# Grok-3 mini vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 41.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-qwen3-7-plus
- Last updated: 2026-10-11
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Grok-3 mini scores higher in 2 categories and Qwen3.7 Plus in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Plus leads 39.3 to 13.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 93.3% for Qwen3.7 Plus.

## Snapshot

| | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 45.3 |
| Rank | 141 | 72 |
| Context | — | 1M |
| Input $/M | — | $0.40 |
| Output $/M | — | $1.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Grok-3 mini: 40.8 (#131)
- Qwen3.7 Plus: 36.6 (#206)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1379 | 1473 |
| FrontierCode | — | 10.2% |
| Aider Polyglot | 49.3% | — |
| SciCode | — | 45.5% |
| WeirdML | 42.6% | — |

## Agentic & Tool Use

- Grok-3 mini: —
- Qwen3.7 Plus: 21.4 (#138)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |

## Reasoning

- Grok-3 mini: 13.6 (#334)
- Qwen3.7 Plus: 39.3 (#59)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1460 |
| Epoch Capabilities Index | 140.35 | 147.37 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |

## Math

- Grok-3 mini: 42.1 (#85)
- Qwen3.7 Plus: 50.5 (#56)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 93.3% |
| LMArena Math | 1386 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.4 (#81)
- Qwen3.7 Plus: 54.9 (#51)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 76.3% | 87.9% |
| LMArena Expert | 1395 | 1467 |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |

## Multimodal

- Grok-3 mini: —
- Qwen3.7 Plus: 41.8 (#33)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |

## Multilingual

- Grok-3 mini: 48.1 (#145)
- Qwen3.7 Plus: 54.8 (#38)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1352 | 1445 |
| LMArena Chinese | 1387 | 1510 |
| LMArena French | 1357 | 1473 |
| LMArena German | 1349 | 1471 |
| LMArena Japanese | 1342 | 1413 |
| LMArena Korean | 1335 | 1415 |
| LMArena Russian | 1353 | 1457 |
| LMArena Spanish | 1381 | 1457 |

## Instruction Following

- Grok-3 mini: 78.5 (#9)
- Qwen3.7 Plus: 75.8 (#52)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1357 | 1440 |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#147)
- Qwen3.7 Plus: 44.5 (#65)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1372 | 1455 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.5 (#169)
- Qwen3.7 Plus: 64.3 (#56)

| Benchmark | Grok-3 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1370 | 1455 |
| LMArena Creative Writing | 1342 | 1439 |
| LMArena Multi-Turn | 1355 | 1460 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |

## FAQ

### Is Grok-3 mini better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 41.2 on the Noometry Index.

### Is Grok-3 mini or Qwen3.7 Plus better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 36.6 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and Qwen3.7 Plus share?

20 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen3.7 Plus has 32.