shisa-base-7B-v1: benchmark results

Provider: Other. Access: Open.

Unified ELO 1386 ± 31, rank #2242 of 2928 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande78.53Accuracy (%) (5-shot)63.8
Open LLM Leaderboard v1 - GSM8K35.86Accuracy (%) (5-shot)51.4
Open LLM Leaderboard v1 - HellaSwag77.63Normalized accuracy (%) (10-shot)31.4
Open LLM Leaderboard v1 - ARC Challenge52.3Normalized accuracy (%) (25-shot)27
Open LLM Leaderboard v1 - TruthfulQA MC242.4MC2 (%) (0-shot)20.4
pfgen-bench - Completion Mode - Helpfulness0.03Helpfulness Score19.8
pfgen-bench - Completion Mode - Score0.3pfgen Score (mean of three)16
pfgen-bench - Completion Mode - Truthfulness0.48Truthfulness Score15.8
pfgen-bench - Completion Mode - Fluency0.38Fluency Score15
Open LLM Leaderboard v1 - MMLU23.12Accuracy (%) (5-shot)1

Interactive version: theaggregate.ai/model?slug=shisa-base-7b-v1 · How It Works · Data refreshed daily, snapshot 2026-09-23.