# GPT-5.6 Luna vs Kimi K2.7 Code

> GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 43.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-6-luna-vs-kimi-k2-7-code
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GPT-5.6 Luna scores higher in 5 categories and Kimi K2.7 Code in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 52.9.
- The biggest single-benchmark swing is FrontierMath Tier 4: 61% for GPT-5.6 Luna and 12.2% for Kimi K2.7 Code.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 262K.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 54.6 | 43.3 |
| Rank | 30 | 94 |
| Context | 1.05M | 262K |
| Input $/M | $0.20 | $0.95 |
| Output $/M | $1.20 | $4 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.6 Luna: 54.5 (#28)
- Kimi K2.7 Code: 42.9 (#95)

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| DeepSWE | 67.2% | 30.5% |
| FrontierCode | 39.8% | 30.1% |
| LMArena WebDev | 1519 | 1473 |
| SciCode | 53.6% | 47.5% |
| WeirdML | 60.9% | 54.1% |
| ALE-Bench | 1,667 | 886.23 |
| CursorBench | 35.9% | — |
| LMArena Coding | 1466 | — |

## Agentic & Tool Use

- GPT-5.6 Luna: 34.4 (#45)
- Kimi K2.7 Code: 24.0 (#122)

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| APEX-Agents | 43% | 37.6% |
| Vending-Bench 2 | 4,095 | 5,083 |
| BALROG | 45.6% | — |
| GBAEval | — | 0.9% |
| GDP.pdf | 22.7% | — |

## Reasoning

- GPT-5.6 Luna: 47.6 (#43)
- Kimi K2.7 Code: 39.0 (#61)

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| SimpleBench | 46.8% | 57.9% |
| CritPt | 20.6% | 10% |
| Chess Puzzles | 40% | 21% |
| Surface Evolver Bench | 61.9% | 48.8% |
| Epoch Capabilities Index | 156.39 | 149.97 |
| ARC-AGI-2 | 59.5% | — |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | 69.4% | — |
| ARC-AGI-1 | 88% | — |
| LMArena Hard Prompts | 1451 | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |

## Math

- GPT-5.6 Luna: 77.7 (#14)
- Kimi K2.7 Code: 52.9 (#48)

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.1% | 54% |
| FrontierMath Tier 4 | 61% | 12.2% |
| OTIS Mock AIME 2024-2025 | 98.3% | 95.6% |
| ProofBench | 60% | — |
| LMArena Math | 1458 | — |

## Knowledge

- GPT-5.6 Luna: 58.5 (#34)
- Kimi K2.7 Code: 53.5 (#57)

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | 91.6% | 87.9% |
| SimpleQA Verified | 41% | 36.5% |
| LMArena Expert | 1478 | — |

## Multimodal

- GPT-5.6 Luna: 42.7 (#28)
- Kimi K2.7 Code: —

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| LMArena Vision | 1258 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |

## Multilingual

- GPT-5.6 Luna: 52.8 (#78)
- Kimi K2.7 Code: —

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| LMArena Non-English | 1417 | — |
| LMArena Chinese | 1470 | — |
| LMArena French | 1456 | — |
| LMArena German | 1454 | — |
| LMArena Japanese | 1411 | — |
| LMArena Korean | 1415 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1448 | — |

## Instruction Following

- GPT-5.6 Luna: 75.6 (#57)
- Kimi K2.7 Code: —

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| LMArena Instruction Following | 1437 | — |

## Long Context

- GPT-5.6 Luna: 43.9 (#82)
- Kimi K2.7 Code: —

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| LMArena Longer Query | 1436 | — |

## Writing & Preference

- GPT-5.6 Luna: 68.0 (#29)
- Kimi K2.7 Code: —

| Benchmark | GPT-5.6 Luna | Kimi K2.7 Code |
|---|---|---|
| LMArena Text | 1431 | — |
| LMArena Creative Writing | 1396 | — |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
| LMArena Multi-Turn | 1434 | — |

## FAQ

### Is GPT-5.6 Luna better than Kimi K2.7 Code?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 43.3 on the Noometry Index.

### Which is cheaper, GPT-5.6 Luna or Kimi K2.7 Code?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

### Is GPT-5.6 Luna or Kimi K2.7 Code better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 42.9 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.6 Luna does, with 1.05M tokens against 262K.

### How many benchmarks do GPT-5.6 Luna and Kimi K2.7 Code share?

18 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Kimi K2.7 Code has 19.