Shlepa - Books MC (RU): leaderboard

The Books multiple-choice track of Shlepa — Russian-language questions about books and literature; accuracy (%).

Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 18 models tracked.

Top models

#ModelScoreOverall rank
1Phi-3-medium-4k-instruct38.17#952
2Gemma 2 9B33.61#958
3Starling-LM-7B-beta30.71#1093
4suzume-llama-3-8B-multilingual29.67#1084
5Llama 3 8B SFR Iterative DPO R26.14#1109
6Llama 2 7B Base10.79#1518

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=shlepa-books-mc-ru · How It Works · Data refreshed daily, snapshot 2026-10-20.