RapidBench v0.0.3 - web search: leaderboard
RapidBench v0.0.3 - web search. RapidBench v0.0.3,116electronics queries×3repetitions; fixed indexed catalogs; complete-answer deterministic product/spec grader; one failed missing observation retained in347-run arm. MCP, web and no-tools are separate benchmark conditions, not model identities. Metric: Successful runs (%). Higher is better.
Metric: Successful runs (%). Source: www.rapidflare.ai. Saturation forecast: Around October 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 59.77 | #10 |
| 2 | Claude Opus 5.5 | 48.85 | #5 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #6 GPT-6 Astra.
Interactive version: theaggregate.ai/benchmark?slug=rapidbench-v0-0-3-web-search · How It Works · Data refreshed daily, snapshot 2026-11-13.