Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models

TL;DR

Reka introduces a series of multimodal language models, including Reka Core, Flash, and Edge, that process text, images, video, and audio, achieving state-of-the-art results and outperforming larger models across various benchmarks.

Contribution

The paper presents Reka's new multimodal models that outperform larger models and set new state-of-the-art results across multiple tasks and benchmarks.

Findings

Reka Edge and Flash outperform larger models in their compute class.

Reka Core approaches the best frontier models on evaluations and human assessments.

Reka Core outperforms GPT-4-0613 on human evaluation and Gemini Ultra on video QA.

Abstract

We introduce Reka Core, Flash, and Edge, a series of powerful multimodal language models trained from scratch by Reka. Reka models are able to process and reason with text, images, video, and audio inputs. This technical report discusses details of training some of these models and provides comprehensive evaluation results. We show that Reka Edge and Reka Flash are not only state-of-the-art but also outperform many much larger models, delivering outsized values for their respective compute class. Meanwhile, our most capable and largest model, Reka Core, approaches the best frontier models on both automatic evaluations and blind human evaluations. On image question answering benchmarks (e.g. MMMU, VQAv2), Core performs competitively to GPT4-V. Meanwhile, on multimodal chat, Core ranks as the second most preferred model under a blind third-party human evaluation setup, outperforming other models such as Claude 3 Opus. On text benchmarks, Core not only performs competitively to other frontier models on a set of well-established benchmarks (e.g. MMLU, GSM8K) but also outperforms GPT4-0613 on human evaluation. On video question answering (Perception-Test), Core outperforms Gemini Ultra. Models are shipped in production at http://chat.reka.ai . A showcase of non cherry picked qualitative examples can also be found at http://showcase.reka.ai .