Noometry

Model comparison

DeepSeek V4 Pro vs Kimi K2.7 Code

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 43.3 on the Noometry Index.

Last verified . 16 shared benchmarks.

DeepSeek V4 Pro DeepSeek

54.3

Rank #31 Confirmed

Kimi K2.7 Code Moonshot AI

43.3

Rank #94 Confirmed

Summary

  • They share 16 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 5 categories and Kimi K2.7 Code in 0 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 39.0.
  • The biggest single-benchmark swing is Chess Puzzles: 47% for DeepSeek V4 Pro and 21% for Kimi K2.7 Code.
  • DeepSeek V4 Pro is cheaper at $0.66 / $1.98 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
  • DeepSeek V4 Pro accepts more context: 1M tokens versus 262K.

Side by side

DeepSeek V4 ProKimi K2.7 Code
ProviderDeepSeekMoonshot AI
Noometry Index54.343.3
Released2026-04-242026-06-12
WeightsOpenOpen
Context window1M262K
Max output393K262K
Input $ / M tokens$0.66$0.95
Output $ / M tokens$1.98$4
Results tracked4819

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

Category by category

Coding DeepSeek V4 Pro leads

DeepSeek V4 Pro: 52.4 (#34), Kimi K2.7 Code: 42.9 (#95)

BenchmarkDeepSeek V4 ProKimi K2.7 Code
FrontierCode28.6%30.1%
LMArena WebDev15821473
SciCode51%47.5%
WeirdML66.2%54.1%
ALE-Bench1,403886.23
SWE-bench Verified77.6%—
DeepSWE—30.5%
LMArena Coding1470—

Agentic & Tool Use DeepSeek V4 Pro leads

DeepSeek V4 Pro: 32.8 (#58), Kimi K2.7 Code: 24.0 (#122)

BenchmarkDeepSeek V4 ProKimi K2.7 Code
APEX-Agents47.3%37.6%
Vending-Bench 23,2855,083
GBAEval—0.9%

Reasoning DeepSeek V4 Pro leads

DeepSeek V4 Pro: 56.5 (#24), Kimi K2.7 Code: 39.0 (#61)

BenchmarkDeepSeek V4 ProKimi K2.7 Code
CritPt18%10%
Chess Puzzles47%21%
Surface Evolver Bench40%48.8%
Epoch Capabilities Index155.31149.97
ARC-AGI-261.3%—
SimpleBench—57.9%
Kagi LLM Benchmark53.5%—
NYT Connections (extended)91.3%—
ARC-AGI-190.5%—
LMArena Hard Prompts1461—
Mystery Game Puzzles43%—
DTBench93.9%—
LMCA45.5%—
ForecastBench56.1—

Math DeepSeek V4 Pro leads

DeepSeek V4 Pro: 64.8 (#30), Kimi K2.7 Code: 52.9 (#48)

BenchmarkDeepSeek V4 ProKimi K2.7 Code
FrontierMath (Tiers 1-3)64.6%54%
FrontierMath Tier 426.8%12.2%
OTIS Mock AIME 2024-202598.6%95.6%
MathArena Final-Answer Competitions76.6%—
ProofBench50%—
LMArena Math1455—

Knowledge DeepSeek V4 Pro leads

DeepSeek V4 Pro: 59.5 (#31), Kimi K2.7 Code: 53.5 (#57)

BenchmarkDeepSeek V4 ProKimi K2.7 Code
GPQA Diamond91.7%87.9%
SimpleQA Verified52.9%36.5%
Vectara Hallucination Rate8.6%—
LMArena Expert1464—

Multilingual Not comparable

DeepSeek V4 Pro: 54.4 (#45), Kimi K2.7 Code: —

BenchmarkDeepSeek V4 ProKimi K2.7 Code
LMArena Non-English1439—
LMArena Chinese1486—
LMArena French1472—
LMArena German1458—
LMArena Japanese1445—
LMArena Korean1447—
LMArena Russian1453—
LMArena Spanish1458—

Instruction Following Not comparable

DeepSeek V4 Pro: 76.1 (#47), Kimi K2.7 Code: —

BenchmarkDeepSeek V4 ProKimi K2.7 Code
LMArena Instruction Following1448—

Long Context Not comparable

DeepSeek V4 Pro: 45.0 (#51), Kimi K2.7 Code: —

BenchmarkDeepSeek V4 ProKimi K2.7 Code
CL-bench Life13.5%—
LMArena Longer Query1458—

Writing & Preference Not comparable

DeepSeek V4 Pro: 65.5 (#46), Kimi K2.7 Code: —

BenchmarkDeepSeek V4 ProKimi K2.7 Code
LMArena Text1451—
LMArena Creative Writing1446—
EQ-Bench Creative Writing1553—
EQ-Bench 41166—
LMArena Multi-Turn1467—

Frequently asked questions

Is DeepSeek V4 Pro better than Kimi K2.7 Code?

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 43.3 on the Noometry Index.

Which is cheaper, DeepSeek V4 Pro or Kimi K2.7 Code?

DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

Is DeepSeek V4 Pro or Kimi K2.7 Code better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 42.9 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4 Pro does, with 1M tokens against 262K.

How many benchmarks do DeepSeek V4 Pro and Kimi K2.7 Code share?

16 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper