test-merge: benchmark results

Provider: vicgalle. Access: Open.

Aggregate Rating 1389 ± 33, rank #6559 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC256.25MC2 (%) (0-shot)67.5
Open LLM Leaderboard v1 - GSM8K49.05Accuracy (%) (5-shot)62
Open LLM Leaderboard v1 - HellaSwag82.29Normalized accuracy (%) (10-shot)50.1
Open LLM Leaderboard v1 - ARC Challenge60.58Normalized accuracy (%) (25-shot)48.4
Open LLM Leaderboard v1 - WinoGrande76.4Accuracy (%) (5-shot)48
Open LLM Leaderboard v1 - MMLU59.38Accuracy (%) (5-shot)45

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