# Grok-3 mini vs Qwen1.5-7B

> Grok-3 mini is the stronger model overall, scoring 41.0 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-qwen1-5-7b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Qwen1.5-7B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.7 to 54.4.
- Qwen1.5-7B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | Qwen1.5-7B |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 41.0 | 30.8 |
| Rank | 130 | 270 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.4 (#126)
- Qwen1.5-7B: 31.6 (#271)

| Benchmark | Grok-3 mini | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1380 | 1107 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |

## Reasoning

- Grok-3 mini: 13.8 (#323)
- Qwen1.5-7B: 19.5 (#237)

| Benchmark | Grok-3 mini | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1066 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |

## Math

- Grok-3 mini: 40.3 (#78)
- Qwen1.5-7B: 29.0 (#222)

| Benchmark | Grok-3 mini | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1386 | 1080 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.3 (#75)
- Qwen1.5-7B: 28.2 (#239)

| Benchmark | Grok-3 mini | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1395 | 1055 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
| MMLU | — | 62.6% |

## Multilingual

- Grok-3 mini: 48.3 (#141)
- Qwen1.5-7B: 28.6 (#266)

| Benchmark | Grok-3 mini | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1352 | 1058 |
| LMArena Chinese | 1387 | 1140 |
| LMArena Russian | 1352 | 1006 |
| LMArena French | 1357 | — |
| LMArena German | 1350 | — |
| LMArena Japanese | 1343 | — |
| LMArena Korean | 1336 | — |
| LMArena Spanish | 1379 | — |

## Instruction Following

- Grok-3 mini: 78.7 (#8)
- Qwen1.5-7B: 54.4 (#276)

| Benchmark | Grok-3 mini | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1356 | 1058 |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#142)
- Qwen1.5-7B: 33.1 (#261)

| Benchmark | Grok-3 mini | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1372 | 1090 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.7 (#163)
- Qwen1.5-7B: 29.8 (#288)

| Benchmark | Grok-3 mini | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1370 | 1084 |
| LMArena Creative Writing | 1342 | 1035 |
| LMArena Multi-Turn | 1355 | 1061 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |

## FAQ

### Is Grok-3 mini better than Qwen1.5-7B?

Grok-3 mini is the stronger model overall, scoring 41.0 to 30.8 on the Noometry Index.

### Is Grok-3 mini or Qwen1.5-7B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 31.6 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and Qwen1.5-7B share?

12 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen1.5-7B has 13.