# ResearchRubrics leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-research-rubrics

ResearchRubrics: A Benchmark of Prompts and Rubrics for Evaluating Deep Research Agents. Every model the catalog carries a published ResearchRubrics value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Rubric compliance (%) |
| Tasks | Deep-research prompts with 2,500+ expert-written rubrics |
| Difficulty | Open-ended deep research and long-form synthesis |
| Published by | [ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents](https://arxiv.org/abs/2511.07685) |

A deep-research agent benchmark that pairs realistic, domain-diverse prompts with more than 2,500 expert-written rubrics scoring factual grounding, reasoning soundness and clarity of long-form, evidence-backed answers.

## ResearchRubrics ranking

1 model with a published ResearchRubrics value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Rubric compliance (%) | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [LongCat-2.5](https://modelchoice.dev/models/longcat-2-5) | Meituan | 81.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
