Tess-XS-v1-3-yarn-128K [float16] [rev: 0f5977a5d2fa]: benchmark results

Provider: migtissera. Access: Open.

Aggregate Rating 1395 ± 33, rank #6336 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K45.19Accuracy (%) (5-shot)59.3
Open LLM Leaderboard v1 - HellaSwag82.95Normalized accuracy (%) (10-shot)54.9
Open LLM Leaderboard v1 - MMLU62.15Accuracy (%) (5-shot)54.2
Open LLM Leaderboard v1 - ARC Challenge61.09Normalized accuracy (%) (25-shot)51.2
Open LLM Leaderboard v1 - TruthfulQA MC250.13MC2 (%) (0-shot)47.2
Open LLM Leaderboard v1 - WinoGrande74.43Accuracy (%) (5-shot)36.5

Interactive version: theaggregate.ai/model?slug=tess-xs-v1-3-yarn-128k-float16-rev-0f5977a5d2fa · How It Works · Data refreshed daily, snapshot 2026-11-08.