# ResearchClawBench leaderboard

Agentic 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://modelscale.dev/leaderboards/benchmarks/agentic-research-claw-bench

Every model the catalog carries a published ResearchClawBench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | End-to-end autonomous research evaluation with RADS scoring |
| Tasks | 40 tasks across 10 scientific domains |
| Difficulty | Scientific research re-discovery |
| Published by | [ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research](https://arxiv.org/abs/2606.07591) |

An end-to-end autonomous scientific research benchmark with 40 tasks across 10 scientific domains, where agents receive related literature and raw data, then attempt to rediscover the hidden target paper.

## ResearchClawBench ranking

19 models with a published ResearchClawBench 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 | End-to-end autonomous research evaluation with RADS scoring | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 21.1 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | 20.7 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GLM-5.2](https://modelscale.dev/models/glm-5-2) | Z.AI | 20.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude Opus 4.6](https://modelscale.dev/models/claude-opus-4-6) | Anthropic | 19.9 | Observed 2026-11-21 · source benchlm:models |
| 5 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 19.8 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Qwen3.7 Max](https://modelscale.dev/models/qwen3-7-max) | Alibaba | 18.7 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GLM-5.1](https://modelscale.dev/models/glm-5-1) | Z.AI | 18.2 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | 18.0 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 18.0 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 18.0 | Observed 2026-11-21 · source benchlm:models |
| 11 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 17.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [MiMo-V2.5](https://modelscale.dev/models/mimo-v2-5) | Xiaomi | 16.9 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | 15.3 | Observed 2026-11-21 · source benchlm:models |
| 13 | [MiMo-V2-Pro](https://modelscale.dev/models/mimo-v2-pro) | Xiaomi | 15.3 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | 14.2 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 14.0 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Grok 4.1](https://modelscale.dev/models/grok-4-1) | xAI | 13.5 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 13.3 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Grok 4.3](https://modelscale.dev/models/grok-4-3) | xAI | 12.4 | 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.
