Agent Arena: long-horizon, hundreds-of-turns tasks expose a 55-minute gap between top models
arena · x · 2026-11-05
LMArena's Agent Arena measures complex, real-world tasks, and the data shows long-horizon sessions amplify differences between frontier models. Tasks span hundreds of turns — porting a codebase to Rust, auditing an investment strategy document, writing a math textbook, and more. Comparing the top model from each of the 5 leading labs reveals a roughly 55-minute gap. Full comparisons at lmarena.ai's Agent Arena.
Related event: Agent Arena Long-Horizon Tests Show 55-Minute Gap Between Top Models(2 posts)→
More from Models
- Hamel Husain: Model benchmark marketing is often disingenuous vs reality — sarahcat21 · 2026-11-05
- Cognition launches SWE-2 Flash, a 276B-A12B coding model that beats all US open-weight rivals — carlesgelada · 2026-11-05
- Kimi K3.1 Pro (2.8T params, 104B active) lands on Ollama Cloud with zero data retention — ollama · 2026-11-05
- Linear CEO Karri Saarinen: time to retire the word "context" in AI — round · 2026-11-05
- Codex on the $20 plan runs dry after about 2.5-3 hours of nonstop work — tristanbob · 2026-11-05
- Morph launches Reflex: first decision model with cached pricing, 10-20x cheaper than Jev — GabGarrett · 2026-11-05