StrangeMerges_12-7B-slerp [bfloat16] [rev: 68ce0b9e6244]: benchmark results

Provider: Gille. Access: Open.

Aggregate Rating 1435 ± 34, rank #4409 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande81.69Accuracy (%) (5-shot)80.5
Open LLM Leaderboard v1 - MMLU64.94Accuracy (%) (5-shot)78.9
Open LLM Leaderboard v1 - HellaSwag85.89Normalized accuracy (%) (10-shot)77.4
Open LLM Leaderboard v1 - GSM8K63.08Accuracy (%) (5-shot)76.4
Open LLM Leaderboard v1 - ARC Challenge66.64Normalized accuracy (%) (25-shot)74.2
Open LLM Leaderboard v1 - TruthfulQA MC252.55MC2 (%) (0-shot)56.5

Interactive version: theaggregate.ai/model?slug=strangemerges-12-7b-slerp-bfloat16-rev-68ce0b9e6244 · How It Works · Data refreshed daily, snapshot 2026-11-08.