# Kimi K2.7 Code vs Qwen-14B

> Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-7-code-vs-qwen-14b
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Kimi K2.7 Code scores higher in 3 categories and Qwen-14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.7 Code leads 52.6 to 28.7.

## Snapshot

| | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 43.0 | 30.8 |
| Rank | 90 | 273 |
| Context | 262K | — |
| Input $/M | $0.95 | — |
| Output $/M | $4 | — |
| Weights | Open | Open |

## Coding

- Kimi K2.7 Code: 42.4 (#92)
- Qwen-14B: 30.6 (#283)

| Benchmark | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena WebDev | 1473 | — |
| SciCode | 47.5% | — |
| WeirdML | 54.1% | — |
| LMArena Coding | — | 1072 |
| ALE-Bench | 886.23 | — |

## Agentic & Tool Use

- Kimi K2.7 Code: 23.9 (#115)
- Qwen-14B: —

| Benchmark | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |

## Reasoning

- Kimi K2.7 Code: 38.2 (#56)
- Qwen-14B: 18.7 (#255)

| Benchmark | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| Epoch Capabilities Index | 150.01 | 112.8 |
| SimpleBench | 57.9% | — |
| CritPt | 10% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | — | 1027 |
| Surface Evolver Bench | 48.8% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |

## Math

- Kimi K2.7 Code: 52.6 (#39)
- Qwen-14B: 28.7 (#224)

| Benchmark | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| LMArena Math | — | 1068 |
| GSM8K | — | 61.3% |

## Knowledge

- Kimi K2.7 Code: 53.6 (#51)
- Qwen-14B: —

| Benchmark | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| GPQA Diamond | 87.9% | — |
| SimpleQA Verified | 36.5% | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |

## Multilingual

- Kimi K2.7 Code: —
- Qwen-14B: 27.7 (#270)

| Benchmark | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1042 |
| LMArena Chinese | — | 1077 |

## Instruction Following

- Kimi K2.7 Code: —
- Qwen-14B: 52.6 (#284)

| Benchmark | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |

## Long Context

- Kimi K2.7 Code: —
- Qwen-14B: 31.3 (#276)

| Benchmark | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1029 |

## Writing & Preference

- Kimi K2.7 Code: —
- Qwen-14B: 27.8 (#294)

| Benchmark | Kimi K2.7 Code | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |

## FAQ

### Is Kimi K2.7 Code better than Qwen-14B?

Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 30.8 on the Noometry Index.

### Is Kimi K2.7 Code or Qwen-14B better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 30.6 in the Noometry coding category.

### How many benchmarks do Kimi K2.7 Code and Qwen-14B share?

1 benchmark has published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Qwen-14B has 18.