# Grok-3 mini vs Qwen2.5 72B Instruct

> Grok-3 mini is the stronger model overall, scoring 41.2 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Qwen2.5 72B Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 42.1 to 19.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 8.1% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 31.9 |
| Rank | 141 | 267 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.8 (#131)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 42.6% | 16% |
| LMArena Coding | 1379 | 1292 |
| Aider Polyglot | 49.3% | — |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Grok-3 mini: —
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Grok-3 mini: 13.6 (#334)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1271 |
| Epoch Capabilities Index | 140.35 | 129 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Grok-3 mini: 42.1 (#85)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 8.1% |
| Omni-MATH | 31.8% | 33% |
| LMArena Math | 1386 | 1283 |
| MATH Level 5 | 90.9% | 63.2% |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.4 (#81)
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 76.3% | 49.1% |
| MMLU-Pro | 79.9% | 63.1% |
| Confabulations | 10.8% | 19.1% |
| GPQA (HELM) | 67.5% | 42.6% |
| LMArena Expert | 1395 | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Grok-3 mini: 48.1 (#145)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1352 | 1252 |
| LMArena Chinese | 1387 | 1272 |
| LMArena French | 1357 | 1280 |
| LMArena German | 1349 | 1234 |
| LMArena Japanese | 1342 | 1180 |
| LMArena Korean | 1335 | 1188 |
| LMArena Russian | 1353 | 1264 |
| LMArena Spanish | 1381 | 1256 |

## Instruction Following

- Grok-3 mini: 78.5 (#9)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | 95.1% | 80.6% |
| LMArena Instruction Following | 1357 | 1254 |

## Long Context

- Grok-3 mini: 41.0 (#147)
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1372 | 1282 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.5 (#169)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | Grok-3 mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1370 | 1269 |
| LMArena Creative Writing | 1342 | 1221 |
| WildBench | 65.1% | 80.2% |
| LMArena Multi-Turn | 1355 | 1272 |
| Short-Story Creative Writing | 73.5% | — |

## FAQ

### Is Grok-3 mini better than Qwen2.5 72B Instruct?

Grok-3 mini is the stronger model overall, scoring 41.2 to 31.9 on the Noometry Index.

### Is Grok-3 mini or Qwen2.5 72B Instruct better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 33.2 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and Qwen2.5 72B Instruct share?

28 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen2.5 72B Instruct has 43.