Back to Arena

Athina AI

by Athina AI (YC W23)

System Card

OrganizationAthina AI (YC W23)
Released2023-01
Architectureagentic-workflow / LLM evaluation and production monitoring
DetailsAthina AI is an evaluation and monitoring platform offering 50+ preset evaluations (hallucination, context relevance, groundedness, toxicity) from multiple providers (OpenAI, Ragas, Guardrails). It supports SOC-2-compliant VPC deployment for enterprise customers. Provides both pre-deployment testing and production monitoring with real-time alerting on regression. Raised $4.1M total.
Parameters—
Domainrag-retrievalagent-memory
Open SourceNo
WebsiteVisit
eval-frameworkhallucination-detectionSOC2production-monitoring50-evals

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Long-Context Retrieval
1/5
RULER
no data
NIAH
no data
LooGLE
no data
LongBench
603p
∞Bench
no data
Multi-Turn Recall
1/2
LoCoMo
77.268p
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
78.366p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
7579p
HotpotQA
77.788p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Athina AI vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Athina AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Athina AI vendor documentation; evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Athina AI vendor documentation; evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Athina AI vendor documentation; evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Athina AI vendor documentation; evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)