# DeepSeek-V2.5 (Sep 2024) vs Kimi K2 Thinking Turbo

> Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-kimi-k2-thinking-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 34.2.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 37.0 | 45.4 |
| Rank | 197 | 63 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- Kimi K2 Thinking Turbo: 38.1 (#166)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1310 | 1454 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1322 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- Kimi K2 Thinking Turbo: 31.4 (#72)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1428 |
| Chess Puzzles | — | 20% |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- Kimi K2 Thinking Turbo: 45.5 (#62)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Math | 1289 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 83.1% |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- Kimi K2 Thinking Turbo: 50.9 (#64)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Expert | 1266 | 1439 |
| GPQA Diamond | — | 84.2% |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- Kimi K2 Thinking Turbo: 51.6 (#104)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1273 | 1398 |
| LMArena Chinese | 1317 | 1457 |
| LMArena French | 1288 | 1425 |
| LMArena German | 1258 | 1390 |
| LMArena Japanese | 1228 | 1356 |
| LMArena Korean | 1209 | 1329 |
| LMArena Russian | 1289 | 1390 |
| LMArena Spanish | 1248 | 1407 |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- Kimi K2 Thinking Turbo: 74.2 (#103)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1280 | 1403 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- Kimi K2 Thinking Turbo: 43.2 (#99)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1301 | 1415 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- Kimi K2 Thinking Turbo: 60.2 (#99)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1294 | 1415 |
| LMArena Creative Writing | 1285 | 1373 |
| LMArena Multi-Turn | 1297 | 1414 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 37.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Kimi K2 Thinking Turbo better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Kimi K2 Thinking Turbo share?

17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Kimi K2 Thinking Turbo has 21.