General Benchmarks
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| General Language Understanding and Reasoning | General Benchmarks MMLU, HellaSwag, OBQA, WinoGrande, ARC-C, PiQA, SciQ, LogiQA | MMLU Accuracy35.68 | 70 | |
| General Language Understanding and Reasoning | General Benchmarks MMLU, CEval, CMMLU, HumanEval, MBPP, MATH, GSM8K, MultiArith, BBH | MMLU59.3 | 18 | |
| General Multimodal Understanding | General Benchmarks | Average Score74 | 12 | |
| General Language Modeling | General Benchmarks Llama 3.1 8B | Generation Quality Score66.5 | 11 | |
| Language Modeling | General Benchmarks (C-Eval, IFEval, MATH-500, LCB, H-Swag, SST-5, CrossNER) (test) | C-Eval Score80.2 | 6 | |
| General Multimodal Reasoning | General Benchmarks | Top-1 Accuracy57.8 | 6 | |
| Natural Language Understanding and Reasoning | General Benchmarks Italian | ARC-C-it37.47 | 6 | |
| General Capability Preservation | General Benchmarks Aggregated (test) | General Capability Score76.54 | 5 | |
| General Reasoning | General Benchmarks MMLU-R, MMLU-P, GPQA | MMLU-R (multi@5 Acc)92.3 | 4 | |
| General Language Understanding | General Benchmarks (MMLU, AlpacaEval, Arena-Hard) | MMLU Accuracy73.41 | 4 | |
| General Language Evaluation | 12 general benchmarks Avg | General Average Score68.24 | 3 |
Showing 11 of 11 rows