speechless-mistral-dolphin-orca-platypus-samantha-7B: benchmark results

Provider: Other. Access: Open.

Unified ELO 1457 ± 20, rank #1662 of 2928 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MuSR43.61Score75.2
Open LLM Leaderboard v1 - ARC Challenge64.33Normalized accuracy (%) (25-shot)66.2
Open LLM Leaderboard v1 - HellaSwag84.4Normalized accuracy (%) (10-shot)65.8
Open LLM Leaderboard v1 - MMLU63.72Accuracy (%) (5-shot)62.8
Open LLM Leaderboard v1 - WinoGrande78.37Accuracy (%) (5-shot)62.7
Open LLM Leaderboard v1 - TruthfulQA MC252.52MC2 (%) (0-shot)56.4
Open LLM Leaderboard - BBH49.83Score47.7
Open LLM Leaderboard v1 - GSM8K21.38Accuracy (%) (5-shot)41.9
Open LLM Leaderboard - GPQA28.36Score38.5
Open LLM Leaderboard - MMLU-Pro29.9Score35.9
Open LLM Leaderboard - IFEval37Score35.8
Open LLM Leaderboard - MATH Level 52.95Score18.6

Interactive version: theaggregate.ai/model?slug=speechless-mistral-dolphin-orca-platypus-samantha-7b · How It Works · Data refreshed daily, snapshot 2026-09-23.