#LMArena

71 stories · 9 in 7 days · 40 in 30 days
Stories, products and papers tagged "LMArena", newest first.
Nov 7
Nov 6
Nov 5
Nov 3
Oct 31
Oct 28
Oct 20
Oct 19
Oct 18
ModelsBuildersSelected00:08
Arena Launches Alignment Index Built From 90K+ Agent Sessions

Agent rankings so far have focused on capability benchmarks; this index instead scores whether agents overstep instructions, misattribute evidence or falsely claim success, which maps directly to production reliability and incident risk. Teams deploying agents can use the three signal categories as a checklist for their own evaluations before rollout. The public leaderboard makes it possible to compare specific model candidates on safety-of-behaviour rather than raw benchmark scores.

lmarena.ai@lmarena_aiSource
Oct 17
Oct 16
Oct 14
Oct 13
Oct 11
Oct 9
PapersBuildersMulti-sourceSelected00:46
Arena study finds GPT-6 Luna and Astra misattribute user statements

False attribution matters more than raw accuracy for agent deployments, because a model that invents user consent or intent can trigger actions the user never authorised. Teams building approval-gated agents, audit logging or compliance workflows should test for this failure mode separately from hallucination benchmarks, since the two do not track together across the GPT-6 family.

Event
lmarena.ai@lmarena_ai11 sourcesSource