# Grok-2 (Dec 2024) vs Qwen2.5-Max

> Qwen2.5-Max is the stronger model overall, scoring 40.1 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 34.3 to 19.6.
- The biggest single-benchmark swing is LiveBench Coding: 46.4% for Grok-2 (Dec 2024) and 64.4% for Qwen2.5-Max.

## Snapshot

| | Grok-2 (Dec 2024) | Qwen2.5-Max |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 40.1 |
| Rank | 233 | 142 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Grok-2 (Dec 2024): 32.9 (#254)
- Qwen2.5-Max: 41.2 (#118)

| Benchmark | Grok-2 (Dec 2024) | Qwen2.5-Max |
|---|---|---|
| LiveBench Coding | 46.4% | 64.4% |
| LMArena Coding | 1288 | 1359 |
| WeirdML | 22.2% | — |

## Reasoning

- Grok-2 (Dec 2024): 16.4 (#294)
- Qwen2.5-Max: 24.6 (#144)

| Benchmark | Grok-2 (Dec 2024) | Qwen2.5-Max |
|---|---|---|
| LiveBench Reasoning | 54.8% | 51.4% |
| LMArena Hard Prompts | 1272 | 1360 |
| LiveBench Data Analysis | 54.5% | 67.9% |
| Epoch Capabilities Index | 130.48 | 132.54 |
| LiveBench | 54.3% | 62.3% |
| SimpleBench | 22.7% | — |
| DTBench | 65.2% | — |

## Math

- Grok-2 (Dec 2024): 19.6 (#278)
- Qwen2.5-Max: 34.3 (#162)

| Benchmark | Grok-2 (Dec 2024) | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | 54.9% | 58.4% |
| LMArena Math | 1283 | 1369 |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |

## Knowledge

- Grok-2 (Dec 2024): 29.8 (#225)
- Qwen2.5-Max: 34.8 (#181)

| Benchmark | Grok-2 (Dec 2024) | Qwen2.5-Max |
|---|---|---|
| Confabulations | 20.1% | 21.8% |
| LMArena Expert | 1254 | 1337 |
| GPQA Diamond | 53.8% | — |

## Multilingual

- Grok-2 (Dec 2024): 43.3 (#183)
- Qwen2.5-Max: 48.3 (#140)

| Benchmark | Grok-2 (Dec 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1282 | 1352 |
| LMArena Chinese | 1289 | 1382 |
| LMArena French | 1317 | 1396 |
| LMArena German | 1287 | 1350 |
| LMArena Japanese | 1244 | 1299 |
| LMArena Korean | 1237 | 1304 |
| LMArena Russian | 1286 | 1353 |
| LMArena Spanish | 1281 | 1377 |

## Instruction Following

- Grok-2 (Dec 2024): 67.1 (#197)
- Qwen2.5-Max: 71.5 (#147)

| Benchmark | Grok-2 (Dec 2024) | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | 69.6% | 75.3% |
| LMArena Instruction Following | 1270 | 1335 |

## Long Context

- Grok-2 (Dec 2024): 38.7 (#186)
- Qwen2.5-Max: 41.3 (#137)

| Benchmark | Grok-2 (Dec 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1276 | 1358 |

## Writing & Preference

- Grok-2 (Dec 2024): 48.8 (#192)
- Qwen2.5-Max: 55.6 (#141)

| Benchmark | Grok-2 (Dec 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1305 | 1367 |
| LMArena Creative Writing | 1284 | 1339 |
| Short-Story Creative Writing | 63.6% | 72.9% |
| LMArena Multi-Turn | 1290 | 1364 |
| LiveBench Language | 45.6% | 56.3% |

## FAQ

### Is Grok-2 (Dec 2024) better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.1 to 33.4 on the Noometry Index.

### Is Grok-2 (Dec 2024) or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 32.9 in the Noometry coding category.

### How many benchmarks do Grok-2 (Dec 2024) and Qwen2.5-Max share?

27 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Qwen2.5-Max has 27.