DeepSearchQA leaderboard
As of 6 Nov 2026, the top score on DeepSearchQA is 66.1% by Gemini Deep Research Agent (Google), ahead of GPT-5 Pro at 65.2%, across 12 model configurations with a published result (Google, result dated 11 Dec 2025). Research questions with many separate facts to gather; scored on answers that are fully correct, so missing one item fails the task. Published by Google. DeepSearchQA is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 6 Nov 2026)
- Gemini Deep Research Agent holds the top DeepSearchQA score at 66.1% (Google, 11 Dec 2025).
- GPT-5 Pro is second on DeepSearchQA at 65.2% (Google, 11 Dec 2025).
- DeepSearchQA: Research questions with many separate facts to gather; scored on answers that are fully correct, so missing one item fails the task. Published by Google (Google).
- 12 model configurations have a published DeepSearchQA result on BenchLeader (BenchLeader, 6 Nov 2026).
- DeepSearchQA does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
Research questions with many separate facts to gather; scored on answers that are fully correct, so missing one item fails the task. Published by Google.
- Published by
- Googledata via Kaggle Benchmarks
- Category
- Agents & tools
- Index weight
- Reference only
- Models
- 12
- Data as of
- 6 Nov 2026
Kaggle (kaggle.com); each board credits its publishing lab.
- 1Gemini Deep Research Agent66.1%
- 2GPT-5 Pro65.2%
- 3GPT-5.463.7%
- 4Gemini 3.1 Pro60.2%
- 5GPT-559.4%
- 6o3 Deep Research44.2%
- 7o4 mini Deep Research40.4%
- 8Gemini 2.5 Flash25.9%
- 9Gemini 2.5 Pro24.6%
- 10Claude Opus 4.5 (thinking)24.0%
- 11Claude Sonnet 4.5 (thinking)16.0%
- 12Claude Haiku 4.5 (thinking)12.8%
| # | ||||
|---|---|---|---|---|
| 1 |  Gemini Deep Research Agent | 66.1% | – | 2025-12-11 |
| 2 |  GPT-5 Pro | 65.2% | 59.9 | 2025-12-11 |
| 3 | GPT-5.4 | 63.7% | 58.0 | – |
| 4 | Gemini 3.1 Pro | 60.2% | 60.5 | 2026-04-13 |
| 5 | GPT-5 | 59.4% | 57.7 | 2025-12-11 |
| 6 | o3 Deep Research | 44.2% | – | 2025-12-11 |
| 7 | o4 mini Deep Research | 40.4% | – | 2025-12-11 |
| 8 | Gemini 2.5 Flash | 25.9% | 52.7 | 2025-12-11 |
| 9 | Gemini 2.5 Pro | 24.6% | 54.5 | 2025-12-11 |
| 10 |  Claude Opus 4.5thinking | 24.0% | 59.6 | 2025-12-11 |
| 11 | Claude Sonnet 4.5thinking | 16.0% | 52.2 | 2025-12-11 |
| 12 | Claude Haiku 4.5thinking | 12.8% | 45.4 | 2025-12-11 |
More agents & tools benchmarks · All LLM benchmarks
Related benchmarks
Top head-to-heads on DeepSearchQA
Cite as: BenchLeader, “DeepSearchQA leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/kaggle_dsqa.
DeepSearchQA: questions
- What does DeepSearchQA measure?
- Research questions with many separate facts to gather; scored on answers that are fully correct, so missing one item fails the task. Published by Google. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on DeepSearchQA?
- As of 6 Nov 2026, the highest score on DeepSearchQA is 66.1% by Gemini Deep Research Agent (result dated 11 Dec 2025), ahead of GPT-5 Pro at 65.2%. Scores come from Google and are re-read daily.
- Which AI model leads DeepSearchQA?
- Gemini Deep Research Agent leads DeepSearchQA with 66.1% as of 6 Nov 2026 (result dated 11 Dec 2025), ahead of GPT-5 Pro at 65.2%.
- How many models have DeepSearchQA results?
- 12 model configurations have a DeepSearchQA result on BenchLeader, all taken from Google via Kaggle Benchmarks.
- Who runs DeepSearchQA and how often is it updated?
- DeepSearchQA is published by Google. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does DeepSearchQA count toward the BenchLeader Index?
- No. DeepSearchQA is shown for reference but left out of the composite index.