ML Benchmarks & Leaderboards

Compare AI models across standardized benchmarks. Find the best models for your use case.

2 live5 coming soon
Conversational AILive

Chatbot Quality

Chatbot Quality Monitoring

Purpose-driven metrics for monitoring chatbot quality. Response accuracy, hallucination rates, and domain-specific evaluation.

8+ modelsCustom datasets
Text EmbeddingsLive

MTEB

Massive Text Embedding Benchmark

Compare embedding models across retrieval, classification, clustering, and semantic similarity.

2000+ models56 datasets
Information RetrievalComing Soon

BEIR

Benchmarking Information Retrieval

Zero-shot evaluation of retrieval models across 18 diverse datasets.

100+ models18 datasets
Image ClassificationComing Soon

ImageNet

ImageNet Classification

The standard benchmark for image classification models.

800+ models1 datasets
Object DetectionComing Soon

COCO

Common Objects in Context

Object detection, segmentation, and captioning benchmarks.

500+ models1 datasets
Speech RecognitionComing Soon

LibriSpeech

LibriSpeech ASR

Standard benchmark for automatic speech recognition (ASR) models.

200+ models1 datasets
Language ModelsComing Soon

MMLU

Massive Multitask Language Understanding

Test LLMs across 57 academic subjects from STEM to humanities.

100+ models57 datasets

Missing a benchmark?

Let us know which benchmarks you'd like to see on CodeSOTA. We prioritize based on user demand.

Request a Benchmark