Qiskit QuantumKatas: leaderboard
We adapt Microsoft's QuantumKatas -- a well-established quantum computing curriculum -- from Q# to Qiskit, the most widely-adopted quantum computing framework, and package it with an evaluation framework for systematic LLM assessment. The resulting benchmark comprises 350 tasks across 26 categories, spanning fundamental gates through advanced algorithms (Grover's, Simon's, Deutsch-Jozsa), error co
Metric: Best (self-reported). Source: benchmarklist.com. Saturation forecast: Around June 2027. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 83.1 | #31 |
| 2 | Claude Opus 4.7 | 80.9 | #49 |
| 3 | Claude Sonnet 4.6 | 78 | #90 |
| 4 | GPT-5.3 Codex | 75.1 | #69 |
| 5 | Gemini 3.1 Pro (Preview) | 74.6 | #58 |
| 6 | Gemma 4 31B | 68 | #200 |
| 7 | GPT-OSS-120B | 65.7 | #341 |
| 8 | Gemma 4 26B A4B | 61.4 | #358 |
| 9 | Claude Haiku 4.5 | 60.3 | #280 |
| 10 | GPT-OSS-20B | 59.7 | #518 |
| 11 | Mistral Large 3 | 48.6 | #401 |
| 12 | Llama 4 Maverick | 43.7 | #464 |
| 13 | Mistral Small 3.2 | 40 | #605 |
| 14 | Granite 4.1 30B | 38.9 | #573 |
| 15 | Llama 4 Scout | 34.3 | #656 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=qiskit-quantumkatas · How It Works · Data refreshed daily, snapshot 2026-10-20.