Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Large Language Model Evaluation research benchmarks – Page 2 · SOTA2 Research

Large Language Model Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Knowledge Specialized Target (test)

56.5Weighted Average Score

4

Mar 10, 2026

Code Specialized Target (test)

52.8Weighted Average Score

4

Mar 10, 2026

Math Specialized Target (test)

49.7Weighted Average Score

4

Mar 10, 2026

LLM Core Evaluation Suite GSM8K, MBPP, CEval, MMLU, ARC-C, ARC-E, CSQA, BoolQ (test)

24.72GSM8K

2

Apr 27, 2026

Multi-vendor LLM Pipeline (Confirmation pass)

-0.5Mean Quality Delta

1

May 12, 2026

RULER, LongBench-paragraph, and HumanEval-WildChat (Primary sweep)

0Mean Quality Delta

1

May 12, 2026

Page 2 of 2

Popular datasets

Llama Open LLM Leaderboard HuggingFace Open LLM Leaderboard MMLU, GSM8k, HellaSwag, WinoGrande MT-Bench

Follow for updates

Join SOTA2 Contact