Noometry

Model comparison

Claude Sonnet 4.5 vs Kimi K2 (Jul 2025)

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 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 4.5's lead doesn't matter for your workload.

Last verified . 37 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Kimi K2 (Jul 2025) Moonshot AI

41.2

Rank #140 Confirmed

Summary

  • They share 37 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 8 categories and Kimi K2 (Jul 2025) in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude Sonnet 4.5 leads 48.4 to 37.3.
  • The biggest single-benchmark swing is SimpleBench: 54.3% for Claude Sonnet 4.5 and 26.3% 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 4.5.
  • Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 200K.
  • Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5Kimi K2 (Jul 2025)
ProviderAnthropicMoonshot AI
Noometry Index44.141.2
Released2025-09-292025-07-12
WeightsProprietaryOpen
Context window200K262K
Max output64K262K
Input $ / M tokens$3$0.57
Output $ / M tokens$15$2.30
Results tracked7342

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), Kimi K2 (Jul 2025): 42.4 (#102)

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
SWE-bench Verified (bash only)71.4%63.4%
GSO14.7%4.9%
WeirdML47.7%42.8%
LMArena Coding14891399
ALE-Bench796.15597.5
SWE-bench Verified71.3%—
Aider Polyglot—59.1%
LMArena WebDev1393—
SWE-bench Multilingual67%—
SciCode44.7%—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), Kimi K2 (Jul 2025): 32.4 (#64)

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
Terminal-Bench46.5%35.7%
Berkeley Function Calling Leaderboard73.2%59.1%
METR Time Horizons67.4%59.2%
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
LMArena Search1159—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#125), Kimi K2 (Jul 2025): 23.3 (#179)

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
SimpleBench54.3%26.3%
Kagi LLM Benchmark57.9%64.4%
LMArena Hard Prompts14621384
Epoch Capabilities Index146.84146.01
ForecastBench61.960.2
ARC-AGI-213.6%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
CritPt1.1%—
Chess Puzzles12%—
EnigmaEval6%—
EBR-Bench2.4%—
Mystery Game Puzzles17%—
DTBench83.2%—
LMCA38.8%—

Math Kimi K2 (Jul 2025) leads

Claude Sonnet 4.5: 32.3 (#216), Kimi K2 (Jul 2025): 42.7 (#83)

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
Omni-MATH55.3%65.4%
LMArena Math14491397
FrontierMath (Feb 2025 set)15.2%21.4%
FrontierMath Tier 4 (v1)4.2%0%
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
OTIS Mock AIME 2024-202577.8%—
ProofBench19%—
MATH Level 597.7%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#76), Kimi K2 (Jul 2025): 37.3 (#157)

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
MMLU-Pro86.9%81.9%
Vectara Hallucination Rate12%17.9%
GPQA (HELM)68.6%65.3%
LMArena Expert14821365
GPQA Diamond82.3%—
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
Confabulations—20.4%

Multimodal Not comparable

Claude Sonnet 4.5: 34.8 (#89), Kimi K2 (Jul 2025): —

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
VPCT39.8%—
LMArena Document1450—

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.4 (#69), Kimi K2 (Jul 2025): 49.6 (#130)

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
LMArena Non-English14251372
LMArena Chinese14591415
LMArena French14581379
LMArena German14271387
LMArena Japanese13901349
LMArena Korean14031325
LMArena Russian14371385
LMArena Spanish14571386

Instruction Following Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 75.0 (#78), Kimi K2 (Jul 2025): 71.1 (#156)

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
IFEval85%85%
LMArena Instruction Following14591348

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), Kimi K2 (Jul 2025): 41.2 (#145)

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
LMArena Longer Query14761353
Fiction.LiveBench—66.7%
CL-bench—17.6%

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), Kimi K2 (Jul 2025): 62.3 (#78)

BenchmarkClaude Sonnet 4.5Kimi K2 (Jul 2025)
LMArena Text14391380
LMArena Creative Writing14421350
EQ-Bench Creative Writing16781666
WildBench85.4%86.2%
LMArena Multi-Turn14651371
Short-Story Creative Writing—85.6%

Frequently asked questions

Is Claude Sonnet 4.5 better than Kimi K2 (Jul 2025)?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 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 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 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 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Kimi K2 (Jul 2025) better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Kimi K2 (Jul 2025) does, with 262K tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and Kimi K2 (Jul 2025) share?

37 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Kimi K2 (Jul 2025) has 42.

Related comparisons

Go deeper