MBPP+
AssessTools
An improved programming benchmark for evaluating code-writing models.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 8Hugging Face Blog·4/21/2026researchQIMMA: a quality-first Arabic LLM leaderboard
QIMMA is a new Arabic large language model leaderboard that validates benchmark quality before evaluating models. It consolidates 109 subsets from 14 benchmarks into a suite of more than 52,000 samples across seven domains, including cultural, STEM, legal, medical, safety, poetry, and coding tasks. The project also releases public per-sample outputs and includes Arabic-adapted code evaluation.