Noometry

Model comparison

Claude Fable 5 vs Claude Haiku 4.5

Claude Fable 5 is the stronger model overall, scoring 66.8 to 39.5 on the Noometry Index. Claude Haiku 4.5 costs 10× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 36 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

Claude Haiku 4.5 Anthropic

39.5

Rank #165 Confirmed

Summary

  • They share 36 benchmarks with published results for both. Claude Fable 5 scores higher in 10 categories and Claude Haiku 4.5 in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 15.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Claude Fable 5 and 4% for Claude Haiku 4.5.
  • Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $10 / $50 for Claude Fable 5.
  • Claude Fable 5 accepts more context: 1M tokens versus 200K.

Side by side

Claude Fable 5Claude Haiku 4.5
ProviderAnthropicAnthropic
Noometry Index66.839.5
Released2026-06-072025-10-15
WeightsProprietaryProprietary
Context window1M200K
Max output128K64K
Input $ / M tokens$10$1
Output $ / M tokens$50$5
Results tracked6253

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), Claude Haiku 4.5: 44.0 (#78)

BenchmarkClaude Fable 5Claude Haiku 4.5
LMArena WebDev16251330
SciCode61%43.3%
WeirdML91.9%45.4%
LMArena Coding15191453
ALE-Bench2,041653.48
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—66.6%
SWE-bench Multilingual—64.7%
FrontierSWE47%—
GSO78.4%—
MirrorCode63.9%—

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), Claude Haiku 4.5: 33.6 (#52)

BenchmarkClaude Fable 5Claude Haiku 4.5
Vending-Bench 25,680458.89
Terminal-Bench—35.5%
APEX-Agents63.6%—
Berkeley Function Calling Leaderboard—68.7%
Remote Labor Index16.1%—
τ²-bench Banking39.7%—
DeepResearch Bench—45.5%
PostTrainBench41.8%—
BALROG—31.2%
ExploitBench—13.7%
GBAEval74.5%—
GDP.pdf30%—
LMArena Search1230—

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), Claude Haiku 4.5: 15.1 (#320)

BenchmarkClaude Fable 5Claude Haiku 4.5
ARC-AGI-289.2%4%
NYT Connections (extended)92.7%14.3%
ARC-AGI-198.5%47.7%
CritPt28.6%0%
Chess Puzzles41%8%
LMArena Hard Prompts15081420
DTBench98.4%73.6%
LMCA61.1%30.9%
Epoch Capabilities Index162.06142.41
SimpleBench81.9%—
Kagi LLM Benchmark91.4%—
EnigmaEval39.3%—
EBR-Bench39.5%—
Mystery Game Puzzles52%—
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—61.4

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), Claude Haiku 4.5: 44.9 (#78)

BenchmarkClaude Fable 5Claude Haiku 4.5
OTIS Mock AIME 2024-2025100%66.7%
LMArena Math15191396
FrontierMath (Tiers 1-3)87%—
FrontierMath Tier 490.2%—
ProofBench95%—
Omni-MATH—56.1%
MATH Level 5—96.4%
FrontierMath (Feb 2025 set)—5.9%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—2.1%

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), Claude Haiku 4.5: 37.7 (#153)

BenchmarkClaude Fable 5Claude Haiku 4.5
GPQA Diamond85.9%71.2%
SimpleQA Verified70.7%13.2%
LMArena Expert15341442
MMLU-Pro—77.7%
Vectara Hallucination Rate—9.8%
GPQA (HELM)—60.5%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.3 (#17), Claude Haiku 4.5: 26.8 (#118)

BenchmarkClaude Fable 5Claude Haiku 4.5
Blueprint-Bench 238.6%0%
LMArena Document14961420
LMArena Vision1324—
Furniture Assembly35.8%—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), Claude Haiku 4.5: 49.9 (#129)

BenchmarkClaude Fable 5Claude Haiku 4.5
LMArena Non-English14811377
LMArena Chinese15431417
LMArena French15051408
LMArena German14861375
LMArena Japanese15061339
LMArena Korean14881347
LMArena Russian15041381
LMArena Spanish14981420

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), Claude Haiku 4.5: 71.4 (#149)

BenchmarkClaude Fable 5Claude Haiku 4.5
LMArena Instruction Following15021414
IFEval—80.1%

Long Context Claude Fable 5 leads

Claude Fable 5: 46.3 (#23), Claude Haiku 4.5: 43.6 (#92)

BenchmarkClaude Fable 5Claude Haiku 4.5
LMArena Longer Query15091427

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), Claude Haiku 4.5: 57.9 (#123)

BenchmarkClaude Fable 5Claude Haiku 4.5
LMArena Text14911396
LMArena Creative Writing14941372
EQ-Bench 413401064
LMArena Multi-Turn15041409
EQ-Bench Creative Writing1943—
WildBench—83.9%

Frequently asked questions

Is Claude Fable 5 better than Claude Haiku 4.5?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 39.5 on the Noometry Index. Claude Haiku 4.5 costs 10× 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 Claude Haiku 4.5?

Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or Claude Haiku 4.5 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 44.0 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5 does, with 1M tokens against 200K.

How many benchmarks do Claude Fable 5 and Claude Haiku 4.5 share?

36 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Claude Haiku 4.5 has 53.

Related comparisons

Go deeper