ClawForge - Information Transfer: leaderboard

ClawForge-Bench (2026) gives a command-line agent 362 generated workflow tasks over seeded calendars, inboxes, task boards, files and configuration, where pre-existing state may be partial, stale or duplicated, and grades the final state with executable validators. This board is the strict full-pass accuracy on the 32 tasks whose primary ability is information transfer, carrying information correctly between workflow surfaces; percent, higher is better.

Metric: Strict full-pass accuracy (%) on the 32 tasks whose primary ability is information transfer (carrying information correctly between workflow surfaces), on the ClawForge-Bench snapshot (17 generator-backed scenarios, 362 executable state-conflict workflow tasks over tasks, calendar, email, messaging, files and runtime configuration), command-line agent in multi mode with full interaction history and a 25-step budget, scored by result-first validators over the final normalized state; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-5.481.2#135
2Kimi K2.571.9#266
3GPT-5.3 Codex71.9#124
4GPT-5.262.5#185
5Claude Sonnet 4.659.4#173
6Claude Opus 4.659.4#113
7O350#237

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=clawforge-information-transfer · How It Works · Data refreshed daily, snapshot 2026-11-21.