CircuitRubric - Short (Strict Ports): leaderboard
CircuitRubric structural analog-circuit netlist benchmark (Short (Strict Ports)) measuring exact graph-isomorphism + sizing-ratio FULL% across 125 fixtures.
Metric: FULL Exact Graph-Isomorphism Pass Rate (%). Source: github.com. Saturation forecast: Around February 2027. 31 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 84.8 | #102 | |
| 2 | Claude Opus 4.8 | xHigh | 77.6 | #64 |
| 3 | GPT-5.5 | 72 | #56 | |
| 4 | Kimi K2.6 | 66.4 | #197 | |
| 5 | Claude Opus 4.7 | 65.6 | #86 | |
| 6 | Qwen 3.7 Max | 65.6 | #160 | |
| 7 | GLM-5.1 | 62.4 | #200 | |
| 8 | DeepSeek V4 Pro | 52 | #201 | |
| 9 | Qwen 3.7 Plus | 48.8 | #221 | |
| 10 | Claude Sonnet 4.6 | 48 | #179 | |
| 11 | MiniMax-M3 | 45.6 | #290 | |
| 12 | GLM-4.5 | 34.4 | #540 | |
| 13 | DeepSeek V4 Flash | 33.6 | #273 | |
| 14 | Kimi K2 0905 | 20.8 | #578 | |
| 15 | Claude Haiku 4.5 (20251001) | 19.2 | #549 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=circuitrubric-short-strict-ports · How It Works · Data refreshed daily, snapshot 2026-11-22.