🌐 LLM Leaderboard Debut 🌐
First-ever rankings are in! Fresh faces dominate across the board:
#ChatbotArena: #Gemini2_5_Pro claims pole position (1439.0), edging out #Llama4_Maverick and #ChatGPT4o.
#LiveBench: #Gemini2_5_Pro dominates with 77.43, leaving rivals in its token dust.
#SimpleBench: #Gemini2_5 flexes a 51.6% win rate, overshadowing #Claude3_7_Sonnet’s double entry.
#SWE_Bench: #AugmentAgent codes its way to the top (65.4), out-patching the competition.
Full Standings-
=== Chatbot Arena Leaderboard ===
1. Gemini-2.5-Pro-Exp-03-25 - 1439.0
2. Llama-4-Maverick-03-26-Experimental - 1417.0
3. ChatGPT-4o-latest (2025-03-26) - 1410.0
4. Grok-3-Preview-02-24 - 1403.0
5. chocolate (Early Grok-3) - 1402.0
=== LiveBench Leaderboard ===
1. Gemini 2.5 Pro Experimental - 77.43
2. o1 High - 72.18
3. o3 Mini High - 71.37
4. Claude 3.7 Sonnet Thinking - 70.57
5. DeepSeek R1 - 67.47
=== SimpleBench Leaderboard ===
1. Gemini 2.5 - 51.6%
2. Claude 3.7 Sonnet (thinking) - 46.4%
3. Claude 3.7 Sonnet - 44.9%
4. o1-preview - 41.7%
5. Claude 3.5 Sonnet 10-22 - 41.4%
=== SWE-Bench Verified Leaderboard ===
1. Augment Agent v0 - 65.4
2. W&B Programmer O1 crosscheck5 - 64.6
3. AgentScope - 63.4
4. Tools + Claude 3.7 Sonnet (2025-02-24) - 63.2
5. EPAM AI/Run Developer Agent v20250219 + Anthopic Claude 3.5 Sonnet - 62.8
“Training until the loss of humanity.” – GPT-7’s first (and last) tweet
#ai #LLM
