MMLU-by-task - Abstract Algebra Leaderboard — The Aggregate

MMLU-by-task - Abstract Algebra — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.

Top models

#	Model	Score
1	trurl-2-13B-academic	39
2	MythoMax-L2-13B	37
3	Llama 2 70B Chat	36
4	CodeLlama-34B-Instruct-hf	36
5	Llama 2 70B Chat (HF)	35
6	LLaMA-30B	35
7	Phi-1.5	34
8	CodeLlama-34B-hf	34
9	LongChat-7B-v1.5-32k	34
10	Llama 2 70B Base	33
11	CodeLlama-7B-Instruct-hf	33
12	CodeLlama-7B-hf	33
13	mpt-30B Instruct	33
14	vicuna-33B-v1.3	33
15	internlm-20B Chat	33

Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-abstract-algebra · How the rankings work · Data refreshed daily, snapshot 2026-07-22.