"Reflection 70B holds its own against even the top closed-source models (Claude 3.5 Sonnet, GPT-4o).
It’s the top LLM in (at least) MMLU, MATH, IFEval, GSM8K.
Beats GPT-4o on every benchmark tested.
It clobbers Llama 3.1 405B. It’s not even close.
The technique that drives Reflection 70B is simple, but very powerful.
Current LLMs have a tendency to hallucinate, and can’t recognize when they do so.
Reflection-Tuning enables LLMs to recognize their mistakes, and then correct them before committing to an answer.
Additionally, we separate planning into a separate step, improving CoT potency and keeping the outputs simple and concise for end users.
Important to note: We have checked for decontamination against all benchmarks mentioned using @lmsysorg’s LLM Decontaminator.
The weights of our 70B model are available today on @huggingface here: https://huggingface.co/mattshumer/Reflection-70B
@hyperbolic_labs API available later today.
Next week, we will release the weights of Reflection-405B, along with a short report going into more detail on our process and findings.
Most importantly, a huge shoutout to @csahil28 and @GlaiveAI.
I’ve been noodling on this idea for months, and finally decided to pull the trigger a few weeks ago. I reached out to Sahil and the data was generated within hours.
If you’re training models, check Glaive out.
This model is quite fun to use and insanely powerful.
Please check it out — with the right prompting, it’s an absolute beast for many use-cases.
Demo here: https://reflection-playground-production.up.railway.app/
405B is coming next week, and we expect it to outperform Sonnet and GPT-4o by a wide margin.
But this is just the start. I have a few more tricks up my sleeve.
I’ll continue to work with @csahil28 to release even better LLMs that make this one look like a toy.
Stay tuned."