OntoAct Reference - Tacit-FLE medium (ReAct): leaderboard
Plain ReAct agent (Yao et al., 2023) row only, the paper's untrained baseline agent, compared across its three model conditions: GPT-5.6 Luna with reasoning effort none, GPT-5.6 Luna with medium effort and GPT-5.6 Terra with effort none. Tacit-FLE (introduced by the paper on the Factorio Learning Environment): repair a hidden fault in an existing factory using inherited operational records; medium plant scale, 36 tasks; failed episodes use the full budget. Methods share tasks and interaction budgets. Retrieval-augmented ReAct, Reflexion, IfR, WALL-E and OntoAct rows are agent methods and are not published. Metric: Repair success rate (%). Higher is better. Source: https://arxiv.org/html/2610.21983v1
Metric: Repair success rate (%). Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Terra (Non-reasoning) | 52.8 | #41 (GPT-5.6 Terra) |
| 2 | GPT-5.6 Luna (Non-reasoning) | 52.8 | #68 (GPT-5.6 Luna) |
| 3 | GPT-5.6 Luna (Medium) | 44.4 | #68 (GPT-5.6 Luna) |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ontoact-reference-tacit-fle-medium-react · How It Works · Data refreshed daily, snapshot 2026-10-18.