Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning
Open paper
Benchmark
Model
Rank
Results
code-generation-on-livecodebench-v5
Apriel-1.5-OpenReasoner
#4
Pass@1: 70.8
multi-task-language-understanding-on-mmlu-pro
Apriel-1.5-OpenReasoner
#50
Accuracy: 77.3
Rank counts only results with a code link.