Skip to main content
BenchLM
Advertise

Benchmark profile

DeepSearchQA

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

Data verified

Benchmark score on DeepSearchQA — July 29, 2026

BenchLM mirrors the published score view for DeepSearchQA. Claude Opus 5 leads the public snapshot at 95.0% , followed by Kimi K3 (95.0%) and Claude Opus 4.8 (93.1%). BenchLM does not use these results to rank models overall.

1Closed

Claude Opus 5

Anthropic

claude-opus-5

95.0%
Overall 82.81
2Closed

Kimi K3

Moonshot AI

kimi-3

95.0%
Overall 79.89Context 1.05M
3Closed

Claude Opus 4.8

Anthropic

claude-opus-4-8

93.1%
Overall 77.41Context 1M
12 modelsAgenticCurrentDisplay onlyUpdated July 29, 2026

Benchmark score table (12 models)

Score
1
Claude Opus 5Anthropic · Closed
95.0%
2
Kimi K3Moonshot AI · Closed
95.0%
3
Claude Opus 4.8Anthropic · Closed
93.1%
4
Step 3.7 FlashStepFun · Open weight
92.8%
5
Kimi K2.6Moonshot AI · Open weight
92.5%
6
Muse Spark 1.1Meta · Closed
84.9%
7
Kimi K2.5Moonshot AI · Open weight
77.1%
8
Muse SparkMeta · Closed
74.8%
9
Claude Opus 4.6Anthropic · Closed
73.7%
10
GPT-5.4OpenAI · Closed
73.6%
11
Gemini 3.1 ProGoogle · Closed
69.7%
12
Grok 4.20xAI · Closed
62.8%

The published DeepSearchQA snapshot places Claude Opus 5 first at 95.0%. The third row is 1.9 points behind. The broader top-10 range is 21.4 points, so the table still separates the published systems.

12 models have been evaluated on DeepSearchQA. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. DeepSearchQA is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About DeepSearchQA

Year

2026

Tasks

Agentic browsing and list-answer questions

Format

Search / open / find browser-agent evaluation

Difficulty

Agentic web research

Meta describes DeepSearchQA as a browser-tool evaluation graded with an F1-style semantic set match. BenchLM stores it as a display-only agentic search benchmark.

Muse Spark Eval Methodology

BenchLM freshness & provenance

Version

DeepSearchQA 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does DeepSearchQA measure?

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

Which model scores highest on DeepSearchQA?

Claude Opus 5 by Anthropic currently leads with a score of 95.0% on DeepSearchQA.

How many models are evaluated on DeepSearchQA?

12 AI models have been evaluated on DeepSearchQA on BenchLM.

Compare Top Models on DeepSearchQA

Claude Opus 5 vs Kimi K3Kimi K3 vs Claude Opus 4.8Claude Opus 4.8 vs Step 3.7 FlashStep 3.7 Flash vs Kimi K2.6
Last updated: July 29, 2026 · BenchLM version DeepSearchQA 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.