Search Scenario Factuality Rankings Updated
arena · x · 2026-07-16
Arena provided an update on the factuality leaderboard changes in Search Arena.
- With factuality enabled, GPT-5.5-search climbed to the top spot.
- GPT-5.2-search saw a more significant leap, moving from #11 to #3.
- claude-sonnet-4-6-search dropped from #6 to #9, and gemini-3.1-pro-grounding fell from #7 to #13.
- They also noted that while some open-source models saw score declines when factuality weights were increased, mistral-medium-3.5 and tencent huyuan-hy3-preview actually moved up.
Related event: Arena Adds Factuality to Model Rankings(12 posts)→
More from Models
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11