repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 8h ago
open-compass/opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%OpenAI and Broadcom announce chip designed for LLM inference at scale →
- PossiblePossibly related (embedding) · 50%Are there good closed vs open LLM rankings? Also, are 70B–350B models actually worth it? →
- PossiblePossibly related (embedding) · 50%Instead of decentralized training effort we should build the “One dataset” →
- PossiblePossibly related (embedding) · 49%OpenAI and Broadcom unveil LLM-optimized inference chip →
- PossiblePossibly related (embedding) · 47%Hypothetically speaking... →
- PossiblePossibly related (embedding) · 53%Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer →
- PossiblePossibly related (embedding) · 54%Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer - MIT Technology Review →
Covers
newsOpenAI and Broadcom announce chip designed for LLM inference at scalenewsAre there good closed vs open LLM rankings? Also, are 70B–350B models actually worth it?newsInstead of decentralized training effort we should build the “One dataset”newsOpenAI and Broadcom unveil LLM-optimized inference chipnewsHypothetically speaking...
Covers (incoming)
Related across the graph
newsOpenAI and Broadcom announce chip designed for LLM inference at scalenewsOpenAI and Broadcom unveil LLM-optimized inference chipnewsMeet GPT-Red: an LLM super-hacker OpenAI built to make its models safer - MIT Technology ReviewnewsHypothetically speaking...newsAre there good closed vs open LLM rankings? Also, are 70B–350B models actually worth it?newsMeet GPT-Red: an LLM super-hacker OpenAI built to make its models safernewsInstead of decentralized training effort we should build the “One dataset”