VistaHop (No Tools): leaderboard
VistaHop (2026) Pass@1 without any tools: the model answers each long-horizon visual search question from the image and query alone. Percent; higher is better.
Metric: Pass@1 (%) on 600 Visual DeepSearch tasks (25 scenarios; 154 with 5 to 9 evidence steps and 446 with 10 or more) that require repeatedly inspecting image regions and chaining visual and web evidence, run in the VistaArena agent loop (at most 10 rounds, one tool call per round, temperature 0.7, five runs averaged) with a Qwen3-VL-32B-Instruct judge, without tools (a single answer from the image and query); higher is better. Source: arxiv.org. Saturation forecast: Around September 2028. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 11.33 | #176 |
| 2 | Claude Sonnet 4.5 | 11.08 | #250 |
| 3 | Gemini 2.5 Pro | 8.63 | #266 |
| 4 | Qwen 3 VL 235B A22B Instruct | 7.84 | #522 |
| 5 | Qwen 3 VL 30B A3B Instruct | 6.72 | #871 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=vistahop-no-tools · How It Works · Data refreshed daily, snapshot 2026-11-13.