Compare models

Up to 4 models side by side. The best value in each row is highlighted; a dash means no published result. Showing the top three by Intelligence Index until you pick your own.

  • Claude Fable 5.2
  • Gemini 4 Carbon
  • Claude Opus 5.5
MeasureClaude Fable 5.2AnthropicReleased 2026-11-09Artificial AnalysisGemini 4 CarbonGoogle DeepMindReleased 2026-10-28Artificial AnalysisClaude Opus 5.5AnthropicReleased 2026-09-22Artificial Analysis
Cost, speed and limits
Intelligence Index64.660.059.1
Cost to run the Index$26.54$5.48$10.04
Time per task44.5 min33.8 min25.4 min
Output speed102 tok/s61 tok/s114 tok/s
Time to first answer token262.1 s72.1 s404.5 s
Input price (per 1M tokens)$8.00$2.00$4.00
Output price (per 1M tokens)$40.00$10.00$20.00
Context window1M1M1M
Reasoning & knowledge
AA-Omniscience Accuracy79.1%58.3%65.5%
CritPt35.4%—31.7%
CritPt v2 (Hard)76.5%69.0%68.0%
HLE-Diamond80.2%69.1%67.9%
Humanity's Last Exam74.3%—61.4%
Coding & terminal agents
FrontierCode 1.156.2%—52.2%
FrontierCode-AA 2.048.8%40.6%46.4%
SciCode67.7%—66.9%
Terminal-Bench 4.059.6%65.1%59.6%
Terminal-Bench-Science 0.173.3%64.8%59.1%
Agentic work
AA-AnalystAgent——56.3%
AA-Briefcase v1.1 (Elo)1785 Elo1611 Elo1801 Elo
AutomationBench-AA76.4%77.8%69.5%
GDPval-AA (normalized Elo)1831 Elo1733 Elo1866 Elo
Harvey LAB-AA7.2%—4.2%
ITBench-AA——38.2%
Multimodal Knowledge Agent (MKA)56.6%54.3%53.0%
Long context & documents
AA-LCR (long-context reasoning)83.3%79.3%84.7%
GDP.pdf24.2%28.4%26.2%
MLCR-AA (medical long context)43.9%19.4%27.8%
Multimodal & science
AA-3D (Elo)1271 Elo—1202 Elo
Code2Video-AA (Elo)——1536 Elo
MMMU-Pro——87.7%
VIALS-AA67.1%64.0%61.5%
Health & safety
AA-Omniscience Non-Hallucination40.7%88.6%49.7%
HealthBench59.6%—57.0%
HealthBench Professional67.7%—59.9%

Indices, evaluations, speed and latency: Artificial Analysis. Prices and context: Artificial Analysis, then OpenRouter. Release dates: see the badge on each model. How we source everything: methodology.