Roboflow

Claude Fable 5 vs Claude Fable 5.2

Claude Fable 5.2 and Claude Fable 5 score 86.5% vs 71.7% averaged across five Vision Evals tasks (#7 and #28 of 73 models), so Claude Fable 5.2 leads overall.

  • Claude Fable 5.2 wins 4 of the 5 tasks, with its widest lead on object detection (81.6% vs 56.4%).
  • Claude Fable 5.2 is cheaper: $0.031 vs $0.039 overall average cost per sample.

Compare Claude Fable 5 vs Claude Fable 5.2 live

Run the same image across every model that supports a task and compare their outputs side-by-side.

Detect and compare bounding boxes across models on the same image.

Open Object Detection in the full playground
AnthropicClaude Fable 5
Run to compare this model.
AnthropicClaude Fable 5.2
Run to compare this model.

Claude Fable 5 vs Claude Fable 5.2 on Vision Evals

Score by taskClaude Fable 5Claude Fable 5.2
Object Detection
56.4
81.6
Counting
63.5
86.5
Reasoning
66.2
88.1
OCR
72.3
79.5
Identification
100.0
96.9

Roboflow Vision Evals. Full breakdown below.

Claude Fable 5 vs Claude Fable 5.2 Comparison Table

Evals updated November 19, 2026Pricing updated November 21, 2026

PropertyClaude Fable 5Claude Fable 5.2
OrganizationAnthropicAnthropic
Categoryclosedclosed
Modalitymultimodalmultimodal
Release DateJun 2026Nov 2026
Context Window1.0M1.0M
ParametersUnknownUnknown
LicenseProprietaryProprietary
Commercial usecommercial use per vendor termscommercial use per vendor terms
Pricing per 1M tokens
Input $/1M$10.00$8.00
Output $/1M$50.00$40.00
Vision Tasks
Both support 10 more tasks
Model Features
Both support 3 more features
Vision Evalsground-truth scores across 5 vision tasks, pooled at low effort
Overall
71.7%
86.5%
Avg cost / sample$0.039$0.031
Avg speed / sample9.54s9.33s
By task
Object Detection (low)
56.4%
$0.059
81.6%
±0.3, Mean of 3 runs, range 81.2 to 81.9
$0.048
Object Detection (high)–
83.3%
±0.5, Mean of 3 runs, range 82.8 to 83.7
$0.055
Counting (low)
63.5%
$0.017
86.5%
±0.0, Mean of 3 runs, range 86.5 to 86.5
$0.015
Counting (high)–
92.8%
±1.4, Mean of 3 runs, range 91.9 to 94.6
$0.021
Identification (low)
100.0%
$0.014
96.9%
±0.0, Mean of 3 runs, range 96.9 to 96.9
$0.011
Identification (high)–
94.8%
±1.6, Mean of 3 runs, range 93.8 to 96.9
$0.012
OCR (low)
72.3%
$0.041
79.5%
$0.030
by category
Single value
70.9%
Transcription
90.2%
Structured JSON
85.7%
Text localization
31.6%
Single value
64.8%
Transcription
94.7%
Structured JSON
92.8%
Text localization
74.5%
OCR (high)
74.2%
$0.075
84.8%
$0.043
by category
Single value
72.2%
Transcription
87.7%
Structured JSON
89.2%
Text localization
33.3%
Single value
77.4%
Transcription
97.9%
Structured JSON
94.1%
Text localization
72.9%
Reasoning (low)
66.2%
$0.018
88.1%
±1.3, Mean of 3 runs, range 86.8 to 89.4
$0.016
Reasoning (high)
66.2%
$0.024
92.0%
±1.0, Mean of 3 runs, range 91.4 to 93.4
$0.024

Claude Fable 5 vs Claude Fable 5.2: Overview

Claude Fable 5

Claude Fable 5 is Anthropic's first generally available Mythos-class large language model, released on June 9, 2026. It is built for long-horizon, asynchronous, and agentic tasks that prior Claude generations could not sustain, including multi-day autonomous coding sessions, complex knowledge work, and document-heavy analysis. The model supports a 1 million token context window with up to 128,000 output tokens per request and uses adaptive thinking as its sole reasoning mode, where the effort level is adjustable but raw chain-of-thought is never returned. Vision capabilities allow the model to parse diagrams, charts, and tables embedded in files and PDFs, and to use visual feedback to evaluate its own coding outputs against design goals.

Claude Fable 5 shares the same underlying model weights as Claude Mythos 5, but is deployed with safety classifiers that automatically reroute queries in high-risk domains — including cybersecurity, biology, and chemistry — to Claude Opus 4.8. These classifiers trigger in fewer than 5% of sessions on average. As a designated Covered Model, all traffic is subject to mandatory 30-day data retention to support safety monitoring. The model is available via the Claude API, Amazon Bedrock, Vertex AI, and Microsoft Foundry. Anthropic has not publicly disclosed parameter count, architecture details, or training data composition for this model.

Claude Fable 5.2

Claude Fable 5.2 is a proprietary multimodal model from Anthropic, released on November 9, 2026. It accepts text and images and produces text, with a one million token context window and up to 128,000 output tokens. Adaptive thinking is always enabled, with an effort setting that controls reasoning. Anthropic positions Fable for demanding reasoning and long-running technical work, including coding and analysis of visual inputs.

Fable 5.2 succeeds Fable 5.1. Anthropic reports improvements in coding, reasoning, and vision, with output generation up to 30% faster than its predecessor. Fable and Mythos 5.2 share an underlying model, with additional cybersecurity and biology safeguards applied to Fable. Model weights are not publicly released.