Noometry

Model comparison

Claude Opus 4.5 vs Kimi K2.6

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 47.7 on the Noometry Index. Kimi K2.6 costs 5.8× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 41 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Kimi K2.6 Moonshot AI

47.7

Rank #60 Confirmed

Summary

  • They share 41 benchmarks with published results for both. Claude Opus 4.5 scores higher in 6 categories and Kimi K2.6 in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Opus 4.5 leads 47.3 to 21.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 52.5% for Claude Opus 4.5 and 87.2% for Kimi K2.6.
  • Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $5 / $25 for Claude Opus 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 Opus 4.5Kimi K2.6
ProviderAnthropicMoonshot AI
Noometry Index50.547.7
Released2025-11-012026-04-20
WeightsProprietaryOpen
Context window200K262K
Max output64K262K
Input $ / M tokens$5$0.95
Output $ / M tokens$25$4
Results tracked6951

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

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 54.8 (#27), Kimi K2.6: 50.7 (#43)

BenchmarkClaude Opus 4.5Kimi K2.6
SWE-bench Verified76.7%76.7%
LMArena WebDev14941509
WeirdML63.7%55.9%
LMArena Coding15041488
ALE-Bench1,0251,093
SWE-bench Verified (bash only)76.8%—
SWE-bench Multilingual70.7%—
SciCode—53.5%
GSO26.5%—
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.3 (#12), Kimi K2.6: 21.9 (#137)

BenchmarkClaude Opus 4.5Kimi K2.6
Vending-Bench 24,9676,205
Terminal-Bench63.1%—
Berkeley Function Calling Leaderboard77.5%—
OSWorld 2.0—4.6%
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
BALROG43.5%—
ExploitBench—18.4%
GBAEval—0.9%
GDP.pdf—12%
LMArena Search1180—
METR Time Horizons75%—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.6 (#51), Kimi K2.6: 40.5 (#55)

BenchmarkClaude Opus 4.5Kimi K2.6
NYT Connections (extended)52.5%87.2%
Chess Puzzles12%26%
EBR-Bench14.3%2.4%
LMArena Hard Prompts14761470
Mystery Game Puzzles22%18%
DTBench89.9%90.9%
LMCA44.5%37.3%
Epoch Capabilities Index150.09151.05
ARC-AGI-237.6%—
SimpleBench62%—
Kagi LLM Benchmark80.2%—
ARC-AGI-180%—
CritPt—8%
EnigmaEval11.9%—
ForecastBench60.7—

Math Kimi K2.6 leads

Claude Opus 4.5: 38.6 (#132), Kimi K2.6: 57.0 (#41)

BenchmarkClaude Opus 4.5Kimi K2.6
FrontierMath (Tiers 1-3)34.4%57.2%
FrontierMath Tier 44.9%25.6%
OTIS Mock AIME 2024-202586.1%96.1%
ProofBench36%16%
LMArena Math14631475
FrontierMath (Feb 2025 set)20.7%39%
FrontierMath Tier 4 (v1)4.2%14.6%
MathArena Final-Answer Competitions—72.9%

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.5 (#44), Kimi K2.6: 54.0 (#54)

BenchmarkClaude Opus 4.5Kimi K2.6
GPQA Diamond86%90.8%
SimpleQA Verified45.7%34.9%
Vectara Hallucination Rate10.9%10.8%
LMArena Expert14871491
Humanity's Last Exam25.2%—

Multimodal Too close to call

Claude Opus 4.5: 31.4 (#107), Kimi K2.6: 31.6 (#103)

BenchmarkClaude Opus 4.5Kimi K2.6
Furniture Assembly28.3%21.7%
LMArena Document14621451
LMArena Vision—1283
GeoBench75%—
VPCT40%—
Blueprint-Bench 2—3.9%

Multilingual Too close to call

Claude Opus 4.5: 54.3 (#47), Kimi K2.6: 54.9 (#37)

BenchmarkClaude Opus 4.5Kimi K2.6
LMArena Non-English14381446
LMArena Chinese14701521
LMArena French14711471
LMArena German14491450
LMArena Japanese14161443
LMArena Korean14241427
LMArena Russian14471446
LMArena Spanish14581464

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), Kimi K2.6: 76.3 (#43)

BenchmarkClaude Opus 4.5Kimi K2.6
LMArena Instruction Following14781451

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), Kimi K2.6: 44.9 (#52)

BenchmarkClaude Opus 4.5Kimi K2.6
LMArena Longer Query14801468
CL-bench21.1%—

Writing & Preference Too close to call

Claude Opus 4.5: 68.1 (#28), Kimi K2.6: 68.5 (#26)

BenchmarkClaude Opus 4.5Kimi K2.6
LMArena Text14511455
LMArena Creative Writing14451434
EQ-Bench Creative Writing16871725
LMArena Multi-Turn14661453
EQ-Bench 4—1202

Frequently asked questions

Is Claude Opus 4.5 better than Kimi K2.6?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 47.7 on the Noometry Index. Kimi K2.6 costs 5.8× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 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 Opus 4.5 lists at $5 and $25.

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

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 50.7 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 Opus 4.5 and Kimi K2.6 share?

41 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Kimi K2.6 has 51.

Related comparisons

Go deeper