Evolve on Graph Supervised Freebase Average - F1: leaderboard
Evolve on Graph v1 evaluates knowledge-graph reasoning using direct answers, chain of thought, self-consistency, ReAct, retrieval, or separately trained Solver/Proposer systems. It uses Qwen2.5-3B/7B-Instruct and Llama3.1-8B-Instruct. Training lasts 140 steps, with 5 rollouts per task and at most 15 assistant turns. Hit@1 requires an exact normalized match to any gold answer; F1 measures overlap between predicted and gold answer lists. Freebase, Wikidata, and task-specific KG-R1 training scopes remain distinct. Trained weights are not aliased to the instruction backbone. This is the mean across 3 Freebase benchmarks. The GTSQA supervised row’s 2-task average has no second model with the same task support and is not included. Metric: F1 (%).
Metric: F1 (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | EoG study Qwen-2.5-7B-Instruct KG-R1 trainedCWQ | 62.67 | |
| 2 | EoG study Qwen-2.5-7B-Instruct KG-R1 trainedWebQSP | 58.4 | |
| 3 | EoG study Qwen-2.5-7B-Instruct KG-R1 trainedGrailQA | 56.32 |
Interactive version: theaggregate.ai/benchmark?slug=evolve-on-graph-supervised-freebase-average-f1 · How It Works · Data refreshed daily, snapshot 2026-10-28.