StarlingMaths-12B-MoE: benchmark results

Provider: Other.

Aggregate Rating 1454 ± 37, rank #3620 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K70.36Accuracy (%) (5-shot)92.7
Open LLM Leaderboard v1 - TruthfulQA MC268.95MC2 (%) (0-shot)88.3
Open LLM Leaderboard v1 - ARC Challenge70.14Normalized accuracy (%) (25-shot)85.2
Open LLM Leaderboard v1 - HellaSwag87.05Normalized accuracy (%) (10-shot)84.3
Open LLM Leaderboard v1 - MMLU65.23Accuracy (%) (5-shot)83.2
Open LLM Leaderboard v1 - WinoGrande82.16Accuracy (%) (5-shot)82.7

Interactive version: theaggregate.ai/model?slug=starlingmaths-12b-moe · How It Works · Data refreshed daily, snapshot 2026-11-08.