DeepSynth-Eval (Agentic Multi-Turn): leaderboard

Metric: Overall checklist score (%; plan, per-section selective full-text reading and writing, final polish; 96 survey-writing tasks, 19,167 atomic checklist requirements; group score min(1, net reward / saturation threshold) with -1 for an incorrect mention, weighted over groups; DeepSeek-V3.2 judge). Source: arxiv.org. Saturation forecast: Around June 2027. 4 models tracked.

Top models

#ModelScore
1Qwen 3 235B A22B 2507 (Thinking)35.5
2GPT-5.233.3
3DeepSeek V3.230.4
4Qwen 3 30B A3B 2507 (Thinking)17.3

Interactive version: theaggregate.ai/benchmark?slug=deepsynth-eval-agentic-multi-turn · How It Works · Data refreshed daily, snapshot 2026-09-26.