AInsteinBench - Quantum Information: leaderboard
The AInsteinBench problems from Qiskit only (the paper's QI column; the subset size is shown only in a figure), solved by the model in the CodeAct agent; the score is the share resolved. ByteDance Seed, which also makes Doubao-Seed-1.8, wrote the benchmark and ran every model.
Metric: % Resolved. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.5 | 67.6 | #161 | |
| 2 | Gemini 3 Pro (Preview) | 62.2 | #120 | |
| 3 | GPT-5 | High | 54.1 | #177 |
| 4 | Seed 1.8 | 54.1 | #250 | |
| 5 | GPT-5.1 | 51.4 | #235 | |
| 6 | Claude Sonnet 4.5 | 48.6 | #258 | |
| 7 | GLM-4.6 | 37.8 | #496 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=ainsteinbench-quantum-information · How It Works · Data refreshed daily, snapshot 2026-11-17.