Noometry

Model comparison

Claude Sonnet 4.6 vs Kimi K2 (Jul 2025)

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 6.0× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 26 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Kimi K2 (Jul 2025) Moonshot AI

41.2

Rank #140 Confirmed

Summary

  • They share 26 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 9 categories and Kimi K2 (Jul 2025) in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 23.3.
  • The biggest single-benchmark swing is WeirdML: 66.1% for Claude Sonnet 4.6 and 42.8% for Kimi K2 (Jul 2025).
  • Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 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 (Jul 2025) has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6Kimi K2 (Jul 2025)
ProviderAnthropicMoonshot AI
Noometry Index50.341.2
Released2026-02-172025-07-12
WeightsProprietaryOpen
Context window1M262K
Max output128K262K
Input $ / M tokens$3$0.57
Output $ / M tokens$15$2.30
Results tracked5742

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 (Jul 2025): 42.4 (#102)

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
WeirdML66.1%42.8%
LMArena Coding15041399
ALE-Bench1,327597.5
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
SWE-bench Verified (bash only)—63.4%
Aider Polyglot—59.1%
LMArena WebDev1522—
SciCode46.8%—
GSO—4.9%

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), Kimi K2 (Jul 2025): 32.4 (#64)

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
Terminal-Bench53.4%35.7%
APEX-Agents43%—
Berkeley Function Calling Leaderboard—59.1%
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—
METR Time Horizons—59.2%
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), Kimi K2 (Jul 2025): 23.3 (#179)

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
LMArena Hard Prompts14841384
Epoch Capabilities Index152.24146.01
ForecastBench6260.2
ARC-AGI-260.4%—
SimpleBench—26.3%
Kagi LLM Benchmark—64.4%
NYT Connections (extended)80.9%—
ARC-AGI-186.5%—
CritPt3.1%—
Chess Puzzles13%—
Thematic Generalization76.3%—
Mystery Game Puzzles16%—
DTBench89.9%—
LMCA46.5%—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), Kimi K2 (Jul 2025): 42.7 (#83)

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
LMArena Math14621397
FrontierMath (Feb 2025 set)32.4%21.4%
FrontierMath Tier 4 (v1)8.3%0%
OTIS Mock AIME 2024-202585.8%—
ProofBench45%—
Omni-MATH—65.4%

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.7 (#65), Kimi K2 (Jul 2025): 37.3 (#157)

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
Vectara Hallucination Rate10.6%17.9%
LMArena Expert15001365
GPQA Diamond87.4%—
SimpleQA Verified35.5%—
MMLU-Pro—81.9%
Confabulations—20.4%
GPQA (HELM)—65.3%

Multimodal Not comparable

Claude Sonnet 4.6: 38.0 (#68), Kimi K2 (Jul 2025): —

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
LMArena Vision1283—
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.4 (#41), Kimi K2 (Jul 2025): 49.6 (#130)

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
LMArena Non-English14401372
LMArena Chinese14911415
LMArena French14651379
LMArena German14281387
LMArena Japanese14201349
LMArena Korean14111325
LMArena Russian14401385
LMArena Spanish14641386

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), Kimi K2 (Jul 2025): 71.1 (#156)

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
LMArena Instruction Following14751348
IFEval—85%

Long Context Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 45.3 (#44), Kimi K2 (Jul 2025): 41.2 (#145)

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
LMArena Longer Query14791353
Fiction.LiveBench—66.7%
CL-bench—17.6%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), Kimi K2 (Jul 2025): 62.3 (#78)

BenchmarkClaude Sonnet 4.6Kimi K2 (Jul 2025)
LMArena Text14581380
LMArena Creative Writing14351350
EQ-Bench Creative Writing18101666
LMArena Multi-Turn14641371
Short-Story Creative Writing—85.6%
WildBench—86.2%
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Kimi K2 (Jul 2025)?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 6.0× 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 (Jul 2025)?

Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or Kimi K2 (Jul 2025) better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 42.4 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 (Jul 2025) share?

26 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Kimi K2 (Jul 2025) has 42.

Related comparisons

Go deeper