# GPT-4.1 nano vs Grok-3 mini

> Grok-3 mini is the stronger model overall, scoring 41.2 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-1-nano-vs-grok-3-mini
- Last updated: 2026-10-12
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and Grok-3 mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 21.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 28.9% for GPT-4.1 nano and 77.8% for Grok-3 mini.

## Snapshot

| | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 27.9 | 41.2 |
| Rank | 327 | 141 |
| Context | 1.05M | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.40 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.1 nano: 24.1 (#330)
- Grok-3 mini: 40.8 (#131)

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| Aider Polyglot | 8.9% | 49.3% |
| WeirdML | 19% | 42.6% |
| LMArena Coding | 1306 | 1379 |
| SciCode | 25.9% | — |

## Agentic & Tool Use

- GPT-4.1 nano: 26.5 (#104)
- Grok-3 mini: —

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |

## Reasoning

- GPT-4.1 nano: 8.5 (#349)
- Grok-3 mini: 13.6 (#334)

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 0% | 0.4% |
| Kagi LLM Benchmark | 33.3% | 61.3% |
| ARC-AGI-1 | 0% | 16.5% |
| LMArena Hard Prompts | 1286 | 1375 |
| Epoch Capabilities Index | 129.62 | 140.35 |
| CritPt | 0% | — |
| DTBench | 52.5% | — |
| LMCA | 5.5% | — |

## Math

- GPT-4.1 nano: 26.9 (#252)
- Grok-3 mini: 42.1 (#85)

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | 77.8% |
| Omni-MATH | 36.7% | 31.8% |
| LMArena Math | 1274 | 1386 |
| MATH Level 5 | 70% | 90.9% |
| FrontierMath (Feb 2025 set) | 1% | 5.9% |

## Knowledge

- GPT-4.1 nano: 21.8 (#273)
- Grok-3 mini: 46.4 (#81)

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 48.9% | 76.3% |
| MMLU-Pro | 55% | 79.9% |
| GPQA (HELM) | 50.7% | 67.5% |
| LMArena Expert | 1272 | 1395 |
| SimpleQA Verified | 6% | — |
| Confabulations | — | 10.8% |

## Multimodal

- GPT-4.1 nano: 29.2 (#113)
- Grok-3 mini: —

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1063 | — |

## Multilingual

- GPT-4.1 nano: 41.6 (#205)
- Grok-3 mini: 48.1 (#145)

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1260 | 1352 |
| LMArena Chinese | 1270 | 1387 |
| LMArena German | 1288 | 1349 |
| LMArena Japanese | 1198 | 1342 |
| LMArena Russian | 1261 | 1353 |
| LMArena French | — | 1357 |
| LMArena Korean | — | 1335 |
| LMArena Spanish | — | 1381 |

## Instruction Following

- GPT-4.1 nano: 67.8 (#193)
- Grok-3 mini: 78.5 (#9)

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| IFEval | 84.3% | 95.1% |
| LMArena Instruction Following | 1267 | 1357 |

## Long Context

- GPT-4.1 nano: 23.7 (#296)
- Grok-3 mini: 41.0 (#147)

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | 25% | 66.7% |
| LMArena Longer Query | 1283 | 1372 |

## Writing & Preference

- GPT-4.1 nano: 40.5 (#243)
- Grok-3 mini: 52.5 (#169)

| Benchmark | GPT-4.1 nano | Grok-3 mini |
|---|---|---|
| LMArena Text | 1285 | 1370 |
| LMArena Creative Writing | 1260 | 1342 |
| WildBench | 81.2% | 65.1% |
| LMArena Multi-Turn | 1277 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 946 | — |

## FAQ

### Is GPT-4.1 nano better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.2 to 27.9 on the Noometry Index.

### Is GPT-4.1 nano or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 24.1 in the Noometry coding category.

### How many benchmarks do GPT-4.1 nano and Grok-3 mini share?

30 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Grok-3 mini has 35.