WellnessBench - Single Turn Pass Rate: leaderboard

WellnessBench - Single Turn Pass Rate: Pass rate (%). WellnessBench native-API evaluation: 60 clinician-authored primary/control task pairs (25 single-turn, 35 dialogue), provider-default reasoning, no system prompt, 4,096 output tokens per turn, three planned repetitions. Gemini 3.7 Flash simulates the user, gates response windows and grades equal-weight rubric rows. Provider blocks and judge failures are excluded; judge audit found optimistic single-turn passes. The Muse models' October 15 run is partial (about two repetitions, three ungraded tasks each). The live overall scoreboard includes later top-ups; older report breakdowns retain their original ten- or twelve-model populations. Consumer-app comparisons are separate and not admitted here.

Metric: Pass rate (%). Source: www.micro1.ai. Saturation forecast: Rough model projection: around 2026. 12 models tracked.

Top models

#ModelScoreOverall rank
1GPT-6.1 Sol (WellnessBench Run: provider-default; native-API; no-system-prompt)91
2GPT-6 Sol (WellnessBench Run: provider-default; native-API; no-system-prompt)91
3GPT-6 Astra (WellnessBench Run: provider-default; native-API; no-system-prompt)89
4GPT-5.6 Sol (WellnessBench Run: provider-default; native-API; no-system-prompt)84
5Grok 4.7 (WellnessBench Run: provider-default; native-API; no-system-prompt)84
6Claude Sonnet 5.5 (WellnessBench Run: provider-default; native-API; no-system-prompt)83
7Muse Spark 1.3 (WellnessBench Run: provider-default; native-API; no-system-prompt; partial-October15)81
8Muse Wonder (WellnessBench Run: provider-default; native-API; no-system-prompt; partial-October15)78
9Claude Fable 5.1 (WellnessBench Run: provider-default; native-API; no-system-prompt)78
10Grok 4.6 (WellnessBench Run: provider-default; native-API; no-system-prompt)77

Interactive version: theaggregate.ai/benchmark?slug=wellnessbench-single-turn-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-06.