# GPT-5-Codex vs Grok 4.6

> Grok 4.6 is the stronger model overall, scoring 56.9 to 37.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-grok-4-6
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5-Codex scores higher in 0 categories and Grok 4.6 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 30.9.
- The biggest single-benchmark swing is WeirdML: 54.5% for GPT-5-Codex and 67.3% for Grok 4.6.
- Grok 4.6 is cheaper at $2 / $6 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- Grok 4.6 accepts more context: 500K tokens versus 400K.

## Snapshot

| | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 37.9 | 56.9 |
| Rank | 192 | 21 |
| Context | 400K | 500K |
| Input $/M | $1.25 | $2 |
| Output $/M | $10 | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5-Codex: 42.4 (#103)
- Grok 4.6: 58.5 (#16)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| WeirdML | 54.5% | 67.3% |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| LMArena Coding | — | 1465 |
| ALE-Bench | — | 1,508 |

## Agentic & Tool Use

- GPT-5-Codex: 31.0 (#72)
- Grok 4.6: 39.4 (#27)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| APEX-Agents | — | 65.3% |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |

## Reasoning

- GPT-5-Codex: 30.9 (#83)
- Grok 4.6: 61.4 (#20)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| ARC-AGI-2 | — | 67.1% |
| SimpleBench | — | 75.9% |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EBR-Bench | — | 30.5% |
| LMArena Hard Prompts | — | 1447 |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.3% |
| LMCA | — | 48.5% |
| Epoch Capabilities Index | — | 156.44 |

## Math

- GPT-5-Codex: —
- Grok 4.6: 67.0 (#24)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 51% |
| LMArena Math | — | 1423 |

## Knowledge

- GPT-5-Codex: —
- Grok 4.6: 63.3 (#20)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| GPQA Diamond | — | 94% |
| SimpleQA Verified | — | 49.3% |
| LMArena Expert | — | 1467 |

## Multimodal

- GPT-5-Codex: —
- Grok 4.6: 43.6 (#23)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |

## Multilingual

- GPT-5-Codex: —
- Grok 4.6: 53.0 (#74)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| LMArena Non-English | — | 1420 |
| LMArena Chinese | — | 1480 |
| LMArena French | — | 1461 |
| LMArena German | — | 1431 |
| LMArena Japanese | — | 1376 |
| LMArena Korean | — | 1397 |
| LMArena Russian | — | 1422 |
| LMArena Spanish | — | 1404 |

## Instruction Following

- GPT-5-Codex: —
- Grok 4.6: 75.4 (#63)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | — | 1431 |

## Long Context

- GPT-5-Codex: —
- Grok 4.6: 44.5 (#66)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | — | 1454 |

## Writing & Preference

- GPT-5-Codex: —
- Grok 4.6: 62.3 (#80)

| Benchmark | GPT-5-Codex | Grok 4.6 |
|---|---|---|
| LMArena Text | — | 1428 |
| LMArena Creative Writing | — | 1428 |
| LMArena Multi-Turn | — | 1425 |

## FAQ

### Is GPT-5-Codex better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.9 to 37.9 on the Noometry Index.

### Which is cheaper, GPT-5-Codex or Grok 4.6?

Grok 4.6 is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

### Is GPT-5-Codex or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.6 does, with 500K tokens against 400K.

### How many benchmarks do GPT-5-Codex and Grok 4.6 share?

1 benchmark has published results for both models. GPT-5-Codex has 3 scored results on Noometry and Grok 4.6 has 49.