Dolphin3.0-Llama3.2-1B — benchmark results

Provider: Cognitive Computations. Released 2024-12-29. Access: Open.

Unified ELO 1236 ± 70, rank #1651 of 1776 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - IFEval54.28Score65.3
UGI - Willingness (W/10)3.2W/10 Score24.1
Open LLM Leaderboard - MATH Level 52.79Score17.8
Open LLM Leaderboard - MMLU-Pro4.17Score11.6
Open LLM Leaderboard - BBH4.66Score9.1
UGI - Writing14.56Writing Score5.7
UGI Leaderboard15.18UGI Score5.6
Open LLM Leaderboard - GPQA0Score2.6
Open LLM Leaderboard - MuSR0.94Score1.6
UGI - Natural Intelligence4.29NatInt Score0.8

Interactive version: theaggregate.ai/model?slug=dolphin3-0-llama3-2-1b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.