# GPT-4 Turbo vs Grok 4

> Grok 4 is the stronger model overall, scoring 47.8 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-turbo-vs-grok-4
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Grok 4 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4 leads 46.5 to 8.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 84% for Grok 4.

## Snapshot

| | GPT-4 Turbo | Grok 4 |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 30.3 | 47.8 |
| Rank | 281 | 49 |
| Context | 128K | — |
| Input $/M | $10 | — |
| Output $/M | $30 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4 Turbo: 33.4 (#247)
- Grok 4: 49.9 (#44)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| WeirdML | 18% | 45.7% |
| LMArena Coding | 1268 | 1408 |
| Aider Polyglot | — | 79.6% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |

## Agentic & Tool Use

- GPT-4 Turbo: —
- Grok 4: 32.1 (#62)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| METR Time Horizons | 36.7% | 66.6% |
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |

## Reasoning

- GPT-4 Turbo: 14.9 (#311)
- Grok 4: 36.9 (#59)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| SimpleBench | 25.1% | 60.5% |
| Chess Puzzles | 6% | 28% |
| LMArena Hard Prompts | 1251 | 1409 |
| Epoch Capabilities Index | 127.25 | 146.46 |
| ForecastBench | 59.4 | 60.9 |
| ARC-AGI-2 | — | 16% |
| Kagi LLM Benchmark | — | 73.6% |
| ARC-AGI-1 | — | 66.7% |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |

## Math

- GPT-4 Turbo: 8.6 (#316)
- Grok 4: 46.5 (#58)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 84% |
| LMArena Math | 1272 | 1422 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| Omni-MATH | — | 60.3% |
| MATH Level 5 | 46.7% | — |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- GPT-4 Turbo: 24.3 (#263)
- Grok 4: 53.7 (#50)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| GPQA Diamond | 46.6% | 87% |
| Confabulations | 28.4% | 12.4% |
| LMArena Expert | 1223 | 1417 |
| MMLU-Pro | — | 85.1% |
| GPQA (HELM) | — | 72.7% |
| MMLU | 81.3% | — |

## Multimodal

- GPT-4 Turbo: 30.0 (#104)
- Grok 4: 33.1 (#89)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| LMArena Vision | 1090 | 1211 |
| GeoBench | — | 45% |

## Multilingual

- GPT-4 Turbo: 40.7 (#211)
- Grok 4: 52.0 (#98)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| LMArena Non-English | 1245 | 1403 |
| LMArena Chinese | 1242 | 1428 |
| LMArena French | 1275 | 1418 |
| LMArena German | 1259 | 1429 |
| LMArena Japanese | 1194 | 1396 |
| LMArena Korean | 1187 | 1376 |
| LMArena Russian | 1259 | 1409 |
| LMArena Spanish | 1260 | 1419 |

## Instruction Following

- GPT-4 Turbo: 66.0 (#211)
- Grok 4: 79.4 (#4)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1250 | 1387 |
| IFEval | — | 94.9% |

## Long Context

- GPT-4 Turbo: 38.0 (#200)
- Grok 4: 63.1 (#4)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1254 | 1409 |
| Fiction.LiveBench | — | 94.4% |

## Writing & Preference

- GPT-4 Turbo: 47.9 (#201)
- Grok 4: 58.7 (#111)

| Benchmark | GPT-4 Turbo | Grok 4 |
|---|---|---|
| LMArena Text | 1272 | 1412 |
| LMArena Creative Writing | 1269 | 1397 |
| LMArena Multi-Turn | 1267 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| WildBench | — | 79.7% |

## FAQ

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

Grok 4 is the stronger model overall, scoring 47.8 to 30.3 on the Noometry Index.

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

Grok 4 scores higher on coding benchmarks: 49.9 versus 33.4 in the Noometry coding category.

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

27 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Grok 4 has 48.