# Kimi K2.7 Code vs MiniMax-M3

> Kimi K2.7 Code and MiniMax-M3 score almost the same on the Noometry Index (43.3 vs 43.8), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/kimi-k2-7-code-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Kimi K2.7 Code scores higher in 4 categories and MiniMax-M3 in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.7 Code leads 52.9 to 40.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Kimi K2.7 Code and 71.1% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- MiniMax-M3 accepts more context: 1M tokens versus 262K.

## Snapshot

| | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| Provider | Moonshot AI | MiniMax |
| Noometry Index | 43.3 | 43.8 |
| Rank | 94 | 85 |
| Context | 262K | 1M |
| Input $/M | $0.95 | $0.30 |
| Output $/M | $4 | $1.20 |
| Weights | Open | Open |

## Coding

- Kimi K2.7 Code: 42.9 (#95)
- MiniMax-M3: 41.8 (#118)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| FrontierCode | 30.1% | 14.7% |
| LMArena WebDev | 1473 | 1482 |
| SciCode | 47.5% | 47.1% |
| ALE-Bench | 886.23 | 640.02 |
| DeepSWE | 30.5% | — |
| WeirdML | 54.1% | — |
| LMArena Coding | — | 1469 |

## Agentic & Tool Use

- Kimi K2.7 Code: 24.0 (#122)
- MiniMax-M3: 22.6 (#130)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 37.6% | 37.7% |
| GBAEval | 0.9% | 0.9% |
| Vending-Bench 2 | 5,083 | 2,158 |
| OSWorld 2.0 | — | 4.6% |

## Reasoning

- Kimi K2.7 Code: 39.0 (#61)
- MiniMax-M3: 30.1 (#87)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| SimpleBench | 57.9% | 45.8% |
| CritPt | 10% | 3.7% |
| Chess Puzzles | 21% | 14% |
| Surface Evolver Bench | 48.8% | 55% |
| Epoch Capabilities Index | 149.97 | 146.95 |
| NYT Connections (extended) | — | 65.1% |
| LMArena Hard Prompts | — | 1447 |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| ForecastBench | — | 61.4 |

## Math

- Kimi K2.7 Code: 52.9 (#48)
- MiniMax-M3: 40.0 (#95)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 71.1% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | — | 18% |
| LMArena Math | — | 1429 |

## Knowledge

- Kimi K2.7 Code: 53.5 (#57)
- MiniMax-M3: 58.4 (#35)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 87.9% | 90.9% |
| SimpleQA Verified | 36.5% | — |
| LMArena Expert | — | 1461 |

## Multimodal

- Kimi K2.7 Code: —
- MiniMax-M3: 40.2 (#51)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |

## Multilingual

- Kimi K2.7 Code: —
- MiniMax-M3: 53.0 (#75)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | — | 1420 |
| LMArena Chinese | — | 1463 |
| LMArena French | — | 1447 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1432 |

## Instruction Following

- Kimi K2.7 Code: —
- MiniMax-M3: 75.5 (#62)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | — | 1433 |

## Long Context

- Kimi K2.7 Code: —
- MiniMax-M3: 44.2 (#72)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | — | 1445 |

## Writing & Preference

- Kimi K2.7 Code: —
- MiniMax-M3: 62.1 (#83)

| Benchmark | Kimi K2.7 Code | MiniMax-M3 |
|---|---|---|
| LMArena Text | — | 1433 |
| LMArena Creative Writing | — | 1404 |
| EQ-Bench 4 | — | 1150 |
| LMArena Multi-Turn | — | 1442 |

## FAQ

### Is Kimi K2.7 Code better than MiniMax-M3?

Kimi K2.7 Code and MiniMax-M3 score almost the same on the Noometry Index (43.3 vs 43.8), so choose on price, context window or the category you care about most.

### Which is cheaper, Kimi K2.7 Code or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

### Is Kimi K2.7 Code or MiniMax-M3 better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 41.8 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 262K.

### How many benchmarks do Kimi K2.7 Code and MiniMax-M3 share?

14 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and MiniMax-M3 has 41.