GOMAX - Medical-device registration: leaderboard

GOMAX October18 snapshot:Claude Code harness,High reasoning,professional deliverables from Chinese industrial cases across five domains. Weighted artifact rubrics,programmatic or model-based verification. deepseek-flash lacks an exact API generation binding and remains source-qualified. Score (%).

Metric: Score (%). Source: huggingface.co. Saturation forecast: Around 2030. 7 models tracked.

Top models

#ModelScoreOverall rank
1GPT-6.1 Sol (High)33#7 (GPT-6.1 Sol)
2GPT-6 Astra (High)14#6 (GPT-6 Astra)
3Claude Fable 5.1 (High)11.5#9 (Claude Fable 5.1)
4Claude Opus 5.5 (High)6#4 (Claude Opus 5.5)
5Kimi K3 (High)5#30 (Kimi K3)
6MiniMax M3 (High)5

No result here: #8 Gemini 4 Argon, #10 Muse Wonder Full.

Interactive version: theaggregate.ai/benchmark?slug=gomax-medical-device-registration · How It Works · Data refreshed daily, snapshot 2026-10-22.