Noometry

Model comparison

Claude Opus 4.5 vs Kimi K2 (Jul 2025)

Claude Opus 4.5 is the stronger model overall, scoring 50.5 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 4.5's lead doesn't matter for your workload.

Last verified . 33 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Kimi K2 (Jul 2025) Moonshot AI

41.2

Rank #140 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Claude Opus 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 reasoning, where Claude Opus 4.5 leads 42.6 to 23.3.
  • The biggest single-benchmark swing is SimpleBench: 62% for Claude Opus 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 $5 / $25 for Claude Opus 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 Opus 4.5Kimi K2 (Jul 2025)
ProviderAnthropicMoonshot AI
Noometry Index50.541.2
Released2025-11-012025-07-12
WeightsProprietaryOpen
Context window200K262K
Max output64K262K
Input $ / M tokens$5$0.57
Output $ / M tokens$25$2.30
Results tracked6942

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 (Jul 2025): 42.4 (#102)

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
SWE-bench Verified (bash only)76.8%63.4%
GSO26.5%4.9%
WeirdML63.7%42.8%
LMArena Coding15041399
ALE-Bench1,025597.5
SWE-bench Verified76.7%—
Aider Polyglot—59.1%
LMArena WebDev1494—
SWE-bench Multilingual70.7%—
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.3 (#12), Kimi K2 (Jul 2025): 32.4 (#64)

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
Terminal-Bench63.1%35.7%
Berkeley Function Calling Leaderboard77.5%59.1%
METR Time Horizons75%59.2%
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%—
LMArena Search1180—
Vending-Bench 24,967—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.6 (#51), Kimi K2 (Jul 2025): 23.3 (#179)

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
SimpleBench62%26.3%
Kagi LLM Benchmark80.2%64.4%
LMArena Hard Prompts14761384
Epoch Capabilities Index150.09146.01
ForecastBench60.760.2
ARC-AGI-237.6%—
NYT Connections (extended)52.5%—
ARC-AGI-180%—
Chess Puzzles12%—
EnigmaEval11.9%—
EBR-Bench14.3%—
Mystery Game Puzzles22%—
DTBench89.9%—
LMCA44.5%—

Math Kimi K2 (Jul 2025) leads

Claude Opus 4.5: 38.6 (#132), Kimi K2 (Jul 2025): 42.7 (#83)

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
LMArena Math14631397
FrontierMath (Feb 2025 set)20.7%21.4%
FrontierMath Tier 4 (v1)4.2%0%
FrontierMath (Tiers 1-3)34.4%—
FrontierMath Tier 44.9%—
OTIS Mock AIME 2024-202586.1%—
ProofBench36%—
Omni-MATH—65.4%

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.5 (#44), Kimi K2 (Jul 2025): 37.3 (#157)

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
Vectara Hallucination Rate10.9%17.9%
LMArena Expert14871365
GPQA Diamond86%—
Humanity's Last Exam25.2%—
SimpleQA Verified45.7%—
MMLU-Pro—81.9%
Confabulations—20.4%
GPQA (HELM)—65.3%

Multimodal Not comparable

Claude Opus 4.5: 31.4 (#107), Kimi K2 (Jul 2025): —

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
GeoBench75%—
VPCT40%—
Furniture Assembly28.3%—
LMArena Document1462—

Multilingual Claude Opus 4.5 leads

Claude Opus 4.5: 54.3 (#47), Kimi K2 (Jul 2025): 49.6 (#130)

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
LMArena Non-English14381372
LMArena Chinese14701415
LMArena French14711379
LMArena German14491387
LMArena Japanese14161349
LMArena Korean14241325
LMArena Russian14471385
LMArena Spanish14581386

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), Kimi K2 (Jul 2025): 71.1 (#156)

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
LMArena Instruction Following14781348
IFEval—85%

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), Kimi K2 (Jul 2025): 41.2 (#145)

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
CL-bench21.1%17.6%
LMArena Longer Query14801353
Fiction.LiveBench—66.7%

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.1 (#28), Kimi K2 (Jul 2025): 62.3 (#78)

BenchmarkClaude Opus 4.5Kimi K2 (Jul 2025)
LMArena Text14511380
LMArena Creative Writing14451350
EQ-Bench Creative Writing16871666
LMArena Multi-Turn14661371
Short-Story Creative Writing—85.6%
WildBench—86.2%

Frequently asked questions

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

Claude Opus 4.5 is the stronger model overall, scoring 50.5 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 4.5's lead doesn't matter for your workload.

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

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

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 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 Opus 4.5 and Kimi K2 (Jul 2025) share?

33 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Kimi K2 (Jul 2025) has 42.

Related comparisons

Go deeper