SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone

Nishant Subramani, Alfredo Gomez, Mona T. Diab


Abstract
Modern language models are evaluated on large benchmarks, which are difficult to make sense of, especially for model selection.Looking at the raw evaluation numbers themselves using a model-centric lens, we propose SimBA, a three phase framework to Simplify Benchmark Analysis. The three phases of SimBA are: stalk, where we conduct dataset & model comparisons, prowl, where we discover a representative subset, and pounce, where we use the representative subset to predict performance on a held-out set of models. Applying SimBA to three popular LM benchmarks: HELM, MMLU, and BigBenchLite reveals that across all three benchmarks, datasets and models relate strongly to one another (stalk). We develop an representative set discovery algorithm which covers a benchmark using raw evaluation scores alone. Using our algorithm, we find that with 6.25% (1/16), 1.7% (1/58), and 28.4% (21/74) of the datasets for HELM, MMLU, and BigBenchLite respectively, we achieve coverage levels of at least 95% (prowl). Additionally, using just these representative subsets, we can both preserve model ranks and predict performance on a held-out set of models with near zero mean-squared error (pounce). Taken together, SimBA can help model developers improve efficiency during model training and dataset creators validate whether their newly created dataset differs from existing datasets in a benchmark. Our code is open source, available at https://github.com/nishantsubramani/simba.
Anthology ID:
2025.findings-emnlp.711
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13220–13233
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.711/
DOI:
Bibkey:
Cite (ACL):
Nishant Subramani, Alfredo Gomez, and Mona T. Diab. 2025. SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 13220–13233, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone (Subramani et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.711.pdf
Checklist:
 2025.findings-emnlp.711.checklist.pdf