Noometry

Model comparison

Claude Opus 5 vs Kimi K2 (Jul 2025)

Claude Opus 5 is the stronger model overall, scoring 67.8 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 5's lead doesn't matter for your workload.

Last verified . 22 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

Kimi K2 (Jul 2025) Moonshot AI

41.2

Rank #140 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude Opus 5 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 5 leads 77.2 to 23.3.
  • The biggest single-benchmark swing is SimpleBench: 80.6% for Claude Opus 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 5.
  • Claude Opus 5 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 5Kimi K2 (Jul 2025)
ProviderAnthropicMoonshot AI
Noometry Index67.841.2
Released2026-07-242025-07-12
WeightsProprietaryOpen
Context window1M262K
Max output128K262K
Input $ / M tokens$5$0.57
Output $ / M tokens$25$2.30
Results tracked5742

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

Category by category

Coding Claude Opus 5 leads

Claude Opus 5: 67.5 (#5), Kimi K2 (Jul 2025): 42.4 (#102)

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
WeirdML91.8%42.8%
LMArena Coding15341399
ALE-Bench2,165597.5
DeepSWE73.6%—
FrontierCode53.4%—
SWE-bench Verified (bash only)—63.4%
Aider Polyglot—59.1%
CursorBench46.6%—
LMArena WebDev1691—
FrontierSWE52%—
SciCode56.4%—
GSO—4.9%

Agentic & Tool Use Claude Opus 5 leads

Claude Opus 5: 55.6 (#1), Kimi K2 (Jul 2025): 32.4 (#64)

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
Terminal-Bench—35.7%
APEX-Agents65.8%—
Berkeley Function Calling Leaderboard—59.1%
OSWorld 2.031.4%—
τ²-bench Banking48.7%—
PostTrainBench35%—
BALROG63.4%—
GBAEval79.6%—
GDP.pdf24%—
METR Time Horizons—59.2%
Vending-Bench 211,182—

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), Kimi K2 (Jul 2025): 23.3 (#179)

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
SimpleBench80.6%26.3%
LMArena Hard Prompts15261384
Epoch Capabilities Index162.78146.01
ARC-AGI-290.4%—
Kagi LLM Benchmark—64.4%
NYT Connections (extended)94.3%—
ARC-AGI-197.5%—
CritPt29.1%—
Chess Puzzles42%—
EBR-Bench45.7%—
Mystery Game Puzzles59%—
DTBench97.9%—
LMCA64.5%—
Bench to the Future 30.12—
ForecastBench—60.2

Math Claude Opus 5 leads

Claude Opus 5: 86.2 (#8), Kimi K2 (Jul 2025): 42.7 (#83)

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
LMArena Math15311397
FrontierMath (Tiers 1-3)85.6%—
FrontierMath Tier 473.2%—
OTIS Mock AIME 2024-202598.9%—
ProofBench99%—
Omni-MATH—65.4%
FrontierMath (Feb 2025 set)—21.4%
FrontierMath Tier 4 (v1)—0%

Knowledge Claude Opus 5 leads

Claude Opus 5: 66.8 (#9), Kimi K2 (Jul 2025): 37.3 (#157)

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
LMArena Expert15571365
GPQA Diamond93.9%—
SimpleQA Verified59.9%—
MMLU-Pro—81.9%
Confabulations—20.4%
Vectara Hallucination Rate—17.9%
GPQA (HELM)—65.3%

Multimodal Not comparable

Claude Opus 5: 50.8 (#8), Kimi K2 (Jul 2025): —

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
LMArena Vision1319—
Blueprint-Bench 230.4%—
Furniture Assembly60.8%—
LMArena Document1516—

Multilingual Claude Opus 5 leads

Claude Opus 5: 58.8 (#4), Kimi K2 (Jul 2025): 49.6 (#130)

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
LMArena Non-English15011372
LMArena Chinese15741415
LMArena French15191379
LMArena German15241387
LMArena Japanese15161349
LMArena Korean15211325
LMArena Russian15071385
LMArena Spanish15191386

Instruction Following Claude Opus 5 leads

Claude Opus 5: 79.2 (#7), Kimi K2 (Jul 2025): 71.1 (#156)

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
LMArena Instruction Following15171348
IFEval—85%

Long Context Claude Opus 5 leads

Claude Opus 5: 46.5 (#21), Kimi K2 (Jul 2025): 41.2 (#145)

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
LMArena Longer Query15151353
Fiction.LiveBench—66.7%
CL-bench—17.6%

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.2 (#1), Kimi K2 (Jul 2025): 62.3 (#78)

BenchmarkClaude Opus 5Kimi K2 (Jul 2025)
LMArena Text15071380
LMArena Creative Writing14911350
EQ-Bench Creative Writing21331666
LMArena Multi-Turn14991371
Short-Story Creative Writing—85.6%
WildBench—86.2%
EQ-Bench 41385—

Frequently asked questions

Is Claude Opus 5 better than Kimi K2 (Jul 2025)?

Claude Opus 5 is the stronger model overall, scoring 67.8 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 5's lead doesn't matter for your workload.

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

Is Claude Opus 5 or Kimi K2 (Jul 2025) better for coding?

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 5 does, with 1M tokens against 262K.

How many benchmarks do Claude Opus 5 and Kimi K2 (Jul 2025) share?

22 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Kimi K2 (Jul 2025) has 42.

Related comparisons

Go deeper