# Codestral vs GPT-6 Astra

> GPT-6 Astra is the stronger model overall, scoring 70.8 to 30.6 on the Noometry Index. Codestral costs 44× less per token, which makes it the better buy when GPT-6 Astra's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/codestral-vs-gpt-6-astra
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and GPT-6 Astra in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 19.8.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $10 / $50 for GPT-6 Astra.
- GPT-6 Astra accepts more context: 1.05M tokens versus 256K.

## Snapshot

| | Codestral | GPT-6 Astra |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.6 | 70.8 |
| Rank | 290 | 1 |
| Context | 256K | 1.05M |
| Input $/M | $0.30 | $10 |
| Output $/M | $0.90 | $50 |
| Weights | Proprietary | Proprietary |

## Coding

- Codestral: 27.3 (#321)
- GPT-6 Astra: 73.7 (#2)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| ALE-Bench | 137.78 | 2,951 |
| DeepSWE | — | 74.1% |
| FrontierCode | — | 53.3% |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1786 |
| FrontierSWE | — | 65.5% |
| SciCode | — | 56.5% |
| GSO | — | 79.4% |
| WeirdML | — | 93.6% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1487 |
| MirrorCode | — | 46.7% |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- GPT-6 Astra: 52.9 (#3)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| APEX-Agents | — | 64.7% |
| Remote Labor Index | — | 20.8% |
| BALROG | — | 68.3% |
| GDP.pdf | — | 34.2% |
| Vending-Bench 2 | — | 15,515 |

## Reasoning

- Codestral: 19.8 (#251)
- GPT-6 Astra: 85.1 (#1)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| ARC-AGI-2 | — | 95% |
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 98.1% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 31.7% |
| Chess Puzzles | — | 72% |
| EBR-Bench | — | 76.2% |
| LMArena Hard Prompts | — | 1462 |
| Mystery Game Puzzles | — | 84% |
| DTBench | — | 97.3% |
| LMCA | — | 64.4% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 166.45 |

## Math

- Codestral: —
- GPT-6 Astra: 93.5 (#2)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 93.7% |
| FrontierMath Tier 4 | — | 97.6% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 99% |
| LMArena Math | — | 1465 |
| FrontierMath Erdős | — | 2.9% |

## Knowledge

- Codestral: —
- GPT-6 Astra: 75.3 (#1)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| GPQA Diamond | — | 95.8% |
| Humanity's Last Exam | — | 54.8% |
| SimpleQA Verified | — | 75.6% |
| Vectara Hallucination Rate | — | 8.7% |
| LMArena Expert | — | 1483 |

## Multimodal

- Codestral: —
- GPT-6 Astra: 55.0 (#3)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| LMArena Vision | — | 1281 |
| Blueprint-Bench 2 | — | 49.7% |
| Furniture Assembly | — | 80% |
| LMArena Document | — | 1468 |

## Multilingual

- Codestral: —
- GPT-6 Astra: 53.7 (#61)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| LMArena Non-English | — | 1430 |
| LMArena Chinese | — | 1484 |
| LMArena French | — | 1456 |
| LMArena German | — | 1440 |
| LMArena Japanese | — | 1379 |
| LMArena Korean | — | 1426 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1407 |

## Instruction Following

- Codestral: —
- GPT-6 Astra: 76.3 (#44)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| LMArena Instruction Following | — | 1450 |

## Long Context

- Codestral: —
- GPT-6 Astra: 44.5 (#62)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| LMArena Longer Query | — | 1456 |

## Writing & Preference

- Codestral: —
- GPT-6 Astra: 75.3 (#7)

| Benchmark | Codestral | GPT-6 Astra |
|---|---|---|
| LMArena Text | — | 1441 |
| LMArena Creative Writing | — | 1418 |
| EQ-Bench Creative Writing | — | 2173 |
| LMArena Multi-Turn | — | 1448 |

## FAQ

### Is Codestral better than GPT-6 Astra?

GPT-6 Astra is the stronger model overall, scoring 70.8 to 30.6 on the Noometry Index. Codestral costs 44× less per token, which makes it the better buy when GPT-6 Astra's lead doesn't matter for your workload.

### Which is cheaper, Codestral or GPT-6 Astra?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-6 Astra lists at $10 and $50.

### Is Codestral or GPT-6 Astra better for coding?

GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 27.3 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Astra does, with 1.05M tokens against 256K.

### How many benchmarks do Codestral and GPT-6 Astra share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and GPT-6 Astra has 56.