TildeOpen-30B: benchmark results

Provider: Other. Access: Open.

Unified ELO 1406 ± 31, rank #1850 of 2656 rated models, from 51 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open PL LLM - 8TAGS (multiple choice, 5-shot)76.88Accuracy (%)73.7
Open PL LLM - CBD (multiple choice, 5-shot)24.41Macro F1 (%)55.4
Open PL LLM - CBD (generative, 5-shot)24.29Macro F1 (%)50.3
Open PL LLM - PolEmo2-IN (multiple choice, 5-shot)75.9Accuracy (%)46.4
Polish Knowledge Benchmark - Cuisine78Accuracy (%)46.3
Polish Knowledge Benchmark - Law & Administration77.58Accuracy (%)37.3
Open PL LLM - PolQA Reranking (multiple choice, 5-shot)60.93Accuracy (%)33
Open PL LLM - Belebele (multiple choice, 5-shot)65.33Accuracy (%)32.8
Polish Knowledge Benchmark - Religion & Philosophy79.34Accuracy (%)32.1
Open PL LLM - PolEmo2-OUT (multiple choice, 5-shot)63.56Accuracy (%)31.3
Polish Knowledge Benchmark - Art68.18Accuracy (%)31.3
Polish Knowledge Benchmark - Traditions & Customs70.86Accuracy (%)29.9

Interactive version: theaggregate.ai/model?slug=tildeopen-30b · How It Works · Data refreshed daily, snapshot 2026-09-19.