# Grok-3 mini vs Grok 4.7

> Grok 4.7 is the stronger model overall, scoring 53.1 to 41.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-grok-4-7
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and Grok 4.7 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 49.1 to 13.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 98.1% for Grok 4.7.

## Snapshot

| | Grok-3 mini | Grok 4.7 |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 41.2 | 53.1 |
| Rank | 141 | 37 |
| Context | — | 500K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Grok-3 mini: 40.8 (#131)
- Grok 4.7: 58.0 (#18)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| LMArena Coding | 1379 | 1427 |
| FrontierCode | — | 47.6% |
| Aider Polyglot | 49.3% | — |
| CursorBench | — | 46.3% |
| LMArena WebDev | — | 1639 |
| FrontierSWE | — | 29.5% |
| SciCode | — | 57.8% |
| WeirdML | 42.6% | — |

## Agentic & Tool Use

- Grok-3 mini: —
- Grok 4.7: 36.7 (#37)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| APEX-Agents | — | 54.6% |
| GDP.pdf | — | 22.8% |
| Vending-Bench 2 | — | 10,537 |

## Reasoning

- Grok-3 mini: 13.6 (#334)
- Grok 4.7: 49.1 (#40)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1413 |
| Epoch Capabilities Index | 140.35 | 153.53 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 76.8% |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 18% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 96% |
| LMCA | — | 49.4% |

## Math

- Grok-3 mini: 42.1 (#85)
- Grok 4.7: 57.8 (#39)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 98.1% |
| LMArena Math | 1386 | 1407 |
| FrontierMath (Tiers 1-3) | — | 53% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 34% |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.4 (#81)
- Grok 4.7: 62.8 (#22)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| GPQA Diamond | 76.3% | 92.7% |
| LMArena Expert | 1395 | 1422 |
| SimpleQA Verified | — | 56% |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |

## Multimodal

- Grok-3 mini: —
- Grok 4.7: 35.5 (#87)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| LMArena Vision | — | 1228 |
| Blueprint-Bench 2 | — | 32.5% |
| Furniture Assembly | — | 20.8% |

## Multilingual

- Grok-3 mini: 48.1 (#145)
- Grok 4.7: 50.8 (#116)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1352 | 1389 |
| LMArena Chinese | 1387 | 1455 |
| LMArena French | 1357 | 1455 |
| LMArena Russian | 1353 | 1397 |
| LMArena Spanish | 1381 | 1400 |
| LMArena German | 1349 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |

## Instruction Following

- Grok-3 mini: 78.5 (#9)
- Grok 4.7: 74.1 (#105)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1404 |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#147)
- Grok 4.7: 43.1 (#104)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1372 | 1413 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.5 (#169)
- Grok 4.7: 70.0 (#24)

| Benchmark | Grok-3 mini | Grok 4.7 |
|---|---|---|
| LMArena Text | 1370 | 1399 |
| LMArena Creative Writing | 1342 | 1391 |
| LMArena Multi-Turn | 1355 | 1393 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 2007 |
| WildBench | 65.1% | — |

## FAQ

### Is Grok-3 mini better than Grok 4.7?

Grok 4.7 is the stronger model overall, scoring 53.1 to 41.2 on the Noometry Index.

### Is Grok-3 mini or Grok 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 40.8 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and Grok 4.7 share?

17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Grok 4.7 has 39.