Noometry

Model comparison

Claude Sonnet 4.5 vs Kimi K2.6

Kimi K2.6 is the stronger model overall, scoring 47.7 to 44.1 on the Noometry Index.

Last verified . 42 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Kimi K2.6 Moonshot AI

47.7

Rank #60 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 3 categories and Kimi K2.6 in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.6 leads 57.0 to 32.3.
  • The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 87.2% for Kimi K2.6.
  • Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Kimi K2.6 accepts more context: 262K tokens versus 200K.
  • Kimi K2.6 has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5Kimi K2.6
ProviderAnthropicMoonshot AI
Noometry Index44.147.7
Released2025-09-292026-04-20
WeightsProprietaryOpen
Context window200K262K
Max output64K262K
Input $ / M tokens$3$0.95
Output $ / M tokens$15$4
Results tracked7351

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

Category by category

Coding Kimi K2.6 leads

Claude Sonnet 4.5: 47.3 (#61), Kimi K2.6: 50.7 (#43)

BenchmarkClaude Sonnet 4.5Kimi K2.6
SWE-bench Verified71.3%76.7%
LMArena WebDev13931509
SciCode44.7%53.5%
WeirdML47.7%55.9%
LMArena Coding14891488
ALE-Bench796.151,093
SWE-bench Verified (bash only)71.4%—
SWE-bench Multilingual67%—
GSO14.7%—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), Kimi K2.6: 21.9 (#137)

BenchmarkClaude Sonnet 4.5Kimi K2.6
Vending-Bench 23,8396,205
Terminal-Bench46.5%—
Berkeley Function Calling Leaderboard73.2%—
OSWorld 2.0—4.6%
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%—
ExploitBench—18.4%
GBAEval—0.9%
GDP.pdf—12%
LMArena Search1159—
METR Time Horizons67.4%—

Reasoning Kimi K2.6 leads

Claude Sonnet 4.5: 26.9 (#125), Kimi K2.6: 40.5 (#55)

BenchmarkClaude Sonnet 4.5Kimi K2.6
NYT Connections (extended)37.3%87.2%
CritPt1.1%8%
Chess Puzzles12%26%
EBR-Bench2.4%2.4%
LMArena Hard Prompts14621470
Mystery Game Puzzles17%18%
DTBench83.2%90.9%
LMCA38.8%37.3%
Epoch Capabilities Index146.84151.05
ARC-AGI-213.6%—
SimpleBench54.3%—
Kagi LLM Benchmark57.9%—
ARC-AGI-163.7%—
EnigmaEval6%—
ForecastBench61.9—

Math Kimi K2.6 leads

Claude Sonnet 4.5: 32.3 (#216), Kimi K2.6: 57.0 (#41)

BenchmarkClaude Sonnet 4.5Kimi K2.6
FrontierMath (Tiers 1-3)23.9%57.2%
FrontierMath Tier 42.4%25.6%
OTIS Mock AIME 2024-202577.8%96.1%
ProofBench19%16%
LMArena Math14491475
FrontierMath (Feb 2025 set)15.2%39%
FrontierMath Tier 4 (v1)4.2%14.6%
MathArena Final-Answer Competitions—72.9%
Omni-MATH55.3%—
MATH Level 597.7%—

Knowledge Kimi K2.6 leads

Claude Sonnet 4.5: 48.4 (#76), Kimi K2.6: 54.0 (#54)

BenchmarkClaude Sonnet 4.5Kimi K2.6
GPQA Diamond82.3%90.8%
SimpleQA Verified30.7%34.9%
Vectara Hallucination Rate12%10.8%
LMArena Expert14821491
Humanity's Last Exam13.7%—
MMLU-Pro86.9%—
GPQA (HELM)68.6%—

Multimodal Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 34.8 (#89), Kimi K2.6: 31.6 (#103)

BenchmarkClaude Sonnet 4.5Kimi K2.6
LMArena Document14501451
LMArena Vision—1283
VPCT39.8%—
Blueprint-Bench 2—3.9%
Furniture Assembly—21.7%

Multilingual Kimi K2.6 leads

Claude Sonnet 4.5: 53.4 (#69), Kimi K2.6: 54.9 (#37)

BenchmarkClaude Sonnet 4.5Kimi K2.6
LMArena Non-English14251446
LMArena Chinese14591521
LMArena French14581471
LMArena German14271450
LMArena Japanese13901443
LMArena Korean14031427
LMArena Russian14371446
LMArena Spanish14571464

Instruction Following Kimi K2.6 leads

Claude Sonnet 4.5: 75.0 (#78), Kimi K2.6: 76.3 (#43)

BenchmarkClaude Sonnet 4.5Kimi K2.6
LMArena Instruction Following14591451
IFEval85%—

Long Context Too close to call

Claude Sonnet 4.5: 45.2 (#46), Kimi K2.6: 44.9 (#52)

BenchmarkClaude Sonnet 4.5Kimi K2.6
LMArena Longer Query14761468

Writing & Preference Kimi K2.6 leads

Claude Sonnet 4.5: 66.5 (#34), Kimi K2.6: 68.5 (#26)

BenchmarkClaude Sonnet 4.5Kimi K2.6
LMArena Text14391455
LMArena Creative Writing14421434
EQ-Bench Creative Writing16781725
LMArena Multi-Turn14651453
WildBench85.4%—
EQ-Bench 4—1202

Frequently asked questions

Is Claude Sonnet 4.5 better than Kimi K2.6?

Kimi K2.6 is the stronger model overall, scoring 47.7 to 44.1 on the Noometry Index.

Which is cheaper, Claude Sonnet 4.5 or Kimi K2.6?

Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Kimi K2.6 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 47.3 in the Noometry coding category.

Which has the bigger context window?

Kimi K2.6 does, with 262K tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and Kimi K2.6 share?

42 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Kimi K2.6 has 51.

Related comparisons

Go deeper