Qiskit QuantumKatas: leaderboard
Metric: Best (self-reported). Source: benchmarklist.com. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 83.1 |
| 2 | Claude Opus 4.7 | 80.9 |
| 3 | Claude Sonnet 4.6 | 78 |
| 4 | GPT-5.3 Codex | 75.1 |
| 5 | Gemini 3.1 Pro (Preview) | 74.6 |
| 6 | Gemma 4 31B | 68 |
| 7 | GPT-OSS-120B | 65.7 |
| 8 | Gemma 4 26B A4B | 61.4 |
| 9 | Claude Haiku 4.5 | 60.3 |
| 10 | GPT-OSS-20B | 59.7 |
| 11 | Mistral Large 3 | 48.6 |
| 12 | Llama 4 Maverick | 43.7 |
| 13 | Mistral Small 3.2 | 40 |
| 14 | Granite 4.1 30B | 38.9 |
| 15 | Llama 4 Scout | 34.3 |
Interactive version: theaggregate.ai/benchmark?slug=qiskit-quantumkatas · How It Works · Data refreshed daily, snapshot 2026-09-05.