mixtralmerge-8x7B-rebalanced-test: benchmark results

Provider: chargoddard. Access: Open.

Aggregate Rating 1458 ± 33, rank #3429 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU70.47Accuracy (%) (5-shot)94
Open LLM Leaderboard v1 - ARC Challenge68.17Normalized accuracy (%) (25-shot)79.6
Open LLM Leaderboard v1 - WinoGrande81.29Accuracy (%) (5-shot)78.3
Open LLM Leaderboard v1 - HellaSwag85.76Normalized accuracy (%) (10-shot)76.6
Open LLM Leaderboard v1 - GSM8K58.23Accuracy (%) (5-shot)69.9
Open LLM Leaderboard v1 - TruthfulQA MC253.75MC2 (%) (0-shot)60.6

Interactive version: theaggregate.ai/model?slug=mixtralmerge-8x7b-rebalanced-test · How It Works · Data refreshed daily, snapshot 2026-11-08.