Skip to main content

Claude Fable 5.2 vs Claude Haiku 4.5

SpecClaude Fable 5.2Claude Haiku 4.5
Respan Index80.8 (#1)19.3 (#132)
Blended price per 1M$16$2
Context window-200K
Input / output per 1M$8 / $40$1 / $5
Max output-64K
Inputtexttext, vision
Released2026-11-092025-10-15

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryClaude Fable 5.2Claude Haiku 4.5
Coding73.0 Claude Fable 5.25.1 Claude Haiku 4.5
Agents85.3 Claude Fable 5.215.7 Claude Haiku 4.5
Reasoning90.2 Claude Fable 5.221.5 Claude Haiku 4.5
Knowledge & language94.0 Claude Fable 5.213.2 Claude Haiku 4.5
Human preference61.7 Claude Fable 5.249.1 Claude Haiku 4.5

How the Respan Index works

Benchmarks both report

Claude Fable 5.2 leads on 8 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude Fable 5.2Claude Haiku 4.5
LMArena WebDev (LMArena)18241330
LMArena Elo15031414
Vending-Bench 2 (Andon Labs)9628.48458.89
Chess Puzzles (Epoch AI)79%8%
GPQA Diamond93.9%71.2%
OTIS Mock AIME 2024-2025 (Epoch AI)99.7%66.7%
SimpleQA Verified94%13.2%
Humanity's Last Exam (with tools)74.2%18.7%

FAQ

Is Claude Fable 5.2 better than Claude Haiku 4.5?

Claude Fable 5.2 scores 80.8 on the Respan Index (#1), ahead of Claude Haiku 4.5 at 19.3 (#132). Claude Fable 5.2 leads on 8 of the 8 benchmarks both report.

Which is cheaper, Claude Fable 5.2 or Claude Haiku 4.5?

Claude Fable 5.2 lists at $8 input and $40 output per 1M tokens; Claude Haiku 4.5 at $1 and $5. Claude Haiku 4.5 is 8.0x cheaper per token at list price.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.