# Grok-3 mini vs Qwen2.5-Max

> Grok-3 mini and Qwen2.5-Max score almost the same on the Noometry Index (41.0 vs 40.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Grok-3 mini scores higher in 3 categories and Qwen2.5-Max in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.3 to 34.8.
- The biggest single-benchmark swing is Confabulations: 10.8% for Grok-3 mini and 21.8% for Qwen2.5-Max.

## Snapshot

| | Grok-3 mini | Qwen2.5-Max |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 41.0 | 40.1 |
| Rank | 130 | 142 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Grok-3 mini: 40.4 (#126)
- Qwen2.5-Max: 41.2 (#118)

| Benchmark | Grok-3 mini | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1380 | 1359 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
| LiveBench Coding | — | 64.4% |

## Reasoning

- Grok-3 mini: 13.8 (#323)
- Qwen2.5-Max: 24.6 (#144)

| Benchmark | Grok-3 mini | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1360 |
| Epoch Capabilities Index | 140.35 | 132.54 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| LiveBench | — | 62.3% |

## Math

- Grok-3 mini: 40.3 (#78)
- Qwen2.5-Max: 34.3 (#162)

| Benchmark | Grok-3 mini | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1386 | 1369 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.3 (#75)
- Qwen2.5-Max: 34.8 (#181)

| Benchmark | Grok-3 mini | Qwen2.5-Max |
|---|---|---|
| Confabulations | 10.8% | 21.8% |
| LMArena Expert | 1395 | 1337 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| GPQA (HELM) | 67.5% | — |

## Multilingual

- Grok-3 mini: 48.3 (#141)
- Qwen2.5-Max: 48.3 (#140)

| Benchmark | Grok-3 mini | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1352 | 1352 |
| LMArena Chinese | 1387 | 1382 |
| LMArena French | 1357 | 1396 |
| LMArena German | 1350 | 1350 |
| LMArena Japanese | 1343 | 1299 |
| LMArena Korean | 1336 | 1304 |
| LMArena Russian | 1352 | 1353 |
| LMArena Spanish | 1379 | 1377 |

## Instruction Following

- Grok-3 mini: 78.7 (#8)
- Qwen2.5-Max: 71.5 (#147)

| Benchmark | Grok-3 mini | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1356 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#142)
- Qwen2.5-Max: 41.3 (#137)

| Benchmark | Grok-3 mini | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1372 | 1358 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.7 (#163)
- Qwen2.5-Max: 55.6 (#141)

| Benchmark | Grok-3 mini | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1370 | 1367 |
| LMArena Creative Writing | 1342 | 1339 |
| Short-Story Creative Writing | 73.5% | 72.9% |
| LMArena Multi-Turn | 1355 | 1364 |
| WildBench | 65.1% | — |
| LiveBench Language | — | 56.3% |

## FAQ

### Is Grok-3 mini better than Qwen2.5-Max?

Grok-3 mini and Qwen2.5-Max score almost the same on the Noometry Index (41.0 vs 40.1), so choose on price, context window or the category you care about most.

### Is Grok-3 mini or Qwen2.5-Max better for coding?

They score almost the same on coding (40.4 vs 41.2); test both on your own repository before choosing.

### How many benchmarks do Grok-3 mini and Qwen2.5-Max share?

20 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen2.5-Max has 27.