New model InternLM outperforms ChatGPT on exams designed for humans

Abstract of the technical report:

We present InternLM, a multilingual foundational language model with 104B parameters. InternLM is pre-trained on a large corpora with 1.6T tokens with a multi-phase progressive process, and then fine-tuned to align with human preferences. We also developed a training system called Uniscale-LLM for efficient large language model training. The evaluation on a number of benchmarks shows that InternLM achieves state-of-the-art performance in multiple aspects, including knowledge understanding, reading comprehension, mathematics, and coding. With such well-rounded capabilities, InternLM achieves outstanding performances on comprehensive exams, including MMLU, AGIEval, C-Eval and GAOKAO-Bench, without resorting to external tools. On these benchmarks, InternLM not only significantly outperforms open-source models, but also obtains superior performance compared to ChatGPT. Also, InternLM demonstrates excellent capability of understanding Chinese language and Chinese culture, which makes it a suitable foundation model to support Chinese-oriented language applications. This manuscript gives a detailed study of our results, with benchmarks and examples across a diverse set of knowledge domains and tasks.

A bit apples to oranges, as they compare against raw LLaMA 65B, not the instruction tuned variants, or the now SOTA finetuned Falcon 40B[1].

1: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderb...

Still, a competitive multilingual model is very cool.