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

Autonomous LLM Fine-tuning research benchmarks · SOTA2 Research

Autonomous LLM Fine-tuning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Qwen3-235B-2507

51.2Hybrid Score

4

Apr 16, 2026

Qwen3-235B-2507

72.2Accuracy

4

Apr 16, 2026

Qwen3-235B-2507

46.9Accuracy

4

Apr 16, 2026

97.2Accuracy

4

Apr 16, 2026

Qwen3-235B-2507

83.3Accuracy

4

Apr 16, 2026

Qwen3-235B-2507

85.3Accuracy

4

Apr 16, 2026

89.7Macro-F1

4

Apr 16, 2026

48.4oMeScore

4

Apr 16, 2026

68.1Validation Score

4

Apr 16, 2026

50.2Rouge-1

4

Apr 16, 2026

Popular datasets

SST HoC GTA ACI-BENCH LawBench

Follow for updates

Join SOTA2 Contact