QuanBench+ - PennyLane: leaderboard
Metric: Pass@1 (%): greedy decoding at temperature 0, one PennyLane program per task, on the 42 framework-aligned QuanBench+ tasks (quantum algorithms, gate decomposition, state preparation), graded by executable functional tests with KL-divergence acceptance for probabilistic outputs; higher is better. Source: arxiv.org. Saturation forecast: Around July 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 42.9 |
| 2 | Gemini 3 Pro | 40.5 |
| 3 | DeepSeek R1 | 33.3 |
| 4 | MiniMax-M2.1 | 31 |
| 5 | Claude 3.7 Sonnet | 26.2 |
| 6 | Kimi K2 (Thinking) | 26.2 |
| 7 | Gemini 2.5 Flash | 23.8 |
| 8 | GPT-4.1 | 23.8 |
| 9 | GLM-4.7 | 23.8 |
| 10 | Llama 4 Maverick | 19 |
| 11 | Qwen 2.5 7B Instruct | 11.9 |
Interactive version: theaggregate.ai/benchmark?slug=quanbench-plus-pennylane · How It Works · Data refreshed daily, snapshot 2026-10-07.