Shlepa - Movies MC (RU): leaderboard

The Movies multiple-choice track of Shlepa — Russian-language questions about film; accuracy (%).

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

Top models

#ModelScoreOverall rank
1Gemma 2 9B50.46#958
2Phi-3-medium-4k-instruct42.82#952
3Starling-LM-7B-beta38.66#1093
4suzume-llama-3-8B-multilingual32.87#1084
5Llama 3 8B SFR Iterative DPO R30.56#1109
6Llama 2 7B Base7.18#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-movies-mc-ru · How It Works · Data refreshed daily, snapshot 2026-10-20.