# GPT-4 vs Grok 4.3

> Grok 4.3 is the stronger model overall, scoring 43.8 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-vs-grok-4-3
- Last updated: 2026-10-11
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Grok 4.3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.3 leads 46.0 to 10.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 93.3% for Grok 4.3.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $30 / $60 for GPT-4.
- Grok 4.3 accepts more context: 1M tokens versus 8K.

## Snapshot

| | GPT-4 | Grok 4.3 |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 29.1 | 43.8 |
| Rank | 316 | 86 |
| Context | 8K | 1M |
| Input $/M | $30 | $1.25 |
| Output $/M | $60 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4: 31.6 (#283)
- Grok 4.3: 41.6 (#121)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| WeirdML | 12.4% | 49.9% |
| LMArena Coding | 1254 | 1415 |
| LMArena WebDev | — | 1357 |
| SciCode | — | 47.3% |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| ALE-Bench | — | 944.17 |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- Grok 4.3: 27.7 (#99)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| METR Time Horizons | 36.1% | — |
| Vending-Bench 2 | — | 35.26 |

## Reasoning

- GPT-4: 17.8 (#289)
- Grok 4.3: 35.9 (#68)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| Chess Puzzles | 4% | 25% |
| LMArena Hard Prompts | 1241 | 1396 |
| DTBench | 62.7% | 90.7% |
| LMCA | 17.1% | 38.3% |
| Epoch Capabilities Index | 125.89 | 149.16 |
| ForecastBench | 57.8 | 60.3 |
| NYT Connections (extended) | — | 55.2% |
| CritPt | — | 8% |
| Mystery Game Puzzles | 12% | — |
| BIG-Bench Hard | 75.1% | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |

## Math

- GPT-4: 10.8 (#309)
- Grok 4.3: 46.0 (#74)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 93.3% |
| LMArena Math | 1269 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| ProofBench | — | 11% |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |

## Knowledge

- GPT-4: 18.4 (#282)
- Grok 4.3: 52.5 (#62)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 35.7% | 88.8% |
| LMArena Expert | 1211 | 1385 |
| SimpleQA Verified | — | 33.2% |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |

## Multimodal

- GPT-4: —
- Grok 4.3: 31.6 (#104)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1229 |
| Blueprint-Bench 2 | — | 0% |

## Multilingual

- GPT-4: 40.6 (#215)
- Grok 4.3: 50.5 (#120)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1246 | 1385 |
| LMArena Chinese | 1242 | 1422 |
| LMArena French | 1283 | 1412 |
| LMArena German | 1251 | 1395 |
| LMArena Japanese | 1209 | 1379 |
| LMArena Korean | 1184 | 1356 |
| LMArena Russian | 1251 | 1399 |
| LMArena Spanish | 1261 | 1398 |

## Instruction Following

- GPT-4: 65.3 (#222)
- Grok 4.3: 72.1 (#140)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1366 |

## Long Context

- GPT-4: 37.7 (#212)
- Grok 4.3: 42.5 (#123)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1244 | 1393 |

## Writing & Preference

- GPT-4: 34.9 (#268)
- Grok 4.3: 58.5 (#118)

| Benchmark | GPT-4 | Grok 4.3 |
|---|---|---|
| LMArena Text | 1263 | 1397 |
| LMArena Creative Writing | 1244 | 1380 |
| LMArena Multi-Turn | 1257 | 1406 |
| EQ-Bench Creative Writing | 752 | — |
| EQ-Bench 4 | — | 1075 |

## FAQ

### Is GPT-4 better than Grok 4.3?

Grok 4.3 is the stronger model overall, scoring 43.8 to 29.1 on the Noometry Index.

### Which is cheaper, GPT-4 or Grok 4.3?

Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-4 lists at $30 and $60.

### Is GPT-4 or Grok 4.3 better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.6 versus 31.6 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.3 does, with 1M tokens against 8K.

### How many benchmarks do GPT-4 and Grok 4.3 share?

25 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Grok 4.3 has 40.