# Deepseek Coder v2 vs Kimi K2.5 Instant

> Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-kimi-k2-5-instant
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Kimi K2.5 Instant in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.5 Instant leads 60.6 to 38.2.

## Snapshot

| | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 35.9 | 43.6 |
| Rank | 220 | 89 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 38.1 (#183)
- Kimi K2.5 Instant: 42.6 (#97)

| Benchmark | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1251 | 1484 |
| LMArena WebDev | — | 1404 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 23.6 (#176)
- Kimi K2.5 Instant: 29.7 (#90)

| Benchmark | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1443 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 34.9 (#190)
- Kimi K2.5 Instant: 39.4 (#105)

| Benchmark | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1241 | 1442 |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 32.3 (#212)
- Kimi K2.5 Instant: 40.2 (#123)

| Benchmark | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1181 | 1440 |
| ARC (AI2) Challenge | 64.3% | — |

## Multimodal

- Deepseek Coder v2: —
- Kimi K2.5 Instant: 40.2 (#50)

| Benchmark | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |

## Multilingual

- Deepseek Coder v2: 36.3 (#240)
- Kimi K2.5 Instant: 52.0 (#94)

| Benchmark | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1182 | 1406 |
| LMArena Chinese | 1201 | 1449 |
| LMArena French | 1185 | 1403 |
| LMArena German | 1164 | 1413 |
| LMArena Korean | 1104 | 1378 |
| LMArena Russian | 1188 | 1404 |
| LMArena Spanish | 1153 | 1447 |
| LMArena Japanese | 1126 | — |

## Instruction Following

- Deepseek Coder v2: 61.7 (#242)
- Kimi K2.5 Instant: 75.3 (#65)

| Benchmark | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1180 | 1430 |

## Long Context

- Deepseek Coder v2: 37.0 (#224)
- Kimi K2.5 Instant: 43.9 (#83)

| Benchmark | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1219 | 1435 |

## Writing & Preference

- Deepseek Coder v2: 38.2 (#253)
- Kimi K2.5 Instant: 60.6 (#95)

| Benchmark | Deepseek Coder v2 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1191 | 1420 |
| LMArena Creative Writing | 1120 | 1381 |
| LMArena Multi-Turn | 1177 | 1427 |

## FAQ

### Is Deepseek Coder v2 better than Kimi K2.5 Instant?

Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 35.9 on the Noometry Index.

### Is Deepseek Coder v2 or Kimi K2.5 Instant better for coding?

Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 38.1 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Kimi K2.5 Instant share?

16 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Kimi K2.5 Instant has 18.