livecodebench.github.io 的前十大競爭對手

swebench.com

swe-bench: evaluate language models on open source software tasks

runloop.ai

Runloop introduces open benchmarks for AI coding agents, setting a new industry standard for transparency, reproducibility, and real-world evaluation.

cognition.ai

Cognition builds autonomous software engineering agents

gensyn.ai

A REE run produces two outputs: the generated text and a receipt. The receipt binds the job inputs to the job output, including the model, prompt, configuration, and generated result.

aider.chat

Aider works with LLM web chat UIs

vals.ai

GDP-weighted multimodal index

imbue.com

We rebuilt Sculptor from the ground up, thanks to your feedback. Now you can run multiple coding agents in safe containers and instantly…

iterate.ai

Read Iterate.ai’s Privacy Policy to learn how we collect, use, protect, and manage personal information, your privacy rights, data security practices, and AI governance commitments.

goodfire.ai

We found a neural mechanism that operates over manifolds: a general-purpose addition module inside Llama 3.1 8B which manipulates circular representations of numbers.