# GPT-4o mini vs Grok-3 mini

> Grok-3 mini is the stronger model overall, scoring 41.0 to 25.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4o-mini-vs-grok-3-mini
- Last updated: 2026-10-10
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Grok-3 mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 40.3 to 9.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 77.8% for Grok-3 mini.

## Snapshot

| | GPT-4o mini | Grok-3 mini |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 25.4 | 41.0 |
| Rank | 337 | 130 |
| Context | 128K | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4o mini: 21.6 (#330)
- Grok-3 mini: 40.4 (#126)

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| Aider Polyglot | 3.6% | 49.3% |
| WeirdML | 11.8% | 42.6% |
| LMArena Coding | 1290 | 1380 |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |

## Agentic & Tool Use

- GPT-4o mini: 27.2 (#95)
- Grok-3 mini: —

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| BALROG | 17.4% | — |

## Reasoning

- GPT-4o mini: 8.7 (#343)
- Grok-3 mini: 13.8 (#323)

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 0% | 0.4% |
| Kagi LLM Benchmark | 28.8% | 61.3% |
| LMArena Hard Prompts | 1267 | 1374 |
| Epoch Capabilities Index | 126.56 | 140.35 |
| SimpleBench | 10.7% | — |
| ARC-AGI-1 | — | 16.5% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |

## Math

- GPT-4o mini: 9.9 (#307)
- Grok-3 mini: 40.3 (#78)

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 77.8% |
| Omni-MATH | 28% | 31.8% |
| LMArena Math | 1267 | 1386 |
| MATH Level 5 | 52.6% | 90.9% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| LiveBench Math | 36.3% | — |
| FrontierMath (Feb 2025 set) | — | 5.9% |
| GSM8K | 91.3% | — |

## Knowledge

- GPT-4o mini: 17.7 (#279)
- Grok-3 mini: 46.3 (#75)

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 37.7% | 76.3% |
| MMLU-Pro | 60.3% | 79.9% |
| Confabulations | 37.2% | 10.8% |
| GPQA (HELM) | 36.8% | 67.5% |
| LMArena Expert | 1235 | 1395 |
| SimpleQA Verified | 8.3% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |

## Multimodal

- GPT-4o mini: 25.3 (#117)
- Grok-3 mini: —

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |

## Multilingual

- GPT-4o mini: 42.2 (#194)
- Grok-3 mini: 48.3 (#141)

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1266 | 1352 |
| LMArena Chinese | 1264 | 1387 |
| LMArena French | 1296 | 1357 |
| LMArena German | 1272 | 1350 |
| LMArena Japanese | 1216 | 1343 |
| LMArena Korean | 1195 | 1336 |
| LMArena Russian | 1275 | 1352 |
| LMArena Spanish | 1276 | 1379 |

## Instruction Following

- GPT-4o mini: 62.1 (#234)
- Grok-3 mini: 78.7 (#8)

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| IFEval | 78.2% | 95.1% |
| LMArena Instruction Following | 1259 | 1356 |
| LiveBench Instruction Following | 56.8% | — |

## Long Context

- GPT-4o mini: 39.1 (#181)
- Grok-3 mini: 41.0 (#142)

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1289 | 1372 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- GPT-4o mini: 39.7 (#243)
- Grok-3 mini: 52.7 (#163)

| Benchmark | GPT-4o mini | Grok-3 mini |
|---|---|---|
| LMArena Text | 1286 | 1370 |
| LMArena Creative Writing | 1268 | 1342 |
| Short-Story Creative Writing | 67.2% | 73.5% |
| WildBench | 79.1% | 65.1% |
| LMArena Multi-Turn | 1285 | 1355 |
| EQ-Bench Creative Writing | 873 | — |
| LiveBench Language | 28.6% | — |

## FAQ

### Is GPT-4o mini better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.0 to 25.4 on the Noometry Index.

### Is GPT-4o mini or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 21.6 in the Noometry coding category.

### How many benchmarks do GPT-4o mini and Grok-3 mini share?

32 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Grok-3 mini has 35.