Claude Fable 5.2 vs Gemini 4 Argon

Compare up to 4 models side by side.


Capability
Capability	—	166
Human preference	—	1529
Priceper 1M tokens
Input	$8.80–$9.68↑ ×4.9	$1.80list $2.00-10%↓
Output	$44.00–$48.40↑ ×4.9	$9.00list $10.00-10%↓
Cache read	$0.22–$0.242↑ ×2.4	$0.09list $0.10-10%↓
Reasoning output	—	$9.00list $10.00-10%
Web searchper request	$0.011↓	$0.0126list $0.014-10%↑ ×1.1
Limits and modalities
Context	1M↓ 5%	1M↑
Max output	128K↑	66K↓ 49%
Modalities	InputTextImagePDFOutputText	InputTextImageAudioVideoPDFOutputText
Availability
Providers	Anthropic, Amazon Bedrock, Anthropic (AWS)	Google (Gemini), Google Vertex AI
30-day uptime	—	—
Measured, last 30 days
Avg latency	—	—
Effective price	—	—
Cache hit rate	—	—
About
Released	2026-11-09	2026-10-13
Knowledge cutoff	2026-06	2026-03

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-07), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-10-28): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text