SuperResearch v1 - Search-Augmented Baseline Global Conclusions: leaderboard
SuperResearch paper 2603.00582 v1, 300 tasks and 12 systems. This pinned experiment defines Overall as the aggregation of Coverage, Consistency, Utility and Objectivity. Current website metrics use a different definition and are not mixed with these results. Coverage is depth-weighted fact/insight/conclusion recall against expert knowledge anchors. Architecture: Search-Augmented Baseline. Search-augmented baselines use the common LangGraph/Tavily scaffold. Native search and deep-research systems retain distinct endpoint identities; unspecified snapshots remain source-qualified. Global Conclusions. Metric: Score (%).
Metric: Score (%). Source: arxiv.org. Saturation forecast: Around 2029. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.3 70B Instruct | 13.15 | #537 |
| 2 | MiniMax-M2.1 | 12.89 | #292 |
| 3 | Qwen 2.5 72B Instruct | 9.9 | #462 |
No result here: #5 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superresearch-v1-search-augmented-baseline-global-conclusions · How It Works · Data refreshed daily, snapshot 2026-10-26.