IceCoffeeTest2: benchmark results

Provider: Other.

Aggregate Rating 1445 ± 36, rank #3980 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag87.45Normalized accuracy (%) (10-shot)86.2
Open LLM Leaderboard v1 - ARC Challenge69.54Normalized accuracy (%) (25-shot)83.5
Open LLM Leaderboard v1 - TruthfulQA MC264.37MC2 (%) (0-shot)82.2
Open LLM Leaderboard v1 - WinoGrande81.29Accuracy (%) (5-shot)78.3
Open LLM Leaderboard v1 - GSM8K63.46Accuracy (%) (5-shot)76.8
Open LLM Leaderboard v1 - MMLU64.5Accuracy (%) (5-shot)71.5

Interactive version: theaggregate.ai/model?slug=icecoffeetest2 · How It Works · Data refreshed daily, snapshot 2026-11-08.