# GPT-5.6 Luna vs MiMo-V2.5

> GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 43.0 on the Noometry Index. MiMo-V2.5 costs 2.6× less per token, which makes it the better buy when GPT-5.6 Luna's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-6-luna-vs-mimo-v2-5
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and MiMo-V2.5 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 35.4.
- The biggest single-benchmark swing is ProofBench: 60% for GPT-5.6 Luna and 16% for MiMo-V2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.20 / $1.20 for GPT-5.6 Luna.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 1.05M.
- MiMo-V2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 54.7 | 43.0 |
| Rank | 24 | 89 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.20 | $0.14 |
| Output $/M | $1.20 | $0.28 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.6 Luna: 53.9 (#25)
- MiMo-V2.5: 43.6 (#75)

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1517 | 1438 |
| SciCode | 53.6% | 43.1% |
| LMArena Coding | 1466 | 1469 |
| ALE-Bench | 1,667 | 513.95 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| WeirdML | 60.9% | — |

## Agentic & Tool Use

- GPT-5.6 Luna: 35.3 (#37)
- MiMo-V2.5: —

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |

## Reasoning

- GPT-5.6 Luna: 47.5 (#38)
- MiMo-V2.5: 27.8 (#98)

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| CritPt | 20.6% | 3.7% |
| LMArena Hard Prompts | 1452 | 1450 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | 69.4% | — |
| ARC-AGI-1 | 88% | — |
| 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)
- MiMo-V2.5: 35.4 (#145)

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| ProofBench | 60% | 16% |
| LMArena Math | 1455 | 1436 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |

## Knowledge

- GPT-5.6 Luna: 58.6 (#31)
- MiMo-V2.5: 40.2 (#109)

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1479 | 1459 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |

## Multimodal

- GPT-5.6 Luna: 43.0 (#22)
- MiMo-V2.5: 39.0 (#53)

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1259 | 1245 |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |

## Multilingual

- GPT-5.6 Luna: 53.0 (#73)
- MiMo-V2.5: 52.0 (#96)

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1418 | 1404 |
| LMArena Chinese | 1469 | 1467 |
| LMArena French | 1457 | 1447 |
| LMArena German | 1459 | 1421 |
| LMArena Japanese | 1416 | 1304 |
| LMArena Korean | 1414 | 1363 |
| LMArena Russian | 1428 | 1395 |
| LMArena Spanish | 1445 | 1412 |

## Instruction Following

- GPT-5.6 Luna: 76.0 (#48)
- MiMo-V2.5: 75.7 (#55)

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1440 | 1433 |

## Long Context

- GPT-5.6 Luna: 43.9 (#78)
- MiMo-V2.5: 44.1 (#69)

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1437 | 1444 |

## Writing & Preference

- GPT-5.6 Luna: 68.3 (#27)
- MiMo-V2.5: 61.8 (#82)

| Benchmark | GPT-5.6 Luna | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1432 | 1427 |
| LMArena Creative Writing | 1397 | 1392 |
| LMArena Multi-Turn | 1433 | 1445 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |

## FAQ

### Is GPT-5.6 Luna better than MiMo-V2.5?

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 43.0 on the Noometry Index. MiMo-V2.5 costs 2.6× less per token, which makes it the better buy when GPT-5.6 Luna's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.6 Luna or MiMo-V2.5?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; GPT-5.6 Luna lists at $0.20 and $1.20.

### Is GPT-5.6 Luna or MiMo-V2.5 better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 43.6 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-V2.5 share?

23 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and MiMo-V2.5 has 23.