CRAB-Bench - Abstract-State Verification: leaderboard

Metric: Abstract-state verification pass rate (%): share of tasks whose conversation passes factuality (actions match the stated plan) and completion (interaction ends correctly), with the RUSE human-aligned user simulator (personas sampled uniformly, all four behavior dimensions); 200 trip-booking tasks (departure and return flight, hotel, attraction) generated from constraint graphs with node and edge distractors, tau-bench framework, pass@1, default inference and reasoning settings, Claude Sonnet 4.6 simulates the user; higher is better. Source: arxiv.org. Saturation forecast: Around July 2027. 4 models tracked.

Top models

#ModelScore
1DeepSeek V3.279
2GLM-565
3Qwen3 Coder Next63
4Claude Sonnet 4.660

Interactive version: theaggregate.ai/benchmark?slug=crab-bench-abstract-state-verification · How It Works · Data refreshed daily, snapshot 2026-09-29.