# GPT-5.6 Luna vs Mistral

> GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-6-luna-vs-mistral
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and Mistral in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.5 to 20.5.

## Snapshot

| | GPT-5.6 Luna | Mistral |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 54.7 | 29.4 |
| Rank | 24 | 297 |
| Context | 1.05M | — |
| Input $/M | $0.20 | — |
| Output $/M | $1.20 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.6 Luna: 53.9 (#25)
- Mistral: 33.2 (#249)

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| LMArena Coding | 1466 | 1162 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1517 | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |

## Agentic & Tool Use

- GPT-5.6 Luna: 35.3 (#37)
- Mistral: —

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |

## Reasoning

- GPT-5.6 Luna: 47.5 (#38)
- Mistral: 21.3 (#199)

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1149 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | 69.4% | — |
| ARC-AGI-1 | 88% | — |
| CritPt | 20.6% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| Epoch Capabilities Index | 156.32 | — |

## Math

- GPT-5.6 Luna: 77.5 (#12)
- Mistral: 20.5 (#275)

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| LMArena Math | 1455 | 1180 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 60% | — |
| Omni-MATH | — | 7.2% |

## Knowledge

- GPT-5.6 Luna: 58.6 (#31)
- Mistral: 16.3 (#283)

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| LMArena Expert | 1479 | 1125 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |

## Multimodal

- GPT-5.6 Luna: 43.0 (#22)
- Mistral: —

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| LMArena Vision | 1259 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |

## Multilingual

- GPT-5.6 Luna: 53.0 (#73)
- Mistral: 33.0 (#249)

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| LMArena Non-English | 1418 | 1129 |
| LMArena Chinese | 1469 | 1109 |
| LMArena French | 1457 | 1179 |
| LMArena German | 1459 | 1155 |
| LMArena Japanese | 1416 | 1012 |
| LMArena Korean | 1414 | 1032 |
| LMArena Russian | 1428 | 1168 |
| LMArena Spanish | 1445 | 1143 |

## Instruction Following

- GPT-5.6 Luna: 76.0 (#48)
- Mistral: 52.9 (#283)

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| LMArena Instruction Following | 1440 | 1152 |
| IFEval | — | 56.8% |

## Long Context

- GPT-5.6 Luna: 43.9 (#78)
- Mistral: 35.0 (#240)

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| LMArena Longer Query | 1437 | 1154 |

## Writing & Preference

- GPT-5.6 Luna: 68.3 (#27)
- Mistral: 37.2 (#255)

| Benchmark | GPT-5.6 Luna | Mistral |
|---|---|---|
| LMArena Text | 1432 | 1165 |
| LMArena Creative Writing | 1397 | 1158 |
| LMArena Multi-Turn | 1433 | 1147 |
| EQ-Bench Creative Writing | 1829 | — |
| WildBench | — | 66% |
| EQ-Bench 4 | 1156 | — |

## FAQ

### Is GPT-5.6 Luna better than Mistral?

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 29.4 on the Noometry Index.

### Is GPT-5.6 Luna or Mistral better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 33.2 in the Noometry coding category.

### How many benchmarks do GPT-5.6 Luna and Mistral share?

17 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and Mistral has 22.