Meta Muse Spark Open Card - WorldVQA (Tools, 3000 questions): leaderboard

Meta Muse Spark Open release evaluation: Tool-assisted visual knowledge on the official 3,000-question subset excluding Notable People; question-level accuracy. Only internal runs; Muse/Inkling xhigh and Kimi max where included.

Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around April 2028. 2 models tracked.

Top models

#ModelScoreOverall rank
1Muse Spark Open (xHigh)49.4#22 (Muse Spark Open)
2Inkling (xHigh)18#122 (Inkling)

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.

Interactive version: theaggregate.ai/benchmark?slug=meta-muse-spark-open-card-worldvqa-tools-3000-questions · How It Works · Data refreshed daily, snapshot 2026-10-16.