TheAgentCompany — raw "AgentCompany"=casing-normalized form of the known TheAgentCompany benchmark
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 4.5 | Anthropic | 41 | 1 | 2026-06-06 |
| 2 | Gemini 2.5 Pro | 39.3 | 1 | 2026-06-06 | |
| 3 | Claude Sonnet 4 | Anthropic | 37 | 1 | 2026-06-06 |
| 4 | MiniMax M2 | MiniMax | 36 | 1 | 2026-06-06 |
| 5 | GLM-4.6 | Z.ai | 35 | 1 | 2026-06-06 |
| 6 | DeepSeek-V3.2 | DeepSeek | 34 | 1 | 2026-06-06 |
| 7 | Kimi K2 (Reasoning) | Moonshot | 30 | 1 | 2026-06-06 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.