Redlining commercial contracts across multi-turn negotiations.
Collection of 140 tasks spanning 3 multi-turn negotiation scenarios (2 SaaS MSAs and 1 professional-services MSA) over 4 alternating turns.
Model
Score
GPT-5.6 SolMax
46.8%
GPT-5.5xHigh
44.1%
GPT-5.6 TerraMax
44.0%
Opus 5Max
GPT-5.6 LunaMax
43.3%
APEX NEWSLETTER
New benchmarks, leaderboard shifts, and research from the APEX team.
By subscribing you agree to receive updates from Mercor.Unsubscribe anytime.