Introducing the Amazon SageMaker JumpStart Model Leaderboard
Machine Learning Blog
AWS launches the SageMaker JumpStart Model Leaderboard, enabling side-by-side comparison of 70+ foundation models on quality, speed, and cost directly in SageMaker Studio.
- Compare models on three reasoning benchmarks (BIG-Bench Hard, GPQA Diamond, MMLU-Pro) evaluated consistently by AWS
- View performance metrics including time to first token, throughput, and hourly instance costs for each model
- Select use case profiles and optimization goals (Balanced, Cost optimized, Latency optimized, Throughput optimized) to see relevant metrics
- Filter by license, provider, and modality to narrow model selection before comparing scores
- Deploy models directly from the leaderboard with a few clicks using the same configuration measured
- Covers 70+ models from Meta, Google, Qwen, IBM, Arcee, and other providers
The leaderboard simplifies model selection by consolidating quality, performance, and cost data from consistent measurements, eliminating the need to compare scores from different sources.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
2026
2026
2026
2026
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.