Benchmarks
Public benchmarks ranking AI models by Elo and scoring them on behavioral dimensions including bluffing, lying, negotiation, and consistency over long games.
Where it ranks
Current edition · updated Oct 20, 2026What it does
Public benchmarks ranking AI models by Elo and scoring them on behavioral dimensions including bluffing, lying, negotiation, and consistency over long games.
- Social intelligence evaluation of AI models
- Pre-deployment behavioral evaluations of AI models
- Multi-agent cooperation, deception, and negotiation testing
- Category
- AI evaluation and observability
- Users
- AI safety researchers, alignment researchers
- Public API
- Not offered
Not yet disclosed: deployment options, platforms, languages and support channels.
Pricing
- Free plan$0
Prices as published by Olam Labs, checked Oct 2026.
Security and compliance
No security details published yet
Olam Labs hasn't published certifications or security practices for Benchmarks that we could find. Ask their team for audit reports.
Reviews
No reviews yet
Reviews come from people who use Benchmarks at work. Share how your team uses it to help other buyers decide.
Alternatives
See the full rankingSimulation testing and evals platform for voice and chat AI agents.
#1 in Evaluate AI systems
A cloud-based business application that captures sessions from MCP servers, Claude Connectors, and ChatGPT Apps via SDKs for TypeScript, Python, and Go.
#2 in Evaluate AI systems
Superagent Red Teaming
by Superagent
Automated adversarial testing service that deploys specialized attack agents against production AI systems to surface vulnerabilities.
#3 in Evaluate AI systems
AI Red Teaming
by DeepKeep
Adaptive evaluation and robustness tests.
#5 in Evaluate AI systems
Vending-Bench 2
by Andon Labs Inc.
Benchmark where AI models manage a simulated vending machine business for a full year, navigating adversarial suppliers, negotiations, and customer complaints.
#6 in Evaluate AI systems
Is this your product?
Claim it to keep details accurate and submit evidence for the next ranking review.
Claim Benchmarks