CircuitRubric - Spec (Strict Ports): leaderboard
CircuitRubric structural analog-circuit netlist benchmark (Spec (Strict Ports)) measuring exact graph-isomorphism + sizing-ratio FULL% across 125 fixtures.
Metric: FULL Exact Graph-Isomorphism Pass Rate (%). Source: github.com. Saturation forecast: Estimated already saturated. 27 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 95.2 | #56 |
| 2 | Qwen 3.7 Plus | 95.2 | #221 |
| 3 | Kimi K2.6 | 94.4 | #197 |
| 4 | DeepSeek V4 Pro | 92 | #201 |
| 5 | Qwen 3.7 Max | 92 | #160 |
| 6 | Claude Sonnet 4.6 | 91.2 | #179 |
| 7 | GLM-5.1 | 91.2 | #200 |
| 8 | MiniMax-M3 | 89.6 | #290 |
| 9 | Claude Haiku 4.5 (20251001) | 88 | #549 |
| 10 | GLM-4.5 | 87.2 | #540 |
| 11 | Llama 4 Maverick | 85.6 | #1113 |
| 12 | DeepSeek V4 Flash | 85.6 | #273 |
| 13 | Llama 3.3 70B Instruct | 84.8 | #1394 |
| 14 | Kimi K2 0905 | 82.4 | #578 |
| 15 | GPT-OSS-20B | 78.4 | #1188 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=circuitrubric-spec-strict-ports · How It Works · Data refreshed daily, snapshot 2026-11-22.