LimyQstar-7B-slerp: benchmark results

Provider: Other. Access: Open.

Unified ELO 1490 ± 19, rank #1356 of 2928 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU65.25Accuracy (%) (5-shot)83.4
Open LLM Leaderboard v1 - HellaSwag86.54Normalized accuracy (%) (10-shot)81.7
Open LLM Leaderboard v1 - WinoGrande81.85Accuracy (%) (5-shot)81
Open LLM Leaderboard v1 - ARC Challenge67.92Normalized accuracy (%) (25-shot)78.6
Open LLM Leaderboard v1 - GSM8K64.59Accuracy (%) (5-shot)78.6
Open LLM Leaderboard v1 - TruthfulQA MC261.82MC2 (%) (0-shot)78.3
Open LLM Leaderboard - MuSR41.46Score54.7
Open LLM Leaderboard - GPQA29.87Score54.5
Open LLM Leaderboard - BBH50.24Score49.3
Open LLM Leaderboard - MMLU-Pro31.03Score40.1
Open LLM Leaderboard - MATH Level 56.87Score36.9
Open LLM Leaderboard - IFEval34.91Score33.4

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