Noometry

Model comparison

Claude Fable 5 vs Kimi K2.5

Claude Fable 5 is the stronger model overall, scoring 66.8 to 48.1 on the Noometry Index. Kimi K2.5 costs 22× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 37 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

Kimi K2.5 Moonshot AI

48.1

Rank #57 Confirmed

Summary

  • They share 37 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and Kimi K2.5 in 1 category; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 31.2.
  • The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Claude Fable 5 and 11.8% for Kimi K2.5.
  • Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $10 / $50 for Claude Fable 5.
  • Claude Fable 5 accepts more context: 1M tokens versus 262K.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5Kimi K2.5
ProviderAnthropicMoonshot AI
Noometry Index66.848.1
Released2026-06-072026-01-27
WeightsProprietaryOpen
Context window1M262K
Max output128K262K
Input $ / M tokens$10$0.45
Output $ / M tokens$50$2.25
Results tracked6251

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

Category by category

Coding Claude Fable 5 leads

Claude Fable 5: 70.6 (#4), Kimi K2.5: 48.8 (#53)

BenchmarkClaude Fable 5Kimi K2.5
LMArena WebDev16251437
SciCode61%49%
WeirdML91.9%45.6%
LMArena Coding15191474
ALE-Bench2,041821.65
SWE-bench Verified—73.8%
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—70.8%
SWE-bench Multilingual—67.3%
FrontierSWE47%—
GSO78.4%—
MirrorCode63.9%—

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), Kimi K2.5: 34.2 (#48)

BenchmarkClaude Fable 5Kimi K2.5
Vending-Bench 25,6801,198
Terminal-Bench—43.2%
APEX-Agents63.6%—
Remote Labor Index16.1%—
τ²-bench Banking39.7%—
OSWorld—63.3%
PostTrainBench41.8%—
GBAEval74.5%—
GDP.pdf30%—
LMArena Search1230—

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), Kimi K2.5: 31.2 (#80)

BenchmarkClaude Fable 5Kimi K2.5
ARC-AGI-289.2%11.8%
SimpleBench81.9%46.8%
Kagi LLM Benchmark91.4%78.5%
NYT Connections (extended)92.7%69.9%
ARC-AGI-198.5%65.3%
CritPt28.6%3.1%
Chess Puzzles41%12%
EnigmaEval39.3%3.4%
LMArena Hard Prompts15081453
Epoch Capabilities Index162.06148.03
Thematic Generalization—69.4%
EBR-Bench39.5%—
Mystery Game Puzzles52%—
DTBench98.4%—
LMCA61.1%—
Surface Evolver Bench95%—
Bench to the Future 30.13—

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), Kimi K2.5: 51.8 (#53)

BenchmarkClaude Fable 5Kimi K2.5
OTIS Mock AIME 2024-2025100%92.2%
LMArena Math15191470
FrontierMath (Tiers 1-3)87%—
FrontierMath Tier 490.2%—
MathArena Final-Answer Competitions—62.3%
ProofBench95%—
FrontierMath (Feb 2025 set)—27.9%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—4.2%

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), Kimi K2.5: 53.6 (#56)

BenchmarkClaude Fable 5Kimi K2.5
GPQA Diamond85.9%87.6%
SimpleQA Verified70.7%34.3%
LMArena Expert15341466
Humanity's Last Exam—24.4%
Vectara Hallucination Rate—14.2%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.3 (#17), Kimi K2.5: 41.1 (#39)

BenchmarkClaude Fable 5Kimi K2.5
LMArena Vision13241269
LMArena Document14961430
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), Kimi K2.5: 53.9 (#53)

BenchmarkClaude Fable 5Kimi K2.5
LMArena Non-English14811433
LMArena Chinese15431495
LMArena French15051454
LMArena German14861441
LMArena Japanese15061421
LMArena Korean14881410
LMArena Russian15041435
LMArena Spanish14981450

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), Kimi K2.5: 75.3 (#64)

BenchmarkClaude Fable 5Kimi K2.5
LMArena Instruction Following15021431

Long Context Kimi K2.5 leads

Claude Fable 5: 46.3 (#23), Kimi K2.5: 52.1 (#7)

BenchmarkClaude Fable 5Kimi K2.5
LMArena Longer Query15091445
Fiction.LiveBench—86.1%
CL-bench—19.3%
CL-bench Life—13.2%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), Kimi K2.5: 65.1 (#53)

BenchmarkClaude Fable 5Kimi K2.5
LMArena Text14911445
LMArena Creative Writing14941423
EQ-Bench Creative Writing19431579
LMArena Multi-Turn15041444
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than Kimi K2.5?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 48.1 on the Noometry Index. Kimi K2.5 costs 22× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Which is cheaper, Claude Fable 5 or Kimi K2.5?

Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or Kimi K2.5 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 48.8 in the Noometry coding category.

Which has the bigger context window?

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

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

37 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Kimi K2.5 has 51.

Related comparisons

Go deeper