Werdykt v1 - Category Rules: leaderboard
Werdykt v1 Category Rules measures text-only decisions in Polish and English. The full test has 5,000 hidden questions in twenty balanced language/category groups of 250; category panels combine 500 questions and language panels have 2,500. Macro accuracy gives groups equal weight. Request errors and unparsed answers count incorrect. Native non-control systems retain their interface, engine, reasoning, legacy and source-independence flags; decision endpoints remain distinct from chat.
Metric: Accuracy (%). Source: basal.si5.pl. Saturation forecast: Rough model projection: around 2026. 121 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.8 Flash (Werdykt Run: native=Gemini%203.8%20Flash; cfg=d6e25ef16f84a68f) | 100 | |
| 2 | Claude Opus 5.5 (Werdykt Run: native=Claude%20Opus%205.5; cfg=6d04e9478761c26f) | 100 | |
| 3 | GPT-6.1 Sol (Werdykt Run: native=GPT-6.1%20Sol; cfg=9bc38d71de848a6b) | 100 | |
| 4 | GPT-6 Astra (Werdykt Run: native=GPT-6%20Astra; cfg=4a80c27c0021a614) | 100 | |
| 5 | Gemini 3.1 Pro (Preview) (Werdykt Run: native=Gemini%203.1%20Pro%20%28preview%29; cfg=e8ffbba3cfe39393) | 99.6 | |
| 6 | GPT-6 Luna (Werdykt Run: native=GPT-6%20Luna; cfg=b572761faa59abee) | 98.8 | |
| 7 | Respan Span-02 · endpoint z rozumowaniem (Werdykt Run: native=Respan%20Span-02%20%C2%B7%20endpoint%20z%20rozumowaniem; cfg=879b2a76d14a9a0e) | 81.2 | |
| 8 | Solar Decide (Werdykt Run: native=Solar%20Decide; cfg=68323f89c62b9816) | 72.2 | |
| 9 | Respan Span-02 · 750 ms (Werdykt Run: native=Respan%20Span-02%20%C2%B7%20750%20ms; cfg=ad28e04420c43a40) | 62.4 | |
| 10 | mammoth-1 (Werdykt Run: native=mammoth-1; cfg=7ac9b4868f7083b8) | 59 |
Interactive version: theaggregate.ai/benchmark?slug=werdykt-v1-category-rules · How It Works · Data refreshed daily, snapshot 2026-11-05.