Sign Up

Decision support

Claude Fable 5.2 vs GPT-6 Astra

Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.

ModelsHardware
Claude Fable 5.2

Anthropic

Sources:models.devOpenRouter

GPT-6 Astra

OpenAI

Sources:models.devOpenRouter

Benchmark results

Head to head on 8 benchmarks both models report

  • Claude Fable 5.25leads
  • GPT-6 Astra3leads

  • DeepSWE 1.1

    Best pass@1 · Higher is better

    • Claude Fable 5.2
      Not reported
    • GPT-6 Astra
      74.1%
      #1 of 28
    Runs and sources
    Claude Fable 5.2

    Not reported

    GPT-6 Astra
    • low67.0%mini-swe-agent · pass@4 79.6% · $1.60 / attempt
    • medium72.8%mini-swe-agent · pass@4 82.3% · $3.08 / attempt
    • high73.2%mini-swe-agent · pass@4 82.3% · $3.92 / attempt
    • xhigh74.1%mini-swe-agent · pass@4 80.5% · $4.43 / attempt
    • max73.2%mini-swe-agent · pass@4 79.6% · $7.50 / attempt
    Source:DeepSWE leaderboard, 2026-09-22Official source JSON

  • Arena Text

    Arena rating · Higher is better

    • Claude Fable 5.2
      Not reported
    • GPT-6 Astra
      1474
      Arena #41CI 1469 to 1480
    Runs and sources
    Claude Fable 5.2

    Not reported

    GPT-6 Astra
    • max147495% CI 1469 to 1480 · 18,315 votes
    Source:Arena Text leaderboard, 2026-11-09

  • Arena WebDev

    Arena rating · Higher is better

    • Claude Fable 5.2
      Best1836
      +71 ahead · Arena #1CI 1813 to 1858
    • GPT-6 Astra
      1764
      Arena #5CI 1756 to 1773
    Runs and sources
    Claude Fable 5.2
    • xhigh183695% CI 1813 to 1858 · 994 votes
    GPT-6 Astra
    • max176495% CI 1756 to 1773 · 8,425 votes
    Source:Arena WebDev leaderboard, 2026-11-10

  • Arena Vision

    Arena rating · Higher is better

    • Claude Fable 5.2
      Not reported
    • GPT-6 Astra
      1283
      Arena #21CI 1274 to 1293
    Runs and sources
    Claude Fable 5.2

    Not reported

    GPT-6 Astra
    • max128395% CI 1274 to 1293 · 5,517 votes
    Source:Arena Vision leaderboard, 2026-11-09

  • Arena Search

    Arena rating · Higher is better

    • Claude Fable 5.2
      Not reported
    • GPT-6 Astra
      1245
      Arena #3CI 1237 to 1253
    Runs and sources
    Claude Fable 5.2

    Not reported

    GPT-6 Astra
    • max124595% CI 1237 to 1253 · 17,456 votes
    Source:Arena Search leaderboard, 2026-11-09

  • Arena Document

    Arena rating · Higher is better

    • Claude Fable 5.2
      Not reported
    • GPT-6 Astra
      1474
      Arena #17CI 1465 to 1483
    Runs and sources
    Claude Fable 5.2

    Not reported

    GPT-6 Astra
    • max147495% CI 1465 to 1483 · 5,723 votes
    Source:Arena Document leaderboard, 2026-11-09

  • Agent Arena

    IPS score · Higher is better

    • Claude Fable 5.2
      Best+0.304
      +0.158 ahead · Arena #1CI +0.264 to +0.343
    • GPT-6 Astra
      +0.145
      Arena #6CI +0.125 to +0.166
    Runs and sources
    Claude Fable 5.2
    • max+0.30495% CI +0.264 to +0.343 · 577,927 observations
    GPT-6 Astra
    • max+0.14595% CI +0.125 to +0.166 · 1,353,961 observations
    Source:Agent Arena leaderboard, 2026-11-11

  • ARC-AGI-2

    Best published score · Higher is better

    • Claude Fable 5.2
      93.8%
      #4 of 85
    • GPT-6 Astra
      Best95.0%
      +1.3 pts ahead · #1 of 85
    Runs, sources and effort chart
    Claude Fable 5.2
    • low86.7%
    • medium89.6%
    • high90.4%
    • xhigh93.8%
    • max92.5%
    GPT-6 Astra
    • none59.6%
    • low85.4%
    • medium92.1%
    • high92.1%
    • xhigh93.3%
    • max95.0%
    Source:External evaluation via Epoch AIOriginal-source terms apply

  • FrontierMath-Tier-4-v2-Private

    Best published score · Higher is better

    • Claude Fable 5.2
      Best100.0%
      +2.4 pts ahead · #1 of 72
    • GPT-6 Astra
      97.6%
      #3 of 72
    Runs and sources
    Claude Fable 5.2
    • max100.0%
    GPT-6 Astra
    • none82.9%
    • low87.8%
    • medium97.6%
    • high97.6%
    • xhigh97.6%
    • max97.6%
    Source:Epoch AI evaluation

  • FrontierMath-Tiers-1-3-v2-Private

    Best published score · Higher is better

    • Claude Fable 5.2
      Best95.1%
      +1.4 pts ahead · #1 of 87
    • GPT-6 Astra
      93.7%
      #2 of 87
    Runs and sources
    Claude Fable 5.2
    • max95.1%
    GPT-6 Astra
    • max93.7%
    Source:Epoch AI evaluation

  • GPQA diamond

    Best published score · Higher is better

    • Claude Fable 5.2
      93.9%
      #14 of 161
    • GPT-6 Astra
      Best95.8%
      +1.9 pts ahead · #3 of 161
    Runs and sources
    Claude Fable 5.2
    • max93.9%
    GPT-6 Astra
    • max95.8%
    Source:Epoch AI evaluation

  • Humanity's Last Exam

    Best published score · Higher is better

    • Claude Fable 5.2
      Not reported
    • GPT-6 Astra
      54.8%
      #1 of 34
    Runs and sources
    Claude Fable 5.2

    Not reported

    GPT-6 Astra
    • unknown54.8%
    Source:External evaluation via Epoch AIOriginal-source terms apply

  • OTIS Mock AIME 2024-2025

    Best published score · Higher is better

    • Claude Fable 5.2
      99.7%
      #13 of 158
    • GPT-6 Astra
      Best100.0%
      +0.3 pts ahead · #1 of 158
    Runs and sources
    Claude Fable 5.2
    • max99.7%
    GPT-6 Astra
    • max100.0%
    Source:Epoch AI evaluation

  • SimpleQA Verified

    Best published score · Higher is better

    • Claude Fable 5.2
      Best94.0%
      +18.4 pts ahead · #1 of 87
    • GPT-6 Astra
      75.6%
      #4 of 87
    Runs and sources
    Claude Fable 5.2
    • max94.0%
    GPT-6 Astra
    • max75.6%
    Source:Epoch AI evaluation

Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.

Original-source terms apply to evaluations credited to their original publishers.

DeepSWE 1.1 results: official leaderboard, data generated 2026-09-22. Only exact model versions in the official dataset are matched.

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

Model specifications

Release date
November 7, 2026
September 4, 2026
Context window
1M
1.1M
Native context
—
—
Max output tokens
128,000
128,000
Knowledge cutoff
2026-06
2026-04-30
Open weights
Closed
Closed
Parameter count
—
—

API pricing · USD per 1M tokens

Input
$8.00
$10.00
Output
$40.00
$50.00
Cached input
$0.20
$1.00
Cache write
$10.00
$12.50

Capabilities and modalities

Input modalities
text, image, file
file, image, text
Output modalities
text
text
Tool calling
Supported
Supported
Reasoning option
Supported
Supported
Supported options
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, tool_choice, tools, verbosity
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools, verbosity
Capabilities
—
—

Architecture and availability

Architecture
—
—
Model families
—
—
Tokenizer
Claude
GPT
Instruction format
—
—
License
—
—
Providers
4
3
Provider endpoints
10
16
Ollama variants
0
0
Metadata source
ai-research
ai-research

A dash means the field is not reported. Provider-specific performance and pricing may differ.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.