SpecVQA - Chinese Descriptive (L0): leaderboard
SpecVQA (2026) asks questions about 620 scientific spectra (NMR, IR, XRD, Raman, mass, UV-Vis and XPS) from published papers, with expert-revised descriptive and reasoning questions in English and Chinese; GPT-o4-mini judges each answer against the reference, numeric answers within 5 percent. This board covers the Chinese descriptive (L0) questions. Accuracy in percent; higher is better.
Metric: Accuracy (0-1, times 100) on the Chinese descriptive (L0) questions; expert-revised question-answer pairs on 620 spectra (NMR, IR, XRD, Raman, MS, UV-Vis, XPS) from published papers; each answer judged correct or not by GPT-o4-mini against the reference, numeric answers within a 5 percent tolerance; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 80.47 | #152 | |
| 2 | Gemini 3 Pro (Preview) | 79.39 | #119 | |
| 3 | Gemini 2.5 Pro | 77.58 | #276 | |
| 4 | Gemini 2.5 Flash | 74.73 | #463 | |
| 5 | O4 Mini (2025-04-16) | 72.37 | #370 | |
| 6 | GPT-5 | 71.54 | #178 | |
| 7 | O3 (2025-04-16) | 70.27 | #231 | |
| 8 | GPT-5.2 | Non-reasoning | 68.99 | #185 |
| 9 | GPT-5.1 | Non-reasoning | 68.99 | #240 |
| 10 | Claude Sonnet 4.5 | Thinking | 63.15 | #261 |
| 11 | Doubao-Seed-1.6-Flash | Thinking | 61.48 | #1250 |
| 12 | Claude Sonnet 4 | Thinking | 59.57 | #410 |
| 13 | Qwen 3 VL 8B Instruct | 59.27 | #1029 | |
| 14 | Qwen 3 VL 8B (Thinking) | 58.05 | #910 | |
| 15 | Doubao-Seed-1.6 | Thinking | 57.36 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=specvqa-chinese-descriptive-l0 · How It Works · Data refreshed daily, snapshot 2026-11-21.