Claude Fable 5.1 vs Claude Opus 5
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 554.3
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 549.6
τ³-Banking · AA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows
Fable 5.141
Opus 538.6
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 · max53.8
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 534.3
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 · max28.6
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 51,434.9
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 582
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 · xhigh99.4
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 · xhigh98
EBR Bench EBR Bench: Agents learn to play Earthborne Rangers across repeated playthroughs
Fable 5.1 · max57.1
Opus 5 · max45.7
Furniture Assembly Furniture Assembly: Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step
Fable 5.1 · max70
Opus 5 · max60.8
τ³-bench · banking · 1.0.1 τ-bench official · 3-banking-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools
Fable 5.1—
Opus 5 · max48.7
ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer
Fable 5.1 · max49.5
Opus 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 568.9
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success
Fable 5.1—
Opus 5 · max47.5
FrontierCode 1.1 FrontierCode 1.1: Agents implement changes in real repositories, graded against maintainer-defined requirements
Fable 5.1 · max49
Opus 5—
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—
SpireClimb SpireClimb: Agents play Slay the Spire under the named game and difficulty setting
Fable 5.1 · max2
Opus 5—
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—
SpireClimb StS2 A10 SpireClimb StS2 A10: Agents play Slay the Spire under the named game and difficulty setting
Fable 5.1 · max4
Opus 5—
| Benchmark | Fable 5.1 | Opus 5 |
|---|---|---|
| AutomationBench-AA | 54.7 | 54.3 |
| GDPval-AA (work tasks) 2.1 | 52.3 | 49.6 |
| τ³-Banking · AA | 41 | 38.6 |
| AA Analyst Agent | 57.5 · max | 53.8 · max |
| Terminal-Bench 4.0 | 44.9 | 34.3 |
| Terminal-Bench Science 0.1 | 43.3 · max | 28.6 · max |
| AA-Briefcase 1.1 · Elo | 1,527.7 | 1,434.9 |
| AA-LCR (long context) 1.1 | 84.7 | 82 |
| SWE-bench Pro (v2 full) | 99.1 · high | 99.4 · xhigh |
| SWE-bench Pro (v2 hard) | 92.2 · high | 98 · xhigh |
| EBR Bench | 57.1 · max | 45.7 · max |
| Furniture Assembly | 70 · max | 60.8 · max |
| τ³-bench · banking · 1.0.1 | — | 48.7 · max |
| ITBench SRE | 49.5 · max | — |
| DeepSWE 1.1 | — | 68.9 |
| EnterpriseOps-Gym-AA | — | 47.5 · max |
| FrontierCode 1.1 | 49 · max | — |
| Harvey LAB-AA 1.1 | 6.4 · max | — |
| SpireClimb | 2 · max | — |
| SpireClimb StS1 A20 Heart | 0 · max | — |
| SpireClimb StS2 A10 | 4 · max | — |
Specs
| Spec | Fable 5.1 | Opus 5 |
|---|---|---|
| Input, per 1M | $10 | $5 |
| Output, per 1M | $50 | $25 |
| Cost per task? | $2.98 | $2.19 |
| Speed, tok/s | 56 | 55 |
| Context | 1M | 1M |
| Weights | Closed | Closed |
| Released | Sep 2026 | Jul 2026 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | Partial |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
Fable 5.1 → Opus 5
Nothing known.
Opus 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.