Toolsslug: agent-arena-tool

Agent Arena

Leaderboard evaluating models on real-world long-horizon agentic tasks via causal tracing.

Curated Intelligence

1 items · Page 1/1
Arena.ai (@arena)T1·Models
78 pts
Anthropic Releases Claude Fable 5.2 and Mythos 5.2 Models

Anthropic has launched Claude Fable 5.2 and Claude Mythos 5.2, claiming gains in coding, reasoning and vision for tackling demanding technical work. Fable 5.2 is now live in Arena's Agent Arena and Code Arena, where it can use web search, filesystem and terminal tools on long-horizon agentic tasks, with leaderboard scores to follow.