Subquadratic LLM Leaderboard — leaderboard

Benchmark for non-transformer architectures (RWKV, Mamba, SSMs): evaluates subquadratic-attention models across ARC, HellaSwag, MMLU, TruthfulQA, WinoGrande, and GSM8K.

Metric: Average Score. Source: huggingface.co. 39 models tracked.

Top models

#ModelScore
1v5-EagleX-v2-7B-HF48.66
2EagleX_1-7T_Chat47.36
3EagleX_1-7T46.84
4Hermes-RWKV-v5-7B46.42
5rwkv-5-world-7b45.15
6bagel-dpo-2.8b-v0.243.89
7bagel-2.8b-v0.243.47
8rwkv-raven-14b42.09
9Hermes-mamba-2.8b-slimpj-cDPO41.77
10Hermes-mamba-2.8b-slimpj41.65

Interactive version: theaggregate.ai/benchmark?slug=subquadratic-llm-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.