QCalEval (In-Context) - Parameter Extraction: leaderboard

Extraction of family-specific physical parameters as JSON on QCalEval (2026) quantum computing calibration plots with in-context demonstrations from the same experiment family, scored per field with tolerances. 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, with one worked extraction example, on the QCalEval quantum-calibration plots with in-context demonstrations from the same experiment family (scenario types with a single sample left out), greedy decoding; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 17 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)84.5#99
2Claude Opus 4.681.3#113
3Gemma 4 31B (IT)76.9#350
4Gemini 3.1 Flash Lite73.6#371
5GPT-5.472.9#135
6GPT-5.4 Mini72.7#406
7Claude Sonnet 4.671.9#173
8Qwen 3.5 27B71.5#375
9Qwen 3.5 35B A3B64.4#492
10Qwen 3.5 397B A17B64.3#264
11Qwen 3.5 9B63#828
12Qwen 3.5 122B A10B62.5#346
13InternVL3-38B59.5#939
14Claude Haiku 4.558.7#583
15Kimi-VL-A3B54.3#2340

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=qcaleval-in-context-parameter-extraction · How It Works · Data refreshed daily, snapshot 2026-11-21.