# GPT-5-Codex vs Grok 4 Fast

> Grok 4 Fast is the stronger model overall, scoring 39.0 to 37.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-grok-4-fast
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. GPT-5-Codex scores higher in 3 categories and Grok 4 Fast in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5-Codex leads 41.9 to 32.3.
- The biggest single-benchmark swing is WeirdML: 54.5% for GPT-5-Codex and 42.9% for Grok 4 Fast.

## Snapshot

| | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 37.3 | 39.0 |
| Rank | 190 | 164 |
| Context | 400K | — |
| Input $/M | $1.25 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5-Codex: 41.9 (#100)
- Grok 4 Fast: 32.3 (#264)

| Benchmark | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| WeirdML | 54.5% | 42.9% |
| LMArena WebDev | — | 1160 |
| LMArena Coding | — | 1429 |

## Agentic & Tool Use

- GPT-5-Codex: 30.8 (#66)
- Grok 4 Fast: 29.3 (#80)

| Benchmark | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| τ²-bench Banking | — | 15.7% |
| Cybench | — | 30% |
| LMArena Search | — | 1171 |

## Reasoning

- GPT-5-Codex: 30.0 (#80)
- Grok 4 Fast: 22.5 (#179)

| Benchmark | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | 66.1% |
| ARC-AGI-2 | — | 5.3% |
| ARC-AGI-1 | — | 48.5% |
| LMArena Hard Prompts | — | 1413 |
| DTBench | — | 82.7% |
| Epoch Capabilities Index | — | 144.21 |
| ForecastBench | — | 60.5 |

## Math

- GPT-5-Codex: —
- Grok 4 Fast: 36.1 (#126)

| Benchmark | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| LMArena Math | — | 1419 |

## Knowledge

- GPT-5-Codex: —
- Grok 4 Fast: 31.5 (#211)

| Benchmark | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| Vectara Hallucination Rate | — | 19.7% |
| LMArena Expert | — | 1411 |

## Multilingual

- GPT-5-Codex: —
- Grok 4 Fast: 51.5 (#106)

| Benchmark | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | — | 1397 |
| LMArena Chinese | — | 1458 |
| LMArena French | — | 1433 |
| LMArena German | — | 1383 |
| LMArena Japanese | — | 1358 |
| LMArena Korean | — | 1359 |
| LMArena Russian | — | 1387 |
| LMArena Spanish | — | 1414 |

## Instruction Following

- GPT-5-Codex: —
- Grok 4 Fast: 73.4 (#116)

| Benchmark | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | — | 1388 |

## Long Context

- GPT-5-Codex: —
- Grok 4 Fast: 63.2 (#3)

| Benchmark | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| Fiction.LiveBench | — | 94.4% |
| LMArena Longer Query | — | 1415 |

## Writing & Preference

- GPT-5-Codex: —
- Grok 4 Fast: 60.2 (#96)

| Benchmark | GPT-5-Codex | Grok 4 Fast |
|---|---|---|
| LMArena Text | — | 1407 |
| LMArena Creative Writing | — | 1388 |
| LMArena Multi-Turn | — | 1414 |

## FAQ

### Is GPT-5-Codex better than Grok 4 Fast?

Grok 4 Fast is the stronger model overall, scoring 39.0 to 37.3 on the Noometry Index.

### Is GPT-5-Codex or Grok 4 Fast better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 32.3 in the Noometry coding category.

### How many benchmarks do GPT-5-Codex and Grok 4 Fast share?

2 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Grok 4 Fast has 30.