threebird-7B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1466 ± 41, rank #2982 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K71.72Accuracy (%) (5-shot)96.5
Open LLM Leaderboard v1 - WinoGrande84.93Accuracy (%) (5-shot)96.1
Open LLM Leaderboard v1 - ARC Challenge72.44Normalized accuracy (%) (25-shot)92
Open LLM Leaderboard v1 - HellaSwag87.82Normalized accuracy (%) (10-shot)88.1
Open LLM Leaderboard v1 - TruthfulQA MC267.61MC2 (%) (0-shot)86.2
Open LLM Leaderboard v1 - MMLU65.02Accuracy (%) (5-shot)80.5

Interactive version: theaggregate.ai/model?slug=threebird-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.