ClawForge - Multi-Source Reasoning: 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 86 tasks whose primary ability is multi-source reasoning, deciding from several conflicting information sources; percent, higher is better.

Metric: Strict full-pass accuracy (%) on the 86 tasks whose primary ability is multi-source reasoning (deciding from several conflicting information sources), 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 March 2027. 7 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-5.440.7#135
2Claude Sonnet 4.639.5#173
3Claude Opus 4.637.2#113
4GPT-5.3 Codex37.2#124
5GPT-5.231.4#185
6Kimi K2.531.4#266
7O325.6#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-multi-source-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.