SPUR - Information Localization: leaderboard

SPUR (2026) tests multimodal models with multiple-choice questions on multi-panel biomedical experimental figures from PubMed Central. Accuracy in percent on information localization questions, which ask the model to map panels to their experimental conditions; higher is better.

Metric: Accuracy (%) on SPUR the 621 information localization multiple-choice questions about multi-panel biomedical experimental figures from PubMed Central papers (questions drafted by GPT-4o, kept only when GPT-4o failed them in at least six of ten text-only attempts, then expert-reviewed): the questions ask the model to map panels to their experimental conditions; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 19 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3 Pro (Preview)59.67#123
2GLM-4.5V57.65#756
3Claude 3.7 SonnetThinking57.45#455
4Ministral-3-8B-Instruct-251257.03#1923
5Llama 4 Maverick56.61#1113
6Seed-1.656.61#481
7Ministral-3-14B-Instruct-251256.56#1651
8Gemini 2.5 Pro (Preview 06-05)56.47#222
9O4 MiniHigh55.34#372
10Qwen 3 VL 30B A3B (Thinking)55.27#727
11GPT-5.154.47#248
12Mistral Small 3.153.48#1734
13Grok 4.1 Fast52.98#431
14Qwen 3 VL 30B A3B Instruct51.05#903
15InternVL3-78B49.84#765

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=spur-information-localization · How It Works · Data refreshed daily, snapshot 2026-11-22.