# GPT-5.6 Luna vs MiMo-V2-Pro

> GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 42.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-6-luna-vs-mimo-v2-pro
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GPT-5.6 Luna scores higher in 7 categories and MiMo-V2-Pro in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.5 to 36.7.
- The biggest single-benchmark swing is NYT Connections (extended): 69.4% for GPT-5.6 Luna and 25.8% for MiMo-V2-Pro.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 1.05M.

## Snapshot

| | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 54.7 | 42.4 |
| Rank | 24 | 102 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.20 | $0.43 |
| Output $/M | $1.20 | $0.87 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.6 Luna: 53.9 (#25)
- MiMo-V2-Pro: 43.4 (#76)

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1517 | 1433 |
| LMArena Coding | 1466 | 1476 |
| ALE-Bench | 1,667 | 785.17 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |

## Agentic & Tool Use

- GPT-5.6 Luna: 35.3 (#37)
- MiMo-V2-Pro: —

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |

## Reasoning

- GPT-5.6 Luna: 47.5 (#38)
- MiMo-V2-Pro: 21.3 (#200)

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 69.4% | 25.8% |
| LMArena Hard Prompts | 1452 | 1457 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| ARC-AGI-1 | 88% | — |
| CritPt | 20.6% | — |
| Chess Puzzles | 40% | — |
| Thematic Generalization | — | 45.9% |
| 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)
- MiMo-V2-Pro: 36.7 (#104)

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1455 | 1447 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 60% | — |

## Knowledge

- GPT-5.6 Luna: 58.6 (#31)
- MiMo-V2-Pro: 40.8 (#106)

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1479 | 1479 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |

## Multimodal

- GPT-5.6 Luna: 43.0 (#22)
- MiMo-V2-Pro: —

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Vision | 1259 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |

## Multilingual

- GPT-5.6 Luna: 53.0 (#73)
- MiMo-V2-Pro: 52.9 (#77)

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1418 | 1416 |
| LMArena Chinese | 1469 | 1455 |
| LMArena French | 1457 | 1470 |
| LMArena German | 1459 | 1417 |
| LMArena Japanese | 1416 | 1366 |
| LMArena Korean | 1414 | 1401 |
| LMArena Russian | 1428 | 1427 |
| LMArena Spanish | 1445 | 1458 |

## Instruction Following

- GPT-5.6 Luna: 76.0 (#48)
- MiMo-V2-Pro: 76.2 (#46)

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1440 | 1444 |

## Long Context

- GPT-5.6 Luna: 43.9 (#78)
- MiMo-V2-Pro: 41.5 (#133)

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1437 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |

## Writing & Preference

- GPT-5.6 Luna: 68.3 (#27)
- MiMo-V2-Pro: 62.9 (#67)

| Benchmark | GPT-5.6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1432 | 1436 |
| LMArena Creative Writing | 1397 | 1415 |
| LMArena Multi-Turn | 1433 | 1456 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |

## FAQ

### Is GPT-5.6 Luna better than MiMo-V2-Pro?

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 42.4 on the Noometry Index.

### Which is cheaper, GPT-5.6 Luna or MiMo-V2-Pro?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.

### Is GPT-5.6 Luna or MiMo-V2-Pro better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 43.4 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.6 Luna does, with 1.05M tokens against 1.05M.

### How many benchmarks do GPT-5.6 Luna and MiMo-V2-Pro share?

20 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and MiMo-V2-Pro has 23.