SciUniverse - Maximize amide synthesis yield: leaderboard
Physical task family in C5R's SciUniverse Level 1 (2026-09-24): form N-benzyl-4-methylbenzamide at the Facility-0 lab with under three minutes from amine addition to quench. Passes when the calibrated LC-MS yield reaches the 6.13% human baseline. One attempt per model, so each score is 0 or 100. Pass@1 (%), higher is better.
Metric: Pass@1 (%). Source: c5r.net. Saturation forecast: Around February 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (xHigh) | 100 | #6 (GPT-6 Astra) |
| 2 | Grok 4.6 (xHigh) | 100 | #44 (Grok 4.6) |
| 3 | Claude Fable 5.1 (xHigh) | 100 | #14 (Claude Fable 5.1) |
| 4 | Gemini 3.8 Flash (High) | 0 | #36 (Gemini 3.8 Flash) |
| 5 | GPT-5.6 Sol (xHigh) | 0 | #29 (GPT-5.6 Sol) |
| 6 | Claude Opus 5 (xHigh) | 0 | #20 (Claude Opus 5) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=sciuniverse-maximize-amide-synthesis-yield · How It Works · Data refreshed daily, snapshot 2026-11-12.