Evaluates AI systems on deep research tasks requiring multi-step information gathering, synthesis, and report generation — mimicking real research workflows.
This definition has not completed editorial and provenance review. Verify its metric, version, source, and evaluation configuration upstream before using it for a model-selection decision.
Tests end-to-end research ability: search, comprehension, synthesis, and writing. Highly relevant to knowledge work.
Score is 0–1 ratio. Few evaluated models (8 scores). Evaluation criteria may be subjective.
Higher is better. Quality ratio (0–1). Top models: ~0.49.
Score is 0–1 ratio.
| # | Model | Score |
|---|---|---|
| 1 | 56.3 | |
| 2 | 50.0 | |
| 3 | 50.0 | |
| 4 | 22.7 | |
| 5 | 22.7 | |
| 6 | 20.6 | |
| 7 | 7.1 | |
| 8 | 4.5 | |
| 9 | 4.3 | |
| 10 | 0.8 | |
| 11 | 0.7 | |
| 12 | 0.7 | |
| 13 | 0.6 | |
| 14 | 0.6 | |
| 15 | 0.6 | |
| 16 | 0.6 | |
| 17 | 0.5 | |
| 18 | 0.5 | |
| 19 | 0.5 | |
| 20 | 0.5 | |
| 21 | 0.5 | |
| 22 | 0.5 | |
| 23 | 0.5 | |
| 24 | 0.5 | |
| 25 | 0.5 | |
| 26 | 0.5 | |
| 27 | 0.5 | |
| 28 | 0.5 | |
| 29 | 0.5 | |
| 30 | 0.5 | |
| 31 | 0.5 | |
| 32 | 0.5 | |
| 33 | 0.5 | |
| 34 | 0.5 | |
| 35 | 0.5 | |
| 36 | 0.5 | |
| 37 | 0.5 | |
| 38 | 0.5 | |
| 39 | 0.5 | |
| 40 | 0.5 | |
| 41 | 0.5 | |
| 42 | 0.5 | |
| 43 | 0.5 | |
| 44 | 0.5 | |
| 45 | 0.5 | |
| 46 | 0.5 | |
| 47 | 0.5 | |
| 48 | 0.5 | |
| 49 | 0.5 | |
| 50 | 0.5 |