RapidBench v0.0.4 - web search: leaderboard
RapidBench v0.0.4 electronics engineering benchmark (348 runs, GLM 5.3 judge, DOI 10.5281/zenodo.23602240) with web search enabled; pass rate (%).
Metric: Successful runs (%). Source: www.rapidflare.ai. Saturation forecast: Around November 2027. 7 models tracked. Updated 20 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 58.62 | #15 |
| 2 | GPT-6 Astra | 56.61 | #10 |
| 3 | Claude Opus 5.5 | 50.29 | #9 |
| 4 | Kimi K3.1 Pro | 46.26 | #35 |
| 5 | Gemini 4 Argon | 42.82 | #18 |
| 6 | DeepSeek V4.1 Flash | 42.24 | #69 |
| 7 | GLM-5.3 | 37.07 | #73 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=rapidbench-v0-0-4-web-search · How It Works · Data refreshed daily, snapshot 2026-11-20.