dolphin-2.9.4-llama3.1-8B — benchmark results

Provider: Cognitive Computations. Released 2024-08-04. Access: Open.

Unified ELO 1137 ± 58, rank #1749 of 1776 rated models, from 7 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - IFEval27.57Score24.6
Open LLM Leaderboard - BBH8.97Score18.8
Open LLM Leaderboard - GPQA1.79Score17.3
Open LLM Leaderboard - MMLU-Pro2.63Score10.2
Open LLM Leaderboard - MATH Level 51.21Score8.7
Open Korean LLM Leaderboard28.07Average Score (%)5.6
Open LLM Leaderboard - MuSR0.62Score0.4

Interactive version: theaggregate.ai/model?slug=dolphin-2-9-4-llama3-1-8b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.