LiveDRBench
Agents perform 100 deep research tasks and return key claims discovered during search. Scores use claim-level F1.
Microsoft reports results across current deep research systems and plans periodic live task updates.
- Made by
- Microsoft Research
- Released
- August 2025
- Kind
- Deep research
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Browser
- Items from
- Real work and use
- Refresh
- New items on a schedule
- Run by
- Anyone
- In views
- Agents, Kept fresh
- Last model added
- February 2025
- Scores refreshed
- November 21st, 2026
OpenAI deep research leads with 55.5% OpenAI deep research leads with 55.5%
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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.
- 1 OpenAI deep research 55.5%
- 2 Perplexity Deep Research 35.5%
- 3 Gemini Deep Research 26.3%
Source: The LiveDRBench paper
Source: The LiveDRBench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | OpenAI deep research | 55.5% | Feb 2025 | Official leaderboard | |
| 2 | Perplexity Deep Research | 35.5% | Official leaderboard | ||
| 3 | Gemini Deep Research | 26.3% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | OpenAI deep research | 55.5% | Feb 2025 | Official 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 LiveDRBench 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 21 months ago, in February 2025, for OpenAI deep research. 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 benchmark’s paper (3 entries).
- Note Models scored Only 1 model we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 21 months ago, in February 2025, for OpenAI deep research.
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 55.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 1 row for models we track and 2 other entries at the last read.
- Pass Last read November 21st, 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.