CrossModel
Back to model catalog

Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

Claude Fable 5Claude Opus 5Claude Sonnet 5Chat with these 3
AttributeClaude Fable 5anthropic/claude-fable-5Claude Opus 5anthropic/claude-opus-5Claude Sonnet 5anthropic/claude-sonnet-5
Specs
Context window1M1M1M
Max output128K128K128K
Input modalitiesTextImageTextImageTextImage
Output modalitiesTextTextText
Capabilities
StreamingSupportedSupportedSupported
Tool callingSupportedSupportedSupported
Structured output (JSON)SupportedSupportedSupported
Image inputSupportedSupportedSupported
Thinking modeSupportedSupportedSupported
Price / 1M tokens
Input$ 10.00$ 5.00$ 2.00
Output$ 50.00$ 25.00$ 10.00
Cache read$ 1.00$ 0.50$ 0.20
Cache write$ 12.50$ 6.25$ 2.50
What it is good at
Best for
  • Agentic coding
  • Professional knowledge work
  • Agentic coding
  • Professional knowledge work
  • Scientific research
  • Agentic coding
  • High-volume agent workloads
Published benchmarks
Frontier-Bench v0.1score
  • 33.7%(setup not fully disclosed)
  • 43.3%(setup not fully disclosed)
—
FrontierCode v1.1 (Main)score—
  • 53.4%(setup not fully disclosed)
—
Terminal-Bench 2.1pass_rate——
  • 80.4%(setup not fully disclosed)
BrowseComp (with tools)accuracy
  • 87.4%(setup not fully disclosed)
  • 90.8%(setup not fully disclosed)
—
AutomationBenchscore
  • 17.4%(setup not fully disclosed)
  • 26%(setup not fully disclosed)
—
SWE-Bench Proresolved_rate
  • 80.3%(setup not fully disclosed)
—
  • 63.2%(setup not fully disclosed)
OSWorld 2.0success_rate
  • 66.1%(setup not fully disclosed)
  • 70.6%(setup not fully disclosed)
—
OSWorld-Verifiedsuccess_rate
  • 85%(setup not fully disclosed)
—
  • 81.2%(setup not fully disclosed)
GDPval-AAelo
  • 1932(setup not fully disclosed)
——
GDPval-AA v2elo—
  • 1861(setup not fully disclosed)
  • 1618(setup not fully disclosed)
ARC-AGI-3score—
  • 30.2%(setup not fully disclosed)
—
Humanity's Last Examaccuracy
  • 56.5%(setup not fully disclosed)
  • 56.3%(setup not fully disclosed)
  • 43.2%(setup not fully disclosed)
Humanity's Last Exam (with tools)accuracy
  • 63.9%(setup not fully disclosed)
  • 64.7%(setup not fully disclosed)
  • 57.4%(setup not fully disclosed)
Blueprint-Bench 2score
  • 38.6%(setup not fully disclosed)
——