SpecVQA - English 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 English descriptive (L0) questions. Accuracy in percent; higher is better.
Metric: Accuracy (0-1, times 100) on the English 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) | 77.82 | #152 | |
| 2 | Gemini 3 Pro (Preview) | 77.18 | #119 | |
| 3 | Gemini 2.5 Pro | 76.45 | #276 | |
| 4 | Gemini 2.5 Flash | 73.95 | #463 | |
| 5 | O4 Mini (2025-04-16) | 71.44 | #370 | |
| 6 | GPT-5 | High | 70.17 | #178 |
| 7 | O3 (2025-04-16) | 69.53 | #231 | |
| 8 | GPT-5.2 | Non-reasoning | 67.76 | #185 |
| 9 | GPT-5.1 | Non-reasoning | 67.76 | #240 |
| 10 | Claude Sonnet 4.5 | Thinking | 61.48 | #261 |
| 11 | Doubao-Seed-1.6-Flash | Thinking | 60.6 | #1250 |
| 12 | Claude Sonnet 4 | Thinking | 59.47 | #410 |
| 13 | Qwen 3 VL 8B (Thinking) | 58.64 | #910 | |
| 14 | Qwen 3 VL 8B Instruct | 57.21 | #1029 | |
| 15 | Doubao-Seed-1.6 | Thinking | 57.21 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=specvqa-english-descriptive-l0 · How It Works · Data refreshed daily, snapshot 2026-11-21.