MMLU-by-task - Abstract Algebra: leaderboard
The "Abstract Algebra" subtask of MMLU-by-task. A single MMLU subject, reporting per-task multiple-choice accuracy from the MMLU-by-task leaderboard across a wide range of academic and professional domains.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 1257 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | trurl-2-13B-academic | 39 | #1413 |
| 2 | MythoMax-L2-13B | 37 | #1409 |
| 3 | Llama 2 70B Chat | 36 | #1237 |
| 4 | Llama 2 70B Chat (HF) | 35 | #1264 |
| 5 | Phi-1.5 | 34 | #1549 |
| 6 | CodeLlama-34B-hf | 34 | #1515 |
| 7 | MPT-30B-Chat | 34 | #1451 |
| 8 | LongChat-7B-v1.5-32k | 34 | #1519 |
| 9 | WizardCoder-15B-V1.0 | 34 | #1588 |
| 10 | Llama 2 70B Base | 33 | #1025 |
| 11 | mpt-30B Instruct | 33 | #1470 |
| 12 | CodeLlama-7B-Instruct-hf | 33 | #1545 |
| 13 | vicuna-33B-v1.3 | 33 | #1347 |
| 14 | Llama 2 7B 32K Instruct | 33 | #1508 |
| 15 | Xwin-LM-70B-V0.1 | 33 | #982 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-abstract-algebra · How It Works · Data refreshed daily, snapshot 2026-10-20.