Noometry

Model comparison

Deepseek Coder v2 vs Kimi K2.7 Code

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 35.9 on the Noometry Index.

Last verified . 0 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Kimi K2.7 Code Moonshot AI

43.3

Rank #94 Confirmed

Summary

  • The widest gap is in knowledge, where Kimi K2.7 Code leads 53.5 to 32.3.

Side by side

Deepseek Coder v2Kimi K2.7 Code
ProviderDeepSeekMoonshot AI
Noometry Index35.943.3
Released2024-06-172026-06-12
WeightsOpenOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.95
Output $ / M tokens—$4
Results tracked2419

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Kimi K2.7 Code leads

Deepseek Coder v2: 38.1 (#183), Kimi K2.7 Code: 42.9 (#95)

BenchmarkDeepseek Coder v2Kimi K2.7 Code
DeepSWE—30.5%
FrontierCode—30.1%
LMArena WebDev—1473
SciCode—47.5%
WeirdML—54.1%
BigCodeBench Instruct48.2%—
LMArena Coding1251—
BigCodeBench Complete59.7%—
ALE-Bench—886.23
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, Kimi K2.7 Code: 24.0 (#122)

BenchmarkDeepseek Coder v2Kimi K2.7 Code
APEX-Agents—37.6%
GBAEval—0.9%
Vending-Bench 2—5,083

Reasoning Kimi K2.7 Code leads

Deepseek Coder v2: 23.6 (#176), Kimi K2.7 Code: 39.0 (#61)

BenchmarkDeepseek Coder v2Kimi K2.7 Code
SimpleBench—57.9%
CritPt—10%
Chess Puzzles—21%
LMArena Hard Prompts1207—
Surface Evolver Bench—48.8%
Epoch Capabilities Index—149.97
WinoGrande83.7%—

Math Kimi K2.7 Code leads

Deepseek Coder v2: 34.9 (#190), Kimi K2.7 Code: 52.9 (#48)

BenchmarkDeepseek Coder v2Kimi K2.7 Code
FrontierMath (Tiers 1-3)—54%
FrontierMath Tier 4—12.2%
OTIS Mock AIME 2024-2025—95.6%
LMArena Math1241—
GSM8K94.5%—

Knowledge Kimi K2.7 Code leads

Deepseek Coder v2: 32.3 (#212), Kimi K2.7 Code: 53.5 (#57)

BenchmarkDeepseek Coder v2Kimi K2.7 Code
GPQA Diamond—87.9%
SimpleQA Verified—36.5%
LMArena Expert1181—
ARC (AI2) Challenge64.3%—

Multilingual Not comparable

Deepseek Coder v2: 36.3 (#240), Kimi K2.7 Code: —

BenchmarkDeepseek Coder v2Kimi K2.7 Code
LMArena Non-English1182—
LMArena Chinese1201—
LMArena French1185—
LMArena German1164—
LMArena Japanese1126—
LMArena Korean1104—
LMArena Russian1188—
LMArena Spanish1153—

Instruction Following Not comparable

Deepseek Coder v2: 61.7 (#242), Kimi K2.7 Code: —

BenchmarkDeepseek Coder v2Kimi K2.7 Code
LMArena Instruction Following1180—

Long Context Not comparable

Deepseek Coder v2: 37.0 (#224), Kimi K2.7 Code: —

BenchmarkDeepseek Coder v2Kimi K2.7 Code
LMArena Longer Query1219—

Writing & Preference Not comparable

Deepseek Coder v2: 38.2 (#253), Kimi K2.7 Code: —

BenchmarkDeepseek Coder v2Kimi K2.7 Code
LMArena Text1191—
LMArena Creative Writing1120—
LMArena Multi-Turn1177—

Frequently asked questions

Is Deepseek Coder v2 better than Kimi K2.7 Code?

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or Kimi K2.7 Code better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 38.1 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and Kimi K2.7 Code share?

0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper