# DeepSeek-V3.2-Speciale vs Kimi K2.7 Code

> Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 39.1 on the Noometry Index. DeepSeek-V3.2-Speciale costs 2.0× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v3-2-speciale-vs-kimi-k2-7-code
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. DeepSeek-V3.2-Speciale scores higher in 0 categories and Kimi K2.7 Code in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.7 Code leads 38.2 to 32.1.
- The biggest single-benchmark swing is WeirdML: 46.7% for DeepSeek-V3.2-Speciale and 54.1% for Kimi K2.7 Code.
- DeepSeek-V3.2-Speciale is cheaper at $0.58 / $1.68 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- Kimi K2.7 Code accepts more context: 262K tokens versus 128K.

## Snapshot

| | DeepSeek-V3.2-Speciale | Kimi K2.7 Code |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 39.1 | 43.0 |
| Rank | 159 | 90 |
| Context | 128K | 262K |
| Input $/M | $0.58 | $0.95 |
| Output $/M | $1.68 | $4 |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.2-Speciale: 39.9 (#136)
- Kimi K2.7 Code: 42.4 (#92)

| Benchmark | DeepSeek-V3.2-Speciale | Kimi K2.7 Code |
|---|---|---|
| WeirdML | 46.7% | 54.1% |
| DeepSWE | — | 30.5% |
| FrontierCode | — | 30.1% |
| LMArena WebDev | — | 1473 |
| SciCode | — | 47.5% |
| ALE-Bench | — | 886.23 |

## Agentic & Tool Use

- DeepSeek-V3.2-Speciale: —
- Kimi K2.7 Code: 23.9 (#115)

| Benchmark | DeepSeek-V3.2-Speciale | Kimi K2.7 Code |
|---|---|---|
| APEX-Agents | — | 37.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 5,083 |

## Reasoning

- DeepSeek-V3.2-Speciale: 32.1 (#65)
- Kimi K2.7 Code: 38.2 (#56)

| Benchmark | DeepSeek-V3.2-Speciale | Kimi K2.7 Code |
|---|---|---|
| SimpleBench | 52.6% | 57.9% |
| CritPt | — | 10% |
| Chess Puzzles | — | 21% |
| Surface Evolver Bench | — | 48.8% |
| Epoch Capabilities Index | — | 150.01 |

## Math

- DeepSeek-V3.2-Speciale: —
- Kimi K2.7 Code: 52.6 (#39)

| Benchmark | DeepSeek-V3.2-Speciale | Kimi K2.7 Code |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 54% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |

## Knowledge

- DeepSeek-V3.2-Speciale: —
- Kimi K2.7 Code: 53.6 (#51)

| Benchmark | DeepSeek-V3.2-Speciale | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | — | 87.9% |
| SimpleQA Verified | — | 36.5% |

## Writing & Preference

- DeepSeek-V3.2-Speciale: 46.1 (#217)
- Kimi K2.7 Code: —

| Benchmark | DeepSeek-V3.2-Speciale | Kimi K2.7 Code |
|---|---|---|
| EQ-Bench Creative Writing | 1276 | — |

## FAQ

### Is DeepSeek-V3.2-Speciale better than Kimi K2.7 Code?

Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 39.1 on the Noometry Index. DeepSeek-V3.2-Speciale costs 2.0× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek-V3.2-Speciale or Kimi K2.7 Code?

DeepSeek-V3.2-Speciale is cheaper. It lists at $0.58 per million input tokens and $1.68 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

### Is DeepSeek-V3.2-Speciale or Kimi K2.7 Code better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 39.9 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2.7 Code does, with 262K tokens against 128K.

### How many benchmarks do DeepSeek-V3.2-Speciale and Kimi K2.7 Code share?

2 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Kimi K2.7 Code has 19.