QCalEval - Parameter Extraction: leaderboard

Extraction of family-specific physical parameters as JSON 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, scored per field with tolerances and failed parses scored 0. Score from 0 to 100; higher is better.

Metric: Score (0-100) for family-specific physical parameters extracted as JSON, per-field tolerance scoring, failed parses scored 0, 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 February 2027. 18 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)71.5#99
2Gemma 4 31B (IT)68.3#350
3Claude Opus 4.664.7#113
4GPT-5.464.3#135
5Gemini 3.1 Flash Lite63.8#371
6GPT-5.4 Mini62.6#406
7Qwen 3.5 397B A17B62.5#264
8Ising-Calibration-1-35B-A3B62.5
9Qwen 3.5 122B A10B61.2#346
10Claude Sonnet 4.660.4#173
11Qwen 3.5 27B58.7#375
12Qwen 3.5 35B A3B57.8#492
13Qwen 3.5 9B57.1#828
14InternVL3-78B52.9#759
15Claude Haiku 4.551#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-parameter-extraction · How It Works · Data refreshed daily, snapshot 2026-11-21.