# GPT-4.1 vs Grok 4

> Grok 4 is the stronger model overall, scoring 48.1 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-1-vs-grok-4
- Last updated: 2026-10-10
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. GPT-4.1 scores higher in 2 categories and Grok 4 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4 leads 48.4 to 22.3.
- The biggest single-benchmark swing is ARC-AGI-1: 5.5% for GPT-4.1 and 66.7% for Grok 4.

## Snapshot

| | GPT-4.1 | Grok 4 |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 35.9 | 48.1 |
| Rank | 219 | 56 |
| Context | 1.05M | — |
| Input $/M | $2 | — |
| Output $/M | $8 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.1: 34.4 (#238)
- Grok 4: 50.3 (#46)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| Aider Polyglot | 52.4% | 79.6% |
| WeirdML | 39% | 45.7% |
| LMArena Coding | 1391 | 1408 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |

## Agentic & Tool Use

- GPT-4.1: 34.7 (#43)
- Grok 4: 32.3 (#68)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | 63% |
| Terminal-Bench | — | 27.2% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |

## Reasoning

- GPT-4.1: 11.7 (#339)
- Grok 4: 36.7 (#65)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 0.4% | 16% |
| SimpleBench | 27% | 60.5% |
| Kagi LLM Benchmark | 52.3% | 73.6% |
| ARC-AGI-1 | 5.5% | 66.7% |
| Chess Puzzles | 6% | 28% |
| LMArena Hard Prompts | 1384 | 1409 |
| Epoch Capabilities Index | 136.78 | 146.44 |
| ForecastBench | 61.5 | 60.9 |
| EnigmaEval | 2.2% | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |

## Math

- GPT-4.1: 22.3 (#280)
- Grok 4: 48.4 (#64)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 84% |
| Omni-MATH | 47.1% | 60.3% |
| LMArena Math | 1370 | 1422 |
| FrontierMath (Feb 2025 set) | 5.5% | 19.7% |
| FrontierMath Tier 4 (v1) | 0% | 2.1% |
| FrontierMath (Tiers 1-3) | 6% | — |
| MATH Level 5 | 83% | — |

## Knowledge

- GPT-4.1: 37.1 (#160)
- Grok 4: 53.8 (#55)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| GPQA Diamond | 66.9% | 87% |
| MMLU-Pro | 81.1% | 85.1% |
| GPQA (HELM) | 65.9% | 72.7% |
| LMArena Expert | 1364 | 1415 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 5.6% | — |

## Multimodal

- GPT-4.1: 38.2 (#67)
- Grok 4: 33.7 (#94)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| LMArena Vision | 1211 | 1210 |
| GeoBench | 72% | 45% |

## Multilingual

- GPT-4.1: 49.4 (#133)
- Grok 4: 51.8 (#103)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| LMArena Non-English | 1370 | 1403 |
| LMArena Chinese | 1382 | 1427 |
| LMArena French | 1382 | 1418 |
| LMArena German | 1381 | 1429 |
| LMArena Japanese | 1319 | 1394 |
| LMArena Korean | 1339 | 1377 |
| LMArena Russian | 1377 | 1410 |
| LMArena Spanish | 1376 | 1420 |

## Instruction Following

- GPT-4.1: 71.3 (#153)
- Grok 4: 79.2 (#5)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| IFEval | 83.8% | 94.9% |
| LMArena Instruction Following | 1367 | 1387 |

## Long Context

- GPT-4.1: 40.0 (#163)
- Grok 4: 63.1 (#4)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| Fiction.LiveBench | 63.9% | 94.4% |
| LMArena Longer Query | 1385 | 1409 |

## Writing & Preference

- GPT-4.1: 57.6 (#125)
- Grok 4: 58.5 (#116)

| Benchmark | GPT-4.1 | Grok 4 |
|---|---|---|
| LMArena Text | 1383 | 1411 |
| LMArena Creative Writing | 1363 | 1397 |
| WildBench | 85.4% | 79.7% |
| LMArena Multi-Turn | 1398 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| EQ-Bench Creative Writing | 1420 | — |

## FAQ

### Is GPT-4.1 better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 35.9 on the Noometry Index.

### Is GPT-4.1 or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 34.4 in the Noometry coding category.

### How many benchmarks do GPT-4.1 and Grok 4 share?

39 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Grok 4 has 48.