Skip to content

Anthropic Proprietary Released Sep 1, 2026 Updated

Claude Fable 5.1

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #11 / 416

    617 / 1,000

    ToolsGuide Score· votes only

  • Vision #23 / 167

    557 / 1,000

    ToolsGuide Score· votes only

  • Coding #5 / 147

    599 / 1,000

    ToolsGuide Score· votes only

  • Agents #6 / 53

    577 / 1,000

    ToolsGuide Score· votes 583, tests 570

  • Price per 1M tokens

    In $10.00· Out $50.00

    $10.00

    Input · median text model $0.43

Summary

Claude Fable 5.1 is Anthropic's model, released Sep 1, 2026. It's ranked in 4 categories and does best at text: #11 of 416, with a ToolsGuide Score of 617 against a median of 235.

It also ranks #5 of 147 for coding (599), #6 of 53 for agents (577), #23 of 167 for vision (557).

Its text and vision and coding score uses votes only, because it has published fewer than two of the tests used for those categories.

It costs $10.00 per million input tokens and $50.00 per million output tokens, about 23× the median text model ($0.43).

It has published results on 7 tests and has the top score on 3 of them, including Humanity's Last Exam and GDPval-AA.

Specifications

Creator
Anthropic
Licence
Proprietary
Released
Sep 1, 2026
Context window
1M tokens
Input price
$10.00 / 1M
Output price
$50.00 / 1M
Tests reported
7
Settings ranked
Claude Fable 5.1 (Max)

Model comparison

Against the ten best text models.

Text score

ToolsGuide Score out of 1,000 · Higher is better

Coding score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where Claude Fable 5.1 sits among the top 20 in each category.

Text

#11 of 416 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full text leaderboard →

Vision

#23 of 167 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full vision leaderboard →

Coding

#5 of 147 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full coding leaderboard →

Agents

#6 of 53 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full agents leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Score against price

Text · the 10 priced models ranked closest · up and to the left is better value

Against its nearest rivals

Text prompts by kind · ToolsGuide Score from votes · hover for values

Text

Claude Fable 5.1 (Max) · hover a bar for its rank

Vision

Claude Fable 5.1 (Max) · hover a bar for its rank

Coding

Claude Fable 5.1 (Max) · hover a bar for its rank

Test results

Every test Claude Fable 5.1 has a published result on, out of 100%, with its rank among the models that took it.

  • Humanity's Last Exam

    #1 / 108

    Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

    65.0%

    Self-reported · In the text score· In the vision score

  • Terminal-Bench 4.0

    #7 / 28

    Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems. Relative to earlier Terminal-Bench releases, 4.0 increases timeouts and adaptively raises RAM/CPU on selected tasks to reduce harness and resource confounds.

    55.8%

    Self-reported · In the coding score· In the agents score

  • AutomationBench

    #13 / 24

    AutomationBench is a tool-use benchmark that evaluates AI agents on automating real-world workflows, testing their ability to orchestrate tools and complete multi-step automation tasks.

    31.4%

    Self-reported · In the agents score

  • OSWorld 2.0

    #2 / 17

    OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks. Each task is an end-to-end workflow that takes human users a median of about 1.6 hours, scored with a binary-completion metric, and targets challenges such as dynamic environments, cross-source reasoning, and implicit-state inference.

    77.9%

    Self-reported

  • GDPval-AA

    #1 / 14

    GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.

    61.8%

    Self-reported

  • Terminal-Bench-Science 0.1

    #6 / 7

    Terminal-Bench-Science 0.1 is a Stanford-led community benchmark of 70 tasks drawn from scientific research workflows across the life, physical, earth, mathematical, and engineering sciences. Tasks are authored and reviewed by scientists and researchers; scores are typically reported as accuracy with relatively large standard error due to strongly bimodal per-task outcomes.

    52.6%

    Self-reported

  • CursorBench v3.2

    #1 / 2

    CursorBench v3.2 evaluates coding agents on interactive software engineering tasks in the Cursor environment.

    73.4%

    Unverified