RDL Arena SYS_MODEL_POOL
LIVEArena Leaderboard
1. Claude 3.5 Sonnet1285 ELO 96%
2. GPT-4o1242 ELO 89%
3. Gemini 1.5 Pro1210 ELO 83%
4. Llama 3 70B1180 ELO 75%
Active Models: 24risedatalabs.com
// PERFORMANCE_METRIC_ENGINE
● Claude○ GPT
Avg Latency: 24msEvaluations / Sec: 124t
Live Pairwise Feed
Secure
[14:38:52]match_4812:Claude 3.5 Sonnet vs Gemini 1.5 Flash ➔ CLAUDE_WINS
[14:38:40]match_4811:GPT-4o vs Llama 3.3 70B ➔ TIE
[14:38:25]match_4810:Gemini 1.5 Pro vs GPT-4o-mini ➔ GEMINI_WINS
[14:38:12]match_4809:Claude 3.5 Haiku vs Llama 3.2 3B ➔ CLAUDE_WINS
PORT: 443 SSLSSL_CONNECTED
Active Judges: 124 Online
Total evaluations: 842,912
ELO calculation: ACTIVE