InterLV-Search - Level 2: leaderboard

Level 2 (offline interleaved multi-hop search, at most seven 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 2 (offline interleaved multi-hop search, 225 questions, at most 7 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 April 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)41.33#102
2GPT-5.438.22#138
3GPT-535.11#185
4Claude Sonnet 4.634.22#179
5Qwen 3.6 Plus27.56#245
6SenseNova-MARS-32B10.67
7VDR-8B6.9
8MMSearch-R1-7B5.33

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=interlv-search-level-2 · How It Works · Data refreshed daily, snapshot 2026-11-22.