Noometry

Model comparison

Claude Opus 4.6 vs Kimi K2.6

Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 47.5 on the Noometry Index. Kimi K2.6 costs 5.8× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 45 shared benchmarks.

Claude Opus 4.6 Anthropic

58.3

Rank #18 Confirmed

Kimi K2.6 Moonshot AI

47.5

Rank #52 Confirmed

Summary

  • They share 45 benchmarks with published results for both. Claude Opus 4.6 scores higher in 10 categories and Kimi K2.6 in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Opus 4.6 leads 51.0 to 21.8.
  • The biggest single-benchmark swing is GBAEval: 44.1% for Claude Opus 4.6 and 0.9% for Kimi K2.6.
  • Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
  • Claude Opus 4.6 accepts more context: 1M tokens versus 262K.
  • Kimi K2.6 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.6Kimi K2.6
ProviderAnthropicMoonshot AI
Noometry Index58.347.5
Released2026-02-042026-04-20
WeightsProprietaryOpen
Context window1M262K
Max output128K262K
Input $ / M tokens$5$0.95
Output $ / M tokens$25$4
Results tracked6851

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

Category by category

Coding Claude Opus 4.6 leads

Claude Opus 4.6: 57.7 (#15), Kimi K2.6: 50.5 (#41)

BenchmarkClaude Opus 4.6Kimi K2.6
SWE-bench Verified78.7%76.7%
LMArena WebDev15461509
WeirdML78%55.9%
LMArena Coding15351488
ALE-Bench996.51,093
FrontierCode26.6%—
SWE-bench Verified (bash only)75.6%—
SWE-bench Multilingual72%—
SciCode—53.5%
GSO41.2%—
AlgoTune1.47—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.0 (#4), Kimi K2.6: 21.8 (#128)

BenchmarkClaude Opus 4.6Kimi K2.6
GBAEval44.1%0.9%
Vending-Bench 28,0186,205
Terminal-Bench79.8%—
APEX-Agents46.3%—
OSWorld 2.0—4.6%
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
ExploitBench—18.4%
GDP.pdf—12%
LMArena Search1253—
METR Time Horizons78.9%—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.7 (#21), Kimi K2.6: 39.6 (#51)

BenchmarkClaude Opus 4.6Kimi K2.6
NYT Connections (extended)92.1%87.2%
Chess Puzzles17%26%
EBR-Bench12.7%2.4%
LMArena Hard Prompts15271470
Mystery Game Puzzles25%18%
DTBench91.2%90.9%
LMCA55.8%37.3%
Epoch Capabilities Index155.36151.03
ARC-AGI-269.2%—
SimpleBench67.6%—
Kagi LLM Benchmark83.6%—
ARC-AGI-194%—
CritPt—8%
EnigmaEval7.6%—
Thematic Generalization80.6%—
ForecastBench60—

Math Claude Opus 4.6 leads

Claude Opus 4.6: 62.7 (#25), Kimi K2.6: 56.8 (#34)

BenchmarkClaude Opus 4.6Kimi K2.6
FrontierMath (Tiers 1-3)66%57.2%
FrontierMath Tier 426.8%25.6%
MathArena Final-Answer Competitions78.5%72.9%
OTIS Mock AIME 2024-202594.4%96.1%
ProofBench50%16%
LMArena Math15171475
FrontierMath (Feb 2025 set)40.7%39%
FrontierMath Tier 4 (v1)22.9%14.6%

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.8 (#23), Kimi K2.6: 53.9 (#48)

BenchmarkClaude Opus 4.6Kimi K2.6
GPQA Diamond90.5%90.8%
SimpleQA Verified47%34.9%
Vectara Hallucination Rate12.2%10.8%
LMArena Expert15461491
Humanity's Last Exam34.4%—

Multimodal Claude Opus 4.6 leads

Claude Opus 4.6: 37.0 (#67), Kimi K2.6: 31.8 (#95)

BenchmarkClaude Opus 4.6Kimi K2.6
LMArena Vision13161282
Furniture Assembly28.3%21.7%
LMArena Document15071451
Blueprint-Bench 2—3.9%

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 58.2 (#4), Kimi K2.6: 55.1 (#35)

BenchmarkClaude Opus 4.6Kimi K2.6
LMArena Non-English14901446
LMArena Chinese15511521
LMArena French15131471
LMArena German15041449
LMArena Japanese14841442
LMArena Korean14651428
LMArena Russian14971446
LMArena Spanish15121463

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.7 (#3), Kimi K2.6: 76.5 (#40)

BenchmarkClaude Opus 4.6Kimi K2.6
LMArena Instruction Following15231451

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), Kimi K2.6: 44.9 (#50)

BenchmarkClaude Opus 4.6Kimi K2.6
LMArena Longer Query15201468
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.7 (#9), Kimi K2.6: 68.7 (#25)

BenchmarkClaude Opus 4.6Kimi K2.6
LMArena Text15041455
LMArena Creative Writing15061434
EQ-Bench Creative Writing18091725
EQ-Bench 412231202
LMArena Multi-Turn15141453

Frequently asked questions

Is Claude Opus 4.6 better than Kimi K2.6?

Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 47.5 on the Noometry Index. Kimi K2.6 costs 5.8× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.6 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 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or Kimi K2.6 better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.7 versus 50.5 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do Claude Opus 4.6 and Kimi K2.6 share?

45 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Kimi K2.6 has 51.

Related comparisons

Go deeper