Typhoon (7B): benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1406 ± 30, rank #5778 of 10916 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande76.56Accuracy (%) (5-shot)49
Open LLM Leaderboard v1 - GSM8K31.61Accuracy (%) (5-shot)48.3
Open LLM Leaderboard v1 - HellaSwag81.55Normalized accuracy (%) (10-shot)45.7
Open LLM Leaderboard v1 - MMLU59.54Accuracy (%) (5-shot)45.4
HELM ThaiExam - TGAT64.62EM40.2
Open LLM Leaderboard v1 - ARC Challenge58.53Normalized accuracy (%) (25-shot)40.1
HELM ThaiExam - ONET37.65EM36.6
HELM ThaiExam - ThaiExam42.3EM36.6
HELM ThaiExam - A-Level31.5EM34.1
HELM ThaiExam - IC38.95EM32.9
HELM ThaiExam - TPAT-138.79EM25.6
Open LLM Leaderboard v1 - TruthfulQA MC240.52MC2 (%) (0-shot)14.5

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