---
title: "Claude Fable 5 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Claude Fable 5."
source: "https://rankedagi.com/models/claude-fable-5"
---

# Claude Fable 5

| Field | Value |
| --- | --- |
| Organization | Anthropic |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2026-06-09 |
| Context window | 1M |
| Input cost per million tokens | $10 |
| Output cost per million tokens | $50 |
| Cached input cost per million tokens | $1 |
| Model ID | claude-fable-5 |
| Last updated | 2026-06-09T21:05:44.349Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 94.6% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 80.3% | Diverse Agentic Coding |  |
| Terminal-Bench 2.1 | coding | 88.0% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.1 |
| RankedAGI Agentic | Agents | 94.9% | RankedAGI Agentic Score |  |
| OSWorld-Verified | Agents | 85.0% |  |  |
| RankedAGI Reasoning | reasoning | 88.0% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 59.0% | Multidisciplinary Reasoning (no tools) |  |
| Humanity's Last Exam w/ Tools | reasoning | 64.5% | Multidisciplinary Reasoning (with tools) |  |
| RankedAGI Math | math | 68.9% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 78.5% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 1932 | Office Tasks (Artificial Analysis) |  |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://www.anthropic.com/news/claude-fable-5-mythos-5 |
| X | https://x.com/claudeai/status/2064394146916229443 |