QCalEval - Outcome Classification: leaderboard
Four-way classification of the experimental outcome (expected, suboptimal parameters, anomalous, apparatus issue) on QCalEval (2026), 243 quantum computing calibration examples from 22 experiment families of superconducting-qubit and neutral-atom experiments, answered zero-shot with the experiment background. Accuracy in percent; higher is better.
Metric: Accuracy (%) of the four-way experimental outcome label (expected behavior, suboptimal parameters, anomalous behavior, apparatus issue), on the 243 quantum-calibration examples of QCalEval (22 experiment families, superconducting qubits and neutral atoms), zero-shot with the family background text, greedy decoding; higher is better. Source: arxiv.org. Saturation forecast: Around March 2027. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ising-Calibration-1-35B-A3B | 67.1 | |
| 2 | Gemini 3.1 Pro (Preview) | 57.2 | #99 |
| 3 | Gemma 4 31B (IT) | 54.3 | #350 |
| 4 | Gemini 3.1 Flash Lite | 53.5 | #371 |
| 5 | GPT-5.4 | 52.7 | #135 |
| 6 | Claude Opus 4.6 | 49 | #113 |
| 7 | Claude Sonnet 4.6 | 48.6 | #173 |
| 8 | Qwen 3.5 27B | 45.7 | #375 |
| 9 | Qwen 3.5 122B A10B | 44 | #346 |
| 10 | Qwen 3.5 397B A17B | 42.8 | #264 |
| 11 | Qwen 3.5 35B A3B | 39.9 | #492 |
| 12 | GPT-5.4 Mini | 39.5 | #406 |
| 13 | Qwen 3.5 9B | 37.9 | #828 |
| 14 | InternVL3-78B | 37 | #759 |
| 15 | Claude Haiku 4.5 | 36.6 | #583 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=qcaleval-outcome-classification · How It Works · Data refreshed daily, snapshot 2026-11-21.