Noometry

Model comparison

Claude Opus 4.6 vs Kimi K2 (Jul 2025)

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 10.0× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 32 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

Kimi K2 (Jul 2025) Moonshot AI

41.2

Rank #140 Confirmed

Summary

  • They share 32 benchmarks with published results for both. Claude Opus 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 Opus 4.6 leads 57.8 to 23.3.
  • The biggest single-benchmark swing is Terminal-Bench: 79.8% for Claude Opus 4.6 and 35.7% for Kimi K2 (Jul 2025).
  • Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 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 (Jul 2025) has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.6Kimi K2 (Jul 2025)
ProviderAnthropicMoonshot AI
Noometry Index58.241.2
Released2026-02-042025-07-12
WeightsProprietaryOpen
Context window1M262K
Max output128K262K
Input $ / M tokens$5$0.57
Output $ / M tokens$25$2.30
Results tracked6842

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: 57.2 (#20), Kimi K2 (Jul 2025): 42.4 (#102)

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
SWE-bench Verified (bash only)75.6%63.4%
GSO41.2%4.9%
WeirdML78%42.8%
LMArena Coding15361399
ALE-Bench996.5597.5
SWE-bench Verified78.7%—
FrontierCode26.6%—
Aider Polyglot—59.1%
LMArena WebDev1547—
SWE-bench Multilingual72%—
AlgoTune1.47—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), Kimi K2 (Jul 2025): 32.4 (#64)

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
Terminal-Bench79.8%35.7%
METR Time Horizons78.9%59.2%
APEX-Agents46.3%—
Berkeley Function Calling Leaderboard—59.1%
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
GBAEval44.1%—
LMArena Search1253—
Vending-Bench 28,018—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), Kimi K2 (Jul 2025): 23.3 (#179)

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
SimpleBench67.6%26.3%
Kagi LLM Benchmark83.6%64.4%
LMArena Hard Prompts15271384
Epoch Capabilities Index155.24146.01
ForecastBench6060.2
ARC-AGI-269.2%—
NYT Connections (extended)92.1%—
ARC-AGI-194%—
Chess Puzzles17%—
EnigmaEval7.6%—
Thematic Generalization80.6%—
EBR-Bench12.7%—
Mystery Game Puzzles25%—
DTBench91.2%—
LMCA55.8%—

Math Claude Opus 4.6 leads

Claude Opus 4.6: 63.0 (#31), Kimi K2 (Jul 2025): 42.7 (#83)

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
LMArena Math15191397
FrontierMath (Feb 2025 set)40.7%21.4%
FrontierMath Tier 4 (v1)22.9%0%
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions78.5%—
OTIS Mock AIME 2024-202594.4%—
ProofBench50%—
Omni-MATH—65.4%

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), Kimi K2 (Jul 2025): 37.3 (#157)

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
Vectara Hallucination Rate12.2%17.9%
LMArena Expert15461365
GPQA Diamond90.5%—
Humanity's Last Exam34.4%—
SimpleQA Verified47%—
MMLU-Pro—81.9%
Confabulations—20.4%
GPQA (HELM)—65.3%

Multimodal Not comparable

Claude Opus 4.6: 37.3 (#74), Kimi K2 (Jul 2025): —

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
LMArena Vision1316—
Furniture Assembly28.3%—
LMArena Document1507—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), Kimi K2 (Jul 2025): 49.6 (#130)

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
LMArena Non-English14891372
LMArena Chinese15511415
LMArena French15131379
LMArena German15021387
LMArena Japanese14841349
LMArena Korean14641325
LMArena Russian14971385
LMArena Spanish15101386

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), Kimi K2 (Jul 2025): 71.1 (#156)

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
LMArena Instruction Following15231348
IFEval—85%

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), Kimi K2 (Jul 2025): 41.2 (#145)

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
CL-bench20.7%17.6%
LMArena Longer Query15201353
Fiction.LiveBench—66.7%
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), Kimi K2 (Jul 2025): 62.3 (#78)

BenchmarkClaude Opus 4.6Kimi K2 (Jul 2025)
LMArena Text15031380
LMArena Creative Writing15051350
EQ-Bench Creative Writing18091666
LMArena Multi-Turn15131371
Short-Story Creative Writing—85.6%
WildBench—86.2%
EQ-Bench 41223—

Frequently asked questions

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

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 10.0× 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 (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 Opus 4.6 lists at $5 and $25.

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

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 42.4 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 (Jul 2025) share?

32 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Kimi K2 (Jul 2025) has 42.

Related comparisons

Go deeper