Noometry

Model comparison

Claude Opus 5 vs Kimi K2.5 Instant

Claude Opus 5 is the stronger model overall, scoring 67.8 to 43.6 on the Noometry Index.

Last verified . 18 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

Kimi K2.5 Instant Moonshot AI

43.6

Rank #89 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Claude Opus 5 scores higher in 9 categories and Kimi K2.5 Instant in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 5 leads 77.2 to 29.7.
  • Kimi K2.5 Instant has downloadable open weights; the other is API-only.

Side by side

Claude Opus 5Kimi K2.5 Instant
ProviderAnthropicMoonshot AI
Noometry Index67.843.6
Released2026-07-24—
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$5—
Output $ / M tokens$25—
Results tracked5718

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 K2.5 Instant: 42.6 (#97)

BenchmarkClaude Opus 5Kimi K2.5 Instant
LMArena WebDev16911404
LMArena Coding15341484
DeepSWE73.6%—
FrontierCode53.4%—
CursorBench46.6%—
FrontierSWE52%—
SciCode56.4%—
WeirdML91.8%—
ALE-Bench2,165—

Agentic & Tool Use Not comparable

Claude Opus 5: 55.6 (#1), Kimi K2.5 Instant: —

BenchmarkClaude Opus 5Kimi K2.5 Instant
APEX-Agents65.8%—
OSWorld 2.031.4%—
τ²-bench Banking48.7%—
PostTrainBench35%—
BALROG63.4%—
GBAEval79.6%—
GDP.pdf24%—
Vending-Bench 211,182—

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), Kimi K2.5 Instant: 29.7 (#90)

BenchmarkClaude Opus 5Kimi K2.5 Instant
LMArena Hard Prompts15261443
ARC-AGI-290.4%—
SimpleBench80.6%—
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—
Epoch Capabilities Index162.78—

Math Claude Opus 5 leads

Claude Opus 5: 86.2 (#8), Kimi K2.5 Instant: 39.4 (#105)

BenchmarkClaude Opus 5Kimi K2.5 Instant
LMArena Math15311442
FrontierMath (Tiers 1-3)85.6%—
FrontierMath Tier 473.2%—
OTIS Mock AIME 2024-202598.9%—
ProofBench99%—

Knowledge Claude Opus 5 leads

Claude Opus 5: 66.8 (#9), Kimi K2.5 Instant: 40.2 (#123)

BenchmarkClaude Opus 5Kimi K2.5 Instant
LMArena Expert15571440
GPQA Diamond93.9%—
SimpleQA Verified59.9%—

Multimodal Claude Opus 5 leads

Claude Opus 5: 50.8 (#8), Kimi K2.5 Instant: 40.2 (#50)

BenchmarkClaude Opus 5Kimi K2.5 Instant
LMArena Vision13191254
Blueprint-Bench 230.4%—
Furniture Assembly60.8%—
LMArena Document1516—

Multilingual Claude Opus 5 leads

Claude Opus 5: 58.8 (#4), Kimi K2.5 Instant: 52.0 (#94)

BenchmarkClaude Opus 5Kimi K2.5 Instant
LMArena Non-English15011406
LMArena Chinese15741449
LMArena French15191403
LMArena German15241413
LMArena Korean15211378
LMArena Russian15071404
LMArena Spanish15191447
LMArena Japanese1516—

Instruction Following Claude Opus 5 leads

Claude Opus 5: 79.2 (#7), Kimi K2.5 Instant: 75.3 (#65)

BenchmarkClaude Opus 5Kimi K2.5 Instant
LMArena Instruction Following15171430

Long Context Claude Opus 5 leads

Claude Opus 5: 46.5 (#21), Kimi K2.5 Instant: 43.9 (#83)

BenchmarkClaude Opus 5Kimi K2.5 Instant
LMArena Longer Query15151435

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.2 (#1), Kimi K2.5 Instant: 60.6 (#95)

BenchmarkClaude Opus 5Kimi K2.5 Instant
LMArena Text15071420
LMArena Creative Writing14911381
LMArena Multi-Turn14991427
EQ-Bench Creative Writing2133—
EQ-Bench 41385—

Frequently asked questions

Is Claude Opus 5 better than Kimi K2.5 Instant?

Claude Opus 5 is the stronger model overall, scoring 67.8 to 43.6 on the Noometry Index.

Is Claude Opus 5 or Kimi K2.5 Instant better for coding?

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 42.6 in the Noometry coding category.

How many benchmarks do Claude Opus 5 and Kimi K2.5 Instant share?

18 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Kimi K2.5 Instant has 18.

Related comparisons

Go deeper