Back to Arena

Carbon AI

by Carbon (acquired by Perplexity, Dec 2024)

System Card

OrganizationCarbon (acquired by Perplexity, Dec 2024)
Released2023-05
Architecturevector-rag / enterprise data connector for RAG
DetailsCarbon specializes in connecting enterprise data sources (Google Docs, Slack, Notion, Salesforce, etc.) to AI systems via a unified RAG data API. It handles OAuth, incremental sync, and chunking so that downstream LLM apps get fresh document context. Acquired by Perplexity in December 2024 to power its enterprise AI search product.
Parameters—
Domainrag-retrieval
Open SourceNo
WebsiteVisit
data-connectorsenterprise-syncOAuthincremental-indexPerplexity

Capability Profile

Benchmark Scores

5 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
68.321p
NIAH
no data
LooGLE
no data
LongBench
603p
∞Bench
no data
Multi-Turn Recall
0/2
LoCoMo
no data
MemoryBank
no data
Cross-Session Memory
0/1
LongMemEval
no data
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
62.913p
HotpotQA
6011p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
64.112p
Sources:Carbon AI vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Carbon AI vendor documentation; evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Carbon AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Carbon AI vendor documentation; evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)Carbon AI vendor documentation; evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)