Noometry

Model comparison

Claude Fable 5.1 vs Claude Haiku 4.5

Claude Fable 5.1 is the stronger model overall, scoring 69.0 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 5.1's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Claude Fable 5.1 Anthropic

69.0

Rank #2 Confirmed

Claude Haiku 4.5 Anthropic

39.5

Rank #165 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Fable 5.1 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 5.1 leads 76.7 to 15.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 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 5.1.
  • Claude Fable 5.1 accepts more context: 1M tokens versus 200K.

Side by side

Claude Fable 5.1Claude Haiku 4.5
ProviderAnthropicAnthropic
Noometry Index69.039.5
Released2026-09-012025-10-15
WeightsProprietaryProprietary
Context window1M200K
Max output128K64K
Input $ / M tokens$10$1
Output $ / M tokens$50$5
Results tracked5253

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

Category by category

Coding Claude Fable 5.1 leads

Claude Fable 5.1: 74.7 (#1), Claude Haiku 4.5: 44.0 (#78)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
LMArena WebDev17441330
SciCode63.1%43.3%
WeirdML92.9%45.4%
LMArena Coding15281453
ALE-Bench2,143653.48
FrontierCode50.9%—
SWE-bench Verified (bash only)—66.6%
CursorBench51.8%—
SWE-bench Multilingual—64.7%
FrontierSWE56.3%—
GSO88.2%—
MirrorCode73.3%—

Agentic & Tool Use Claude Fable 5.1 leads

Claude Fable 5.1: 50.7 (#5), Claude Haiku 4.5: 33.6 (#52)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
Vending-Bench 25,422458.89
Terminal-Bench—35.5%
APEX-Agents68.6%—
Berkeley Function Calling Leaderboard—68.7%
Remote Labor Index17.9%—
DeepResearch Bench—45.5%
BALROG—31.2%
ExploitBench—13.7%
GDP.pdf29.6%—

Reasoning Claude Fable 5.1 leads

Claude Fable 5.1: 76.7 (#7), Claude Haiku 4.5: 15.1 (#320)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
ARC-AGI-290%4%
NYT Connections (extended)90%14.3%
ARC-AGI-197.5%47.7%
CritPt31.1%0%
Chess Puzzles47%8%
LMArena Hard Prompts15261420
DTBench97.6%73.6%
LMCA65.5%30.9%
Epoch Capabilities Index164.7142.41
EBR-Bench57.1%—
Mystery Game Puzzles58%—
ForecastBench—61.4

Math Claude Fable 5.1 leads

Claude Fable 5.1: 89.6 (#4), Claude Haiku 4.5: 44.9 (#78)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
OTIS Mock AIME 2024-2025100%66.7%
LMArena Math15251396
FrontierMath (Tiers 1-3)90.2%—
FrontierMath Tier 487.8%—
ProofBench100%—
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 5.1 leads

Claude Fable 5.1: 69.6 (#6), Claude Haiku 4.5: 37.7 (#153)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
SimpleQA Verified70.8%13.2%
LMArena Expert15351442
GPQA Diamond—71.2%
Humanity's Last Exam46.5%—
MMLU-Pro—77.7%
Vectara Hallucination Rate—9.8%
GPQA (HELM)—60.5%

Multimodal Claude Fable 5.1 leads

Claude Fable 5.1: 53.9 (#4), Claude Haiku 4.5: 26.8 (#118)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
Blueprint-Bench 241.9%0%
LMArena Document15131420
LMArena Vision1318—
Furniture Assembly70%—

Multilingual Claude Fable 5.1 leads

Claude Fable 5.1: 59.1 (#3), Claude Haiku 4.5: 49.9 (#129)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
LMArena Non-English15071377
LMArena Chinese15861417
LMArena French15251408
LMArena German15001375
LMArena Japanese15431339
LMArena Korean15341347
LMArena Russian15211381
LMArena Spanish15161420

Instruction Following Claude Fable 5.1 leads

Claude Fable 5.1: 79.2 (#6), Claude Haiku 4.5: 71.4 (#149)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
LMArena Instruction Following15171414
IFEval—80.1%

Long Context Claude Fable 5.1 leads

Claude Fable 5.1: 46.7 (#20), Claude Haiku 4.5: 43.6 (#92)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
LMArena Longer Query15221427

Writing & Preference Claude Fable 5.1 leads

Claude Fable 5.1: 79.2 (#2), Claude Haiku 4.5: 57.9 (#123)

BenchmarkClaude Fable 5.1Claude Haiku 4.5
LMArena Text15101396
LMArena Creative Writing15071372
LMArena Multi-Turn14921409
EQ-Bench Creative Writing2162—
WildBench—83.9%
EQ-Bench 4—1064

Frequently asked questions

Is Claude Fable 5.1 better than Claude Haiku 4.5?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 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 5.1's lead doesn't matter for your workload.

Which is cheaper, Claude Fable 5.1 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 5.1 lists at $10 and $50.

Is Claude Fable 5.1 or Claude Haiku 4.5 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 44.0 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 200K.

How many benchmarks do Claude Fable 5.1 and Claude Haiku 4.5 share?

34 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Claude Haiku 4.5 has 53.

Related comparisons

Go deeper