5 models
Ranked by Harvey Legal Agent Benchmark
Reasoning Tools JSON 19.6

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

xai/grok-4.7 2026-09-21 500K context $2/M input $6/M output
27 providers
Reasoning Tools JSON 15.8

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

xai/grok-4.6 2026-08-12 500K context $2/M input $6/M output
34 providers
13.1

Muse Wonder Full is the most capable model in Meta's Muse Wonder series, built for long-running professional agents and ultra-long-horizon software engineering. It shares Muse Wonder's Active Memory and Active Focus capabilities and generally scores higher on Meta's agentic and coding evaluations.

meta/muse-wonder-full 2026-10-12 1.04858M context Input not listed Output not listed
Reasoning Tools JSON 10.0

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

google/gemini-3.8-flash 2026-09-02 1.04858M context $0.825/M input $4.125/M output
32 providers
Reasoning Tools JSON 10.0

Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.

meta/muse-wonder-1.0 2026-10-12 1.04858M context $4/M input $20/M output
11 providers