AI BriefingBaidu ERNIE 5.1 Ranks 4th in AI Search
·2026.05.10 18:18
Key point
Baidu's ERNIE 5.1 surpassed Gemini 3.1 Pro to rank 4th on the Search Arena leaderboard.
1 / 2
Details
Baidu's ERNIE 5.1 demonstrated strong performance by entering the top ranks of the Search Arena global leaderboard, an independent evaluation platform.
Key Benchmark Results:
- Search Arena: ERNIE 5.1 recorded 1,223 Elo, ranking 4th. This figure surpasses Gemini 3.1 Pro (with Grounding) and GPT-5.4 Search. Currently, 1st place is held by Claude Opus 4.6 Search (1,255 Elo), and 2nd place by GPT-5.5 Search (1,242 Elo).
- Text Arena: ERNIE 5.1 Preview recorded 1,476 Elo, ranking 13th globally.
These results suggest that Baidu's models, which had largely been overlooked in Western AI coverage, have reached a level on par with leading global models in actual search and reasoning capabilities.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Step 5 Preview Released: 600B Parameter MoE Model Highlights Agentic Tasks and Financial Analysis PerformanceQwen3.5-based Small Decision Model 'Kev' Released with TypeSafe API Compatibility and Performance Metrics