Fietje-2-Instruct: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1332 ± 48, rank #8118 of 10916 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Grip on LLMs - HonestCityBench - Non-Text Modality | 40 | Appropriate acknowledgement rate (%; LLM judge) | 93.3 |
| Grip on LLMs - HonestCityBench - Narrow Expertise | 3 | Appropriate acknowledgement rate (%; LLM judge) | 66.7 |
| Open LLM Leaderboard - BBH | 41.36 | Score | 26.3 |
| Open LLM Leaderboard - IFEval | 27.9 | Score | 25 |
| Grip on LLMs - Dutch Simplification - Amsterdam | 39.48 | SARI (0-100) | 23.3 |
| Open LLM Leaderboard - MMLU-Pro | 21.04 | Score | 22.1 |
| Grip on LLMs - HonestCityBench - Average | 17 | Appropriate acknowledgement rate (%; mean of five categories | 18.3 |
| Grip on LLMs - Dutch Simplification Average | 38.32 | SARI (0-100; mean of two datasets) | 16.7 |
| Grip on LLMs - Dutch tinyARC | 53 | Accuracy (%; GP-IRT estimate from 100 tinyBenchmarks items, | 16.7 |
| Open LLM Leaderboard - MATH Level 5 | 2.27 | Score | 15.3 |
| Grip on LLMs - Dutch Factuality Average | 43 | Accuracy (%; mean of three GP-IRT estimates, Dutch machine t | 13.3 |
| Grip on LLMs - Dutch tinyTruthfulQA | 42 | Accuracy (%; GP-IRT estimate from 100 tinyBenchmarks items, | 13.3 |
Interactive version: theaggregate.ai/model?slug=fietje-2-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.