Benchmark Almanac

MCINext

We track 6 benchmarks that MCINext made or helped make.

0 in use 4 with public code 6 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
Persian NLG Models summarize Persian texts, translate between Persian and two other languages, and write questions from passages. Translation May 2025 20.1 Not in cards
Persian IFEval Models respond to 457 Persian prompts while following constraints on wording, length, or structure. Chat and instructions in many languages May 2025 92.6% Not in cards
MIZAN: A Persian LLM Leaderboard Models answer questions, complete sentences, follow instructions, and hold conversations in Persian. The leaderboard averages six task scores. Knowledge in many languages May 2025 0.75 Not in cards
PerCoR Models read the beginning of a Persian passage and choose its original ending from four options. Reasoning in many languages May 2025 94.3% Not in cards
PerMMLU Models answer Persian multiple-choice questions from school curricula, university entrance exams, and Iranian cultural sources. Knowledge in many languages May 2025 84% Not in cards
Persian MT-Bench Models follow Persian conversations across two to four turns. One asks for film directors, then actors, then the oldest and newest films. Chat and instructions in many languages May 2025 9 Not in cards