InterLV-Search - Level 3 Multi-Branch: leaderboard

The open-web multi-branch questions of Level 3 (at most ten interactions) of InterLV-Search (2026), an interleaved language-vision agentic search benchmark in which intermediate visual evidence decides what to search next; agents use image search, reverse image search, web search, browsing, cropping and code tools. Final-answer accuracy judged by GPT-5.4-mini, percent; higher is better.

Metric: Level 3 open-web interleaved search, the 340 multi-branch questions (at most 10 interactions) final-answer accuracy judged by GPT-5.4-mini for semantic equivalence, %, through the InterLV-Agent reason-act-observe framework with image search, reverse image search, web search, browsing, cropping and code tools; higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)37.94#99
2GPT-5.433.82#135
3Claude Sonnet 4.633.18#173
4Qwen 3.6 Plus29.41#238
5GPT-527.65#178
6SenseNova-MARS-32B21.76
7MMSearch-R1-7B14.77
8VDR-8B11.76

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=interlv-search-level-3-multi-branch · How It Works · Data refreshed daily, snapshot 2026-11-21.