1: 49.0 (#48)
- Grok-2 (Dec 2024): 19.6 (#278)

| Benchmark | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 11.5% |
| LMArena Math | 1472 | 1283 |
| FrontierMath (Feb 2025 set) | 33.4% | 0.7% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Grok-2 (Dec 2024): 29.8 (#225)

| Benchmark | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 89.9% | 53.8% |
| LMArena Expert | 1477 | 1254 |
| SimpleQA Verified | 34% | — |
| Confabulations | — | 20.1% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Grok-2 (Dec 2024): 43.3 (#183)

| Benchmark | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1448 | 1282 |
| LMArena Chinese | 1516 | 1289 |
| LMArena French | 1478 | 1317 |
| LMArena German | 1466 | 1287 |
| LMArena Japanese | 1436 | 1244 |
| LMArena Korean | 1423 | 1237 |
| LMArena Russian | 1453 | 1286 |
| LMArena Spanish | 1467 | 1281 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Grok-2 (Dec 2024): 67.1 (#197)

| Benchmark | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1451 | 1270 |
| LiveBench Instruction Following | — | 69.6% |

## Long Context

- GLM-5.1: 44.9 (#51)
- Grok-2 (Dec 2024): 38.7 (#186)

| Benchmark | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1467 | 1276 |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Grok-2 (Dec 2024): 48.8 (#192)

| Benchmark | GLM-5.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1462 | 1305 |
| LMArena Creative Writing | 1454 | 1284 |
| LMArena Multi-Turn | 1473 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 1592 | — |
| LiveBench Language | — | 45.6% |

## FAQ

### Is GLM-5.1 better than Grok-2 (Dec 2024)?

GLM-5.1 is the stronger model overall, scoring 47.6 to 33.4 on the Noometry Index.

### Is GLM-5.1 or Grok-2 (Dec 2024) better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 32.9 in the Noometry coding category.

### How many benchmarks do GLM-5.1 and Grok-2 (Dec 2024) share?

23 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Grok-2 (Dec 2024) has 34.