# DeepSearchQA 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://modelchoice.dev/leaderboards/benchmarks/agentic-deep-search-qa

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

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Search / open / find browser-agent evaluation |
| Tasks | Agentic browsing and list-answer questions |
| Difficulty | Agentic web research |
| Published by | [Muse Spark Eval Methodology](https://ai.meta.com/static-resource/muse-spark-eval-methodology) |

An agentic browsing benchmark where models search the web, gather evidence, and answer list-style questions using browser tools.

## DeepSearchQA ranking

25 models with a published DeepSearchQA 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 | Search / open / find browser-agent evaluation | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Atria Dawn Preview](https://modelchoice.dev/models/atria-dawn-preview) | Shanghai Artificial Intelligence Laboratory | 96.0 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 95.0 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 95.0 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 93.1 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Step 3.7 Flash](https://modelchoice.dev/models/step-3-7-flash) | StepFun | 92.8 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 92.5 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Apodex 1.1](https://modelchoice.dev/models/apodex-1-1) | Apodex | 92.4 | Observed 2026-11-21 · source benchlm:models |
| 8 | [dots3-note Preview](https://modelchoice.dev/models/dots3-note-preview) | Dots Studio | 92.1 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Inkling 2 Small](https://modelchoice.dev/models/inkling-2-small) | Thinking Machines Lab | 90.9 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Ling 3.0 Flash Sante](https://modelchoice.dev/models/ling-3-0-flash-sante) | InclusionAI | 90.8 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Muse Spark 1.3](https://modelchoice.dev/models/muse-spark-1-3) | Meta | 89.4 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Inkling 2 Mini](https://modelchoice.dev/models/inkling-2-mini) | Thinking Machines Lab | 85.3 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Muse Spark 1.1](https://modelchoice.dev/models/muse-spark-1-1) | Meta | 84.9 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Beam 1.0 501B-A23B NVFP4](https://modelchoice.dev/models/reflection-beam-nvfp4) | Reflection AI | 81.1 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Beam 1.0 501B-A23B](https://modelchoice.dev/models/reflection-beam) | Reflection AI | 80.5 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Beam 1.0 501B-A23B FP8](https://modelchoice.dev/models/reflection-beam-fp8) | Reflection AI | 79.6 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 77.1 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Muse Spark](https://modelchoice.dev/models/muse-spark) | Meta | 74.8 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Muse Glimmer 30B](https://modelchoice.dev/models/muse-glimmer-30b) | Meta | 74.6 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Claude Opus 4.6](https://modelchoice.dev/models/claude-opus-4-6) | Anthropic | 73.7 | Observed 2026-11-21 · source benchlm:models |
| 21 | [GPT-5.4](https://modelchoice.dev/models/gpt-5-4) | OpenAI | 73.6 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Mercury 3](https://modelchoice.dev/models/mercury-3) | Inception | 71.3 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Gemini 3.1 Pro](https://modelchoice.dev/models/gemini-3-1-pro) | Google | 69.7 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Grok 4.20](https://modelchoice.dev/models/grok-4-20-beta) | xAI | 62.8 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Mercury 2.5](https://modelchoice.dev/models/mercury-2-5) | Inception | 34.0 | 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.
