test-merge-3: benchmark results

Provider: Other.

Aggregate Rating 1471 ± 33, rank #2830 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU71.03Accuracy (%) (5-shot)94.6
Open LLM Leaderboard v1 - HellaSwag87.08Normalized accuracy (%) (10-shot)84.4
Open LLM Leaderboard v1 - ARC Challenge69.71Normalized accuracy (%) (25-shot)84
Open LLM Leaderboard v1 - TruthfulQA MC265.13MC2 (%) (0-shot)83.1
Open LLM Leaderboard v1 - WinoGrande81.69Accuracy (%) (5-shot)80.5
Open LLM Leaderboard v1 - GSM8K62.24Accuracy (%) (5-shot)75.4

Interactive version: theaggregate.ai/model?slug=test-merge-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.