MAVEN-Bench: leaderboard
Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language models achieve strong results on individual benchmarks, their ability to compose reasoning strategies, preserve intermediate states, and coordinate tools across domains remains underexplored. We present MAVEN (Modular Agentic Verification and Execution
Metric: Acc. (%) (self-reported). Source: benchmarklist.com. Saturation forecast: Not forecast. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 70 | #142 |
| 2 | Kimi K2 | 57 | #243 |
| 3 | Grok 4 | 55 | #181 |
| 4 | GPT-OSS-120B | 48 | #341 |
| 5 | GLM-4.5 | 43 | #275 |
| 6 | O4 Mini | 38 | #180 |
| 7 | GPT-5 | 32 | #98 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=maven-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.