Claude Fable 5.2 tops Artificial Analysis with score of 65
The gist
Anthropic released Claude Fable 5.2, which scored 65 on Artificial Analysis's Intelligence Index, 5 points ahead of Gemini 4 Carbon.
The top spot comes days before Anthropic's Nasdaq IPO, but most benchmarks are Anthropic's own.
How it unfolded
- Nov 9, 2026Anthropic releases Claude Fable 5.2 and Claude Mythos 5.2; Fable 5.2 takes the #1 spot on the Artificial Analysis Intelligence Index v5 at 65, 5 points ahead of Gemini 4 Carbon (high, 60) and 6 ahead of Claude Opus 5.5 (max, 59).
- Nov 9, 2026Fable 5.2 sets new bests on HLE-Diamond (80%, previous best 69%), AA-Omniscience v1.1 (67, previous best 54), Terminal-Bench-Science (73%, previous best 65%), CritPt v2 hard subset (77%, previous best 72%) and FrontierCode 2.0 (49%, previous best 46%).
- Nov 9, 2026At high and xhigh effort Fable 5.2 scores 62, ahead of every other model at any effort, using 98k output tokens per task against 173k for Opus 5.5 (max).
Key terms
- Nasdaq IPO
- A company's first public sale of shares on the Nasdaq stock exchange.
Source: Wikipedia