Noometry

Model comparison

Claude Sonnet 4.6 vs Kimi K2.7 Code

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.3 on the Noometry Index. Kimi K2.7 Code costs 3.5× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 15 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Kimi K2.7 Code Moonshot AI

43.3

Rank #94 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 3 categories and Kimi K2.7 Code in 2 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Sonnet 4.6 leads 39.1 to 24.0.
  • The biggest single-benchmark swing is GBAEval: 48.8% for Claude Sonnet 4.6 and 0.9% for Kimi K2.7 Code.
  • Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
  • Claude Sonnet 4.6 accepts more context: 1M tokens versus 262K.
  • Kimi K2.7 Code has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6Kimi K2.7 Code
ProviderAnthropicMoonshot AI
Noometry Index50.343.3
Released2026-02-172026-06-12
WeightsProprietaryOpen
Context window1M262K
Max output128K262K
Input $ / M tokens$3$0.95
Output $ / M tokens$15$4
Results tracked5719

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

Category by category

Coding Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.3 (#67), Kimi K2.7 Code: 42.9 (#95)

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
DeepSWE29.9%30.5%
FrontierCode24.3%30.1%
LMArena WebDev15221473
SciCode46.8%47.5%
WeirdML66.1%54.1%
ALE-Bench1,327886.23
SWE-bench Verified75.2%—
LMArena Coding1504—

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), Kimi K2.7 Code: 24.0 (#122)

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
APEX-Agents43%37.6%
GBAEval48.8%0.9%
Vending-Bench 27,2045,083
Terminal-Bench53.4%—
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GDP.pdf18%—
LMArena Search1221—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), Kimi K2.7 Code: 39.0 (#61)

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
CritPt3.1%10%
Chess Puzzles13%21%
Epoch Capabilities Index152.24149.97
ARC-AGI-260.4%—
SimpleBench—57.9%
NYT Connections (extended)80.9%—
ARC-AGI-186.5%—
Thematic Generalization76.3%—
LMArena Hard Prompts1484—
Mystery Game Puzzles16%—
DTBench89.9%—
LMCA46.5%—
Surface Evolver Bench—48.8%
ForecastBench62—

Math Too close to call

Claude Sonnet 4.6: 52.9 (#49), Kimi K2.7 Code: 52.9 (#48)

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
OTIS Mock AIME 2024-202585.8%95.6%
FrontierMath (Tiers 1-3)—54%
FrontierMath Tier 4—12.2%
ProofBench45%—
LMArena Math1462—
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Kimi K2.7 Code leads

Claude Sonnet 4.6: 51.7 (#65), Kimi K2.7 Code: 53.5 (#57)

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
GPQA Diamond87.4%87.9%
SimpleQA Verified35.5%36.5%
Vectara Hallucination Rate10.6%—
LMArena Expert1500—

Multimodal Not comparable

Claude Sonnet 4.6: 38.0 (#68), Kimi K2.7 Code: —

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
LMArena Vision1283—
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Not comparable

Claude Sonnet 4.6: 54.4 (#41), Kimi K2.7 Code: —

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
LMArena Non-English1440—
LMArena Chinese1491—
LMArena French1465—
LMArena German1428—
LMArena Japanese1420—
LMArena Korean1411—
LMArena Russian1440—
LMArena Spanish1464—

Instruction Following Not comparable

Claude Sonnet 4.6: 77.4 (#25), Kimi K2.7 Code: —

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
LMArena Instruction Following1475—

Long Context Not comparable

Claude Sonnet 4.6: 45.3 (#44), Kimi K2.7 Code: —

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
LMArena Longer Query1479—

Writing & Preference Not comparable

Claude Sonnet 4.6: 70.2 (#22), Kimi K2.7 Code: —

BenchmarkClaude Sonnet 4.6Kimi K2.7 Code
LMArena Text1458—
LMArena Creative Writing1435—
EQ-Bench Creative Writing1810—
EQ-Bench 41207—
LMArena Multi-Turn1464—

Frequently asked questions

Is Claude Sonnet 4.6 better than Kimi K2.7 Code?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.3 on the Noometry Index. Kimi K2.7 Code costs 3.5× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.6 or Kimi K2.7 Code?

Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or Kimi K2.7 Code better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 42.9 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 262K.

How many benchmarks do Claude Sonnet 4.6 and Kimi K2.7 Code share?

15 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper