Meta Muse Spark Open Card - ZeroBench (Tools, Pass@5): leaderboard

Meta Muse Spark Open release evaluation: Tool-assisted visual reasoning on 100 questions; success in at least one of five samples, judged by GPT-OSS-120B High. Only internal runs; Muse/Inkling xhigh and Kimi max where included.

Metric: Pass@5 (%). Source: huggingface.co. Saturation forecast: Around May 2028. 2 models tracked.

Top models

#ModelScoreOverall rank
1Muse Spark Open (xHigh)50#22 (Muse Spark Open)
2Inkling (xHigh)14#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-zerobench-tools-pass-5 · How It Works · Data refreshed daily, snapshot 2026-10-16.