# DeepSeek LLM 67B vs Kimi K2.7 Code

> Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-kimi-k2-7-code
- Last updated: 2026-10-11
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Kimi K2.7 Code in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.7 Code leads 53.5 to 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 95.6% for Kimi K2.7 Code.

## Snapshot

| | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 24.9 | 43.3 |
| Rank | 347 | 94 |
| Context | — | 262K |
| Input $/M | — | $0.95 |
| Output $/M | — | $4 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Kimi K2.7 Code: 42.9 (#95)

| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| DeepSWE | — | 30.5% |
| FrontierCode | — | 30.1% |
| LMArena WebDev | — | 1473 |
| SciCode | — | 47.5% |
| WeirdML | — | 54.1% |
| LMArena Coding | 1096 | — |
| ALE-Bench | — | 886.23 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- Kimi K2.7 Code: 24.0 (#122)

| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| APEX-Agents | — | 37.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 5,083 |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Kimi K2.7 Code: 39.0 (#61)

| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| Chess Puzzles | 0% | 21% |
| Epoch Capabilities Index | 110.5 | 149.97 |
| SimpleBench | — | 57.9% |
| CritPt | — | 10% |
| LMArena Hard Prompts | 1070 | — |
| Surface Evolver Bench | — | 48.8% |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Kimi K2.7 Code: 52.9 (#48)

| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 95.6% |
| FrontierMath (Tiers 1-3) | — | 54% |
| FrontierMath Tier 4 | — | 12.2% |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Kimi K2.7 Code: 53.5 (#57)

| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | 24.6% | 87.9% |
| SimpleQA Verified | — | 36.5% |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Kimi K2.7 Code: —

| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Kimi K2.7 Code: —

| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| LMArena Instruction Following | 1079 | — |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Kimi K2.7 Code: —

| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| LMArena Longer Query | 1092 | — |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Kimi K2.7 Code: —

| Benchmark | DeepSeek LLM 67B | Kimi K2.7 Code |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |

## FAQ

### Is DeepSeek LLM 67B better than Kimi K2.7 Code?

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or Kimi K2.7 Code better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Kimi K2.7 Code share?

4 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Kimi K2.7 Code has 19.