WebForge-Bench - Information Retrieval: leaderboard
WebForge-Bench (2026) tests browser agents on tasks set in automatically generated, reproducible websites with injected real-web noise, controlled for difficulty along seven dimensions. This board is task accuracy in percent on the information retrieval and analysis domain with screenshot and DOM input; higher is better.
Metric: Accuracy (%) on the information retrieval and analysis tasks of the 934 WebForge-Bench tasks on generated, self-contained websites with injected real-web noise, up to 50 browser actions in a Chromium GUI, final-state answer checking; multimodal setting: screenshot plus DOM; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 79.4 | #145 |
| 2 | Kimi K2.5 | 75.6 | #266 |
| 3 | Claude Sonnet 4.5 | 73.8 | #261 |
| 4 | GPT-5 Mini | 73.8 | #364 |
| 5 | GPT-5.2 | 64.4 | #185 |
| 6 | Gemini 3 Flash | 62.5 | #175 |
| 7 | Qwen 3 VL 235B A22B | 58.8 | #485 |
| 8 | GPT-5 Nano | 43.8 | #906 |
| 9 | Gemini 2.5 Flash Lite | 41.9 | #964 |
| 10 | qwen3-omni-30B | 26.2 | #1608 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=webforge-bench-information-retrieval · How It Works · Data refreshed daily, snapshot 2026-11-21.