Neural-Mistral-7B: benchmark results

Provider: Other. Access: Open.

Unified ELO 1451 ± 19, rank #1725 of 2928 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC269.26MC2 (%) (0-shot)88.7
Open LLM Leaderboard v1 - HellaSwag85.59Normalized accuracy (%) (10-shot)75.5
Open LLM Leaderboard - IFEval54.89Score66.2
Open LLM Leaderboard v1 - ARC Challenge63.4Normalized accuracy (%) (25-shot)62.6
Open LLM Leaderboard v1 - WinoGrande77.43Accuracy (%) (5-shot)55.9
Open LLM Leaderboard v1 - GSM8K37.53Accuracy (%) (5-shot)52.7
Open LLM Leaderboard v1 - MMLU60.92Accuracy (%) (5-shot)50.2
Open LLM Leaderboard - GPQA28.36Score38.5
Open LLM Leaderboard - MuSR38.73Score33.6
Open LLM Leaderboard - BBH44.28Score32.4
Open LLM Leaderboard - MMLU-Pro27.38Score29.6
Open LLM Leaderboard - MATH Level 51.89Score13.3

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