PaperScope
Agents search multiple scientific papers to compare figures, summarize results, and solve problems. Each question can require evidence from several documents.
- Made by
- Lei Xiong and colleagues
- Released
- January 2026
- Kind
- Deep research
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-5.1 #66 on the capability index
- Last model added
- November 2025
- Scores refreshed
- November 20th, 2026
Grok 4 leads with 41.0 among models released by November 2025 Grok 4 leads with 41.0 among models released by November 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in November 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 41.0 Grok 4
- 30.4 Kimi K2
- 29.3 OpenAI deep research
- 26.5
DeepSeek-V3.1
- 23.7 GPT-4o mini
- 22.9 Qwen3-VL
- 21.6 ASearcher-Web-7B
- 20.5 Gemini 2.5 pro (snapshot unspecified)
- 19.3
Gemini 2.5 Flash
- 19.2 MMSearch-R1-7B
- 18.7 WebWatcher 32B
- 18.1 DR Tulu-8B
- 17.8 GPT-5.1
- 14.4 GLM-4.5V
- 13.3 MiroThinker-v1.0-30B
- 10.7 Tongyi Deep Research 30B
- 1 Grok 4 41.0
- 2 Kimi K2 Sep 2025 30.4
- 3 OpenAI deep research 29.3
- 4
DeepSeek-V3.1 26.5
- 5 GPT-4o mini 23.7
- 6 Qwen3-VL 22.9
- 7 ASearcher-Web-7B 21.6
- 8 Gemini 2.5 pro (snapshot unspecified) 20.5
- 9
Gemini 2.5 Flash Sep 2025, thinking 19.3
- 10 MMSearch-R1-7B 19.2
- 11 WebWatcher 32B 18.7
- 12 DR Tulu-8B 18.1
- 13 GPT-5.1 17.8
- 14 GLM-4.5V 14.4
- 15 MiroThinker-v1.0-30B 13.3
- 16 Tongyi Deep Research 30B 10.7
Source: Official PaperScope leaderboard
- 1 Grok 4 41.0
- 2 Kimi K2 Sep 2025 30.4
- 3 OpenAI deep research 29.3
- 4
DeepSeek-V3.1 26.5
- 5 GPT-4o mini 23.7
- 6
Gemini 2.5 Flash Sep 2025, thinking 19.3
- 7 GPT-5.1 17.8
- 8 GLM-4.5V 14.4
Source: Official PaperScope leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4 | 41.0 | Jul 2025 | Official leaderboard | |
| 2 | Kimi K2 Sep 2025 | 30.4 | ReAct | Sep 2025 | Official leaderboard |
| 3 | OpenAI deep research | 29.3 | Feb 2025 | Official leaderboard | |
| 4 | | 26.5 | ReAct | Aug 2025 | Official leaderboard |
| 5 | GPT-4o mini | 23.7 | ReAct | Jul 2024 | Official leaderboard |
| 6 | Qwen3-VL | 22.9 | ReAct | Official leaderboard | |
| 7 | ASearcher-Web-7B | 21.6 | Official leaderboard | ||
| 8 | Gemini 2.5 pro (snapshot unspecified) | 20.5 | ReAct | Official leaderboard | |
| 9 | | 19.3 | thinking, ReAct | Sep 2025 | Official leaderboard |
| 10 | MMSearch-R1-7B | 19.2 | Official leaderboard | ||
| 11 | WebWatcher 32B | 18.7 | ReAct | Official leaderboard | |
| 12 | DR Tulu-8B | 18.1 | Official leaderboard | ||
| 13 | GPT-5.1 | 17.8 | ReAct | Nov 2025 | Official leaderboard |
| 14 | GLM-4.5V | 14.4 | ReAct | Aug 2025 | Official leaderboard |
| 15 | MiroThinker-v1.0-30B | 13.3 | Official leaderboard | ||
| 16 | Tongyi Deep Research 30B | 10.7 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4 | 41.0 | Jul 2025 | Official leaderboard | |
| 2 | Kimi K2 Sep 2025 | 30.4 | ReAct | Sep 2025 | Official leaderboard |
| 3 | OpenAI deep research | 29.3 | Feb 2025 | Official leaderboard | |
| 4 | | 26.5 | ReAct | Aug 2025 | Official leaderboard |
| 5 | GPT-4o mini | 23.7 | ReAct | Jul 2024 | Official leaderboard |
| 6 | | 19.3 | thinking, ReAct | Sep 2025 | Official leaderboard |
| 7 | GPT-5.1 | 17.8 | ReAct | Nov 2025 | Official leaderboard |
| 8 | GLM-4.5V | 14.4 | ReAct | Aug 2025 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Reasoning, Induction and Summary. Grok 4 leads 1 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Reasoning
8 models we track have a score here.
- 1 Grok 4 36.0
- 2 OpenAI deep research ↑1 13.0
- 3 Kimi K2 Sep 2025 ↓1 12.0
- 4
Gemini 2.5 Flash Sep 2025 ↑2 7.00
- 5 GPT-4o mini 6.00
- 6
DeepSeek-V3.1 ↓2 6.00
- 7 GLM-4.5V ↑1 0.00
- 8 GPT-5.1 ↓1 0.00
Induction
8 models we track have a score here.
- 1
DeepSeek-V3.1 ↑3 26.3
- 2 GPT-4o mini ↑3 25.5
- 3 Kimi K2 Sep 2025 ↓1 24.1
- 4 Grok 4 ↓3 20.0
- 5
Gemini 2.5 Flash Sep 2025 ↑1 13.3
- 6 OpenAI deep research ↓3 0.00
- 7 GLM-4.5V ↑1 0.00
- 8 GPT-5.1 ↓1 0.00
Summary
8 models we track have a score here.
- 1 Kimi K2 Sep 2025 ↑1 56.6
- 2 OpenAI deep research ↑1 56.3
- 3 Grok 4 ↓2 53.7
- 4 GPT-4o mini ↑1 53.3
- 5
DeepSeek-V3.1 ↓1 52.2
- 6 GPT-5.1 ↑1 42.0
- 7
Gemini 2.5 Flash Sep 2025 ↓1 38.4
- 8 GLM-4.5V 37.3
Solution
8 models we track have a score here.
- 1 OpenAI deep research ↑2 59.1
- 2 GPT-5.1 ↑5 51.8
- 3
DeepSeek-V3.1 ↑1 51.6
- 4 Kimi K2 Sep 2025 ↓2 49.9
- 5 Grok 4 ↓4 48.3
- 6 GLM-4.5V ↑2 32.5
- 7
Gemini 2.5 Flash Sep 2025 ↓1 29.7
- 8 GPT-4o mini ↓3 22.1
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official PaperScope leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official PaperScope leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state.
Gemini 4 Neon 56.3%
- MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks.
Gemini 4 Argon 90.7%
- BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes.
Qwen3.7-Max 75%
- τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state.
Qwen 3.8 Max 55.1%
- Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 12 months ago, in November 2025, for GPT-5.1. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (16 entries).
- Pass Models scored 8 models we track, plus 8 other entries on its leaderboard.
- Warning Newest score The newest came 12 months ago, in November 2025, for GPT-5.1.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.1 (#66).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 8 rows for models we track and 8 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.