Claude Fable 5.1 vs Claude Opus 5.5

$2.98 / task

Wins 4 of 19 benchmarks

$1.34 / task

Wins 9 of 19 benchmarks

Only shared

AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation

Fable 5.154.7

Opus 5.561.2

GDPval-AA (work tasks) 2.1 GDPval-AA (work tasks) 2.1: Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work

Fable 5.152.3

Opus 5.554.2

AA Analyst Agent AA Analyst Agent: Data-analyst tasks: the model explores data with tools and reports findings

Fable 5.1 · max57.5

Opus 5.5 · max56.3

ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer

Fable 5.1 · max49.5

Opus 5.5 · max38.2

Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite

Fable 5.144.9

Opus 5.552.5

Terminal-Bench Science 0.1 Terminal-Bench Science 0.1: Agents complete expert-authored research workflows across five scientific domains in a terminal

Fable 5.1 · max43.3

Opus 5.543.3

AA-Briefcase 1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating

Fable 5.11,527.7

Opus 5.51,625.1

AA-LCR (long context) 1.1 AA-LCR (long context) 1.1: Questions that need reading and connecting facts across very long documents (around 100K tokens)

Fable 5.184.7

Opus 5.584.3

FrontierCode 1.1 FrontierCode 1.1: Agents implement changes in real repositories, graded against maintainer-defined requirements

Fable 5.1 · max49

Opus 5.557.1

Harvey LAB-AA 1.1 Harvey LAB-AA 1.1: Legal agents work from case documents; every rubric criterion must pass and material hallucinations receive no credit

Fable 5.1 · max6.4

Opus 5.5 · max4.2

EBR Bench EBR Bench: Agents learn to play Earthborne Rangers across repeated playthroughs

Fable 5.1 · max57.1

Opus 5.5 · max71.4

Furniture Assembly Furniture Assembly: Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step

Fable 5.1 · max70

Opus 5.5 · max83.3

SpireClimb SpireClimb: Agents play Slay the Spire under the named game and difficulty setting

Fable 5.1 · max2

Opus 5.5 · max3.3

SpireClimb StS1 A20 Heart SpireClimb StS1 A20 Heart: Agents play Slay the Spire under the named game and difficulty setting

Fable 5.1 · max0

Opus 5.5 · max0

SpireClimb StS2 A10 SpireClimb StS2 A10: Agents play Slay the Spire under the named game and difficulty setting

Fable 5.1 · max4

Opus 5.5 · max6.7

τ³-Banking · AA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows

Fable 5.141

Opus 5.5—

DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition

Fable 5.1—

Opus 5.5 · max72.3

SWE-bench Pro (v2 full) SWE-bench Pro (v2 full): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate

Fable 5.1 · high99.1

Opus 5.5—

SWE-bench Pro (v2 hard) SWE-bench Pro (v2 hard): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate

Fable 5.1 · high92.2

Opus 5.5—

Benchmark	Fable 5.1	Opus 5.5
AutomationBench-AA	54.7	61.2
GDPval-AA (work tasks) 2.1	52.3	54.2
AA Analyst Agent	57.5 · max	56.3 · max
ITBench SRE	49.5 · max	38.2 · max
Terminal-Bench 4.0	44.9	52.5
Terminal-Bench Science 0.1	43.3 · max	43.3
AA-Briefcase 1.1 · Elo	1,527.7	1,625.1
AA-LCR (long context) 1.1	84.7	84.3
FrontierCode 1.1	49 · max	57.1
Harvey LAB-AA 1.1	6.4 · max	4.2 · max
EBR Bench	57.1 · max	71.4 · max
Furniture Assembly	70 · max	83.3 · max
SpireClimb	2 · max	3.3 · max
SpireClimb StS1 A20 Heart	0 · max	0 · max
SpireClimb StS2 A10	4 · max	6.7 · max
τ³-Banking · AA	41	—
DeepSWE 1.1	—	72.3 · max
SWE-bench Pro (v2 full)	99.1 · high	—
SWE-bench Pro (v2 hard)	92.2 · high	—

Specs

Spec	Fable 5.1	Opus 5.5
Input, per 1M	$10	$4
Output, per 1M	$50	$20
Cost per task?	$2.98	$1.34
Speed, tok/s	56	81
Context	1M	1M
Weights	Closed	Closed
Released	Sep 2026	Sep 2026
See images	✓	✓
Read PDFs	Partial	✓
Hear audio	—	—
Watch video	—	—
Call tools	✓	✓
Force a tool call	Partial	—
Return strict JSON	✓	✓
Search the web	?	✓
Run code	?	✓
Use a computer	?	✓

What breaks when you switch

Fable 5.1 → Opus 5.5

No forced tool use›

Forced tool_choice any or tool returns HTTP 400; remove the forced choice.

Thinking is always on›

Disabled thinking or a manual budget returns HTTP 400; omit thinking or use adaptive thinking.

Remove sampling parameters›

Non-default temperature, top_p or top_k returns HTTP 400; omit these parameters and use prompting.

No assistant prefill›

Assistant prefill returns HTTP 400; use structured outputs or system instructions, with system instructions on Bedrock.

Old computer tool rejected · Claude API / Google Cloud›

The computer_20251124 tool returns HTTP 400 on the Claude API and Google Cloud; use computer_toolset_20260801 there.

Return thinking blocks unmodified›

Edited, reordered or partially dropped thinking blocks return HTTP 400; echo assistant messages complete and unmodified with tool results.

Opus 5.5 → Fable 5.1

Replace forced tool_choice›

Forced tool_choice returns HTTP 400; use auto with an explicit instruction and strict tools, or JSON outputs.

Adaptive thinking is always on›

Disabled thinking or manual budget_tokens returns HTTP 400; omit thinking or use adaptive thinking.

No non-default sampling values›

Non-default temperature, top_p or top_k returns HTTP 400; omit non-default sampling values.

Requires 30-day data retention · Claude API›

A Claude API organization or workspace without 30-day retention receives HTTP 400; configure workspace retention or contact the Anthropic account team.

Thinking blocks bind to conversations›

Where conversation binding is enforced, replaying an invalidated block returns HTTP 400; use the documented drop_block control to continue without it.

No assistant prefill›

Assistant prefill returns HTTP 400; use system prompt instructions instead.