# GPT-5.4 mini vs Grok-3 mini

> GPT-5.4 mini is the stronger model overall, scoring 45.0 to 41.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-grok-3-mini
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GPT-5.4 mini scores higher in 7 categories and Grok-3 mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 mini leads 30.4 to 13.6.
- The biggest single-benchmark swing is ARC-AGI-1: 63.7% for GPT-5.4 mini and 16.5% for Grok-3 mini.

## Snapshot

| | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 45.0 | 41.2 |
| Rank | 76 | 141 |
| Context | 400K | — |
| Input $/M | $0.75 | — |
| Output $/M | $4.50 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 mini: 45.2 (#72)
- Grok-3 mini: 40.8 (#131)

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| WeirdML | 60.3% | 42.6% |
| LMArena Coding | 1438 | 1379 |
| FrontierCode | 27% | — |
| Aider Polyglot | — | 49.3% |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.9 (#81)
- Grok-3 mini: —

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.4 (#85)
- Grok-3 mini: 13.6 (#334)

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 18.9% | 0.4% |
| Kagi LLM Benchmark | 37.9% | 61.3% |
| ARC-AGI-1 | 63.7% | 16.5% |
| LMArena Hard Prompts | 1424 | 1375 |
| Epoch Capabilities Index | 148.84 | 140.35 |
| NYT Connections (extended) | 61.8% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.5 (#75)
- Grok-3 mini: 42.1 (#85)

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 77.8% |
| LMArena Math | 1419 | 1386 |
| FrontierMath (Feb 2025 set) | 28.3% | 5.9% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| ProofBench | 21% | — |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.5 (#67)
- Grok-3 mini: 46.4 (#81)

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 86.9% | 76.3% |
| LMArena Expert | 1435 | 1395 |
| SimpleQA Verified | 29.4% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | — | 67.5% |

## Multimodal

- GPT-5.4 mini: 39.7 (#56)
- Grok-3 mini: —

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 51.9 (#96)
- Grok-3 mini: 48.1 (#145)

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1405 | 1352 |
| LMArena Chinese | 1446 | 1387 |
| LMArena French | 1440 | 1357 |
| LMArena German | 1409 | 1349 |
| LMArena Japanese | 1374 | 1342 |
| LMArena Korean | 1368 | 1335 |
| LMArena Russian | 1417 | 1353 |
| LMArena Spanish | 1405 | 1381 |

## Instruction Following

- GPT-5.4 mini: 74.1 (#102)
- Grok-3 mini: 78.5 (#9)

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1405 | 1357 |
| IFEval | — | 95.1% |

## Long Context

- GPT-5.4 mini: 43.0 (#112)
- Grok-3 mini: 41.0 (#147)

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1407 | 1372 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- GPT-5.4 mini: 64.0 (#58)
- Grok-3 mini: 52.5 (#169)

| Benchmark | GPT-5.4 mini | Grok-3 mini |
|---|---|---|
| LMArena Text | 1412 | 1370 |
| LMArena Creative Writing | 1370 | 1342 |
| LMArena Multi-Turn | 1429 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 1665 | — |
| WildBench | — | 65.1% |

## FAQ

### Is GPT-5.4 mini better than Grok-3 mini?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 41.2 on the Noometry Index.

### Is GPT-5.4 mini or Grok-3 mini better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 40.8 in the Noometry coding category.

### How many benchmarks do GPT-5.4 mini and Grok-3 mini share?

25 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Grok-3 mini has 35.