# Deepseek Coder v2 vs Kimi K2 Thinking Turbo

> Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 35.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-kimi-k2-thinking-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 Thinking Turbo leads 60.2 to 38.4.

## Snapshot

| | Deepseek Coder v2 | Kimi K2 Thinking Turbo |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 35.3 | 45.4 |
| Rank | 217 | 63 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- Kimi K2 Thinking Turbo: 38.1 (#166)

| Benchmark | Deepseek Coder v2 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1251 | 1454 |
| LMArena WebDev | — | 1322 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- Kimi K2 Thinking Turbo: 31.4 (#72)

| Benchmark | Deepseek Coder v2 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1428 |
| Chess Puzzles | — | 20% |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- Kimi K2 Thinking Turbo: 45.5 (#62)

| Benchmark | Deepseek Coder v2 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Math | 1241 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 83.1% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- Kimi K2 Thinking Turbo: 50.9 (#64)

| Benchmark | Deepseek Coder v2 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Expert | 1181 | 1439 |
| GPQA Diamond | — | 84.2% |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- Kimi K2 Thinking Turbo: 51.6 (#104)

| Benchmark | Deepseek Coder v2 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1182 | 1398 |
| LMArena Chinese | 1201 | 1457 |
| LMArena French | 1184 | 1425 |
| LMArena German | 1164 | 1390 |
| LMArena Japanese | 1126 | 1356 |
| LMArena Korean | 1104 | 1329 |
| LMArena Russian | 1188 | 1390 |
| LMArena Spanish | 1153 | 1407 |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- Kimi K2 Thinking Turbo: 74.2 (#103)

| Benchmark | Deepseek Coder v2 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1180 | 1403 |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- Kimi K2 Thinking Turbo: 43.2 (#99)

| Benchmark | Deepseek Coder v2 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1219 | 1415 |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- Kimi K2 Thinking Turbo: 60.2 (#99)

| Benchmark | Deepseek Coder v2 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1191 | 1415 |
| LMArena Creative Writing | 1120 | 1373 |
| LMArena Multi-Turn | 1176 | 1414 |

## FAQ

### Is Deepseek Coder v2 better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 35.3 on the Noometry Index.

### Is Deepseek Coder v2 or Kimi K2 Thinking Turbo better for coding?

They score almost the same on coding (37.5 vs 38.1); test both on your own repository before choosing.

### How many benchmarks do Deepseek Coder v2 and Kimi K2 Thinking Turbo share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Kimi K2 Thinking Turbo has 21.