Agent Arena
Benchmark AI models on real agent work
A platform that ranks AI models using outcomes from real agentic sessions, including leaderboard and token-efficiency comparisons.
Recent stories
Vals reports Kimi K3.1 Pro completes Terminal-Bench 4 runs roughly four times faster than K3 at a third of the cost, but regresses on legal and tax tasks. Agent Arena places it eleventh with a $1.03 median task cost.
A benchmark author says OpenRouter likely routed GLM-5.3-Flash requests to quantized endpoints because precision was not pinned. Twelve reruns using pinned FP8 and self-hosted inference improved results, suggesting earlier scores may have reflected routing.
Agent Arena says Claude Opus 5 Max placed second and Opus 5 High placed third across more than 7,000 real agentic sessions. Practitioner reports remain mixed across harnesses and prompting styles.