dolphin-2.9.1-yi-1.5-34B — benchmark results

Eric Hartford's Cognitive Computations uncensored Dolphin fine-tune of Yi 1.5 34B with coding and function-calling skills. Provider: Cognitive Computations. Released 2024-05-18. Access: Open.

Unified ELO 1491 ± 25, rank #836 of 1776 rated models, from 14 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Chinese LLM - GSM8K67.93Accuracy (%)92.3
Open Chinese LLM Leaderboard68.25Average Score (%)90.7
Open Chinese LLM - C-Eval Semantic89.13Accuracy (%)90.2
Open Chinese LLM - WinoGrande68.59Accuracy (%)87.4
Open LLM Leaderboard - MuSR16.97Score87.4
Open Chinese LLM - HellaSwag67.88Accuracy (%)85.5
Open LLM Leaderboard - GPQA12.42Score85.4
Open LLM Leaderboard - BBH44.17Score84.2
Open LLM Leaderboard - MMLU-Pro39.1Score84.1
Open Chinese LLM - ARC Challenge59.3Accuracy (%)83.4
Open Chinese LLM - CMMLU69.88Accuracy (%)83.4
Open LLM Leaderboard - MATH Level 518.66Score68.6

Interactive version: theaggregate.ai/model?slug=dolphin-2-9-1-yi-1-5-34b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.