OnlySOTA

Claude Fable 5.2 vs Claude Opus 5.5

Both are currently SOTA. Each row is one board’s result, and the marked figure is the one that board ranks higher.

Board Claude Fable 5.2 Claude Opus 5.5
Artificial Analysis LLM Leaderboard Artificial Analysis Intelligence Index 64.6 No. 1 of 57 59.1 No. 3 of 57
Arena — Agent Overall 0.286 No. 1 of 65 0.182 No. 2 of 65
Artificial Analysis Coding Agents Artificial Analysis Coding Agent Index 0.585 No. 1 of 24 0.582 No. 3 of 24
Epoch AI Benchmarking Hub FrontierMath Tiers 1–3 95.1% No. 1 of 88 91.2% No. 4 of 88
HarnessTax — SWE-bench Lite SWE-bench Lite — 93.3% No. 2 of 8
HarnessTax — Terminal-Bench 2.0 Terminal-Bench 2.0 — 85.6% No. 1 of 8
Terminal-Bench 4.0 Terminal-Bench 4.0 — 65.8% No. 1 of 59
Arena — Code Overall 1826 No. 1 of 157 1816 No. 2 of 157
Arena — Text Overall (style control) — 1507 No. 4 of 421
Arena — Vision Overall (style control) — 1295 No. 6 of 167

At a glance

Developer Anthropic Anthropic
Weights closed closed
Released ——
Price Blended Price, USD per 1M tokens (3:1 input:output) $16.00$8.00
Value: where it sits on the kill line SOTA SOTA