OpenEval - IMDb — leaderboard

Metric: Exact Match (%). Source: huggingface.co. 22 models tracked.

Top models

#ModelScore
1mpt-30B95.74
2LLaMA-65B95.51
3falcon-40B95.45
4Llama 2 13B95.17
5falcon-40B Instruct94.89
6LLaMA-30B94.6
7Llama 2 70B94.6
8RedPajama-INCITE-Base-3B-v194.03
9LLaMA-7B93.47
10Llama 2 7B93.18
11pythia-6.9B93.18
12LLaMA-13B91.76
13falcon-7B Instruct91.48
14RedPajama-INCITE-Instruct-3B-v191.48
15falcon-7B89.2

Interactive version: theaggregate.ai/benchmark?slug=openeval-imdb · How the rankings work · Data refreshed daily, snapshot 2026-07-22.