ForeSci - Reviewer Persuasiveness: leaderboard
ForeSci (Tian et al., 2026) asks a model, given only research literature published before a cutoff, to make forward-looking judgements in four AI research decision families. A DeepSeek-V4 virtual reviewer that sees the hidden post-cutoff targets rates how convincing each judgement is on family-specific rubrics; mean holistic score over 500 tasks, scaled to 0-100 (higher is better), for models answering without retrieval.
Metric: Reviewer persuasiveness (x 100; holistic rubric score from a DeepSeek-V4 virtual reviewer given the task, the pre-cutoff evidence and the hidden targets, mean of repeated runs and of the four task families, 500 tasks; native LLM without retrieval, web search disabled). Source: arxiv.org. Saturation forecast: Around February 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 84.6 | #172 |
| 2 | Qwen 3 235B A22B | 78.6 | #622 |
| 3 | GLM-4.6 | 67.4 | #485 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=foresci-reviewer-persuasiveness · How It Works · Data refreshed daily, snapshot 2026-11-12.