DarkForest-20B-v1.2: benchmark results

Provider: Other.

Aggregate Rating 1394 ± 34, rank #6367 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag86.42Normalized accuracy (%) (10-shot)80.9
Open LLM Leaderboard v1 - TruthfulQA MC256.31MC2 (%) (0-shot)67.6
Open LLM Leaderboard v1 - ARC Challenge63.57Normalized accuracy (%) (25-shot)63.3
Open LLM Leaderboard v1 - WinoGrande77.74Accuracy (%) (5-shot)58.2
Open LLM Leaderboard v1 - MMLU59.77Accuracy (%) (5-shot)45.8
Open LLM Leaderboard v1 - GSM8K24.94Accuracy (%) (5-shot)43.8

Interactive version: theaggregate.ai/model?slug=darkforest-20b-v1-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.