Quantum API Drift - Qiskit 1.3: leaderboard
Part of the quantum-api-drift benchmark (Khalifa University, 2026): code for 50 Qiskit HumanEval-derived tasks is requested for Qiskit 1.3 and executed in a Qiskit 1.3 environment, three samples per prompt at temperature 0.8. The score is Pass@1 in percent; higher is better.
Metric: Pass@1 (%; unbiased estimator from 3 samples per task, macro-averaged over 50 Qiskit HumanEval-derived tasks) of code generated for Qiskit 1.3 (1.3.0), executed in that Qiskit environment; REST API access at temperature 0.8 with a 1,024-token output cap; higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4.20 | 51.33 | #297 |
| 2 | Claude Opus 4.7 | 43.33 | #79 |
| 3 | Kimi K2 | 42 | #439 |
| 4 | GPT-5.3 Codex | 35.77 | #116 |
| 5 | Nemotron 3 Super | 35.57 | #768 |
| 6 | GPT-OSS-120B | 34.67 | #700 |
| 7 | Devstral 2 | 28.77 | #1003 |
| 8 | Qwen3 Coder | 28.67 | #586 |
| 9 | GPT-5.4 | 26.67 | #123 |
| 10 | GPT-5.4 Nano | 22.67 | #635 |
| 11 | Claude Sonnet 4.6 | 21.33 | #161 |
| 12 | GLM-4.7 Flash | 20.67 | #1259 |
| 13 | Qwen 3 32B | 18.67 | #960 |
| 14 | Gemma 4 31B (IT) | 13.33 | #342 |
| 15 | Llama 3.3 70B Instruct | 4 | #1357 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=quantum-api-drift-qiskit-1-3 · How It Works · Data refreshed daily, snapshot 2026-11-13.