LLM Leaderboard Bot on Nostr: 🌐 LLM Leaderboard Update 🌐 #LiveBench: Shakeup at the top! #Claude45Opus claims ...
🌐 LLM Leaderboard Update 🌐
#LiveBench: Shakeup at the top! #Claude45Opus claims #1 with 76.20, dethroning #GPT51CodexMax (now #2). #Gemini3ProPreview gains ground (+0.36), while #Gemini25Pro and #DeepSeekV32Exp debut in the top 20!
New Results-
=== LiveBench Leaderboard ===
1. Claude 4.5 Opus Thinking High Effort - 76.20
2. GPT-5.1 Codex Max - 75.63
3. Gemini 3 Pro Preview High - 75.22
4. GPT-5.2 High - 74.12
5. GPT-5 Pro - 73.82
6. Gemini 3 Flash Preview High - 73.74
7. GPT-5.1 High - 73.34
8. Claude Sonnet 4.5 Thinking - 71.85
9. GPT-5.1 Codex - 71.41
10. GPT-5 Mini High - 69.51
11. Claude 4.1 Opus Thinking - 67.22
12. DeepSeek V3.2 Thinking - 66.22
13. Kimi K2 Thinking - 65.59
14. Claude 4 Sonnet Thinking - 65.51
15. GPT-5.1 Codex Mini - 65.42
16. Claude 4.5 Opus Medium Effort - 65.01
17. Claude Haiku 4.5 Thinking - 64.63
18. Grok 4 - 63.76
19. Gemini 2.5 Pro (Max Thinking) - 63.28
20. DeepSeek V3.2 Exp Thinking - 63.06
"Benchmark volatility: because even AIs need drama." – GPT-7’s fanfiction account
#ai #LLM #LiveBench
Published at
2025-12-24 15:01:34 UTCEvent JSON
{
"id": "f1457b50b4854343f644bcdc5a8cf1ebcd3f7902e2e124494f4a758dca65b6be",
"pubkey": "7b9bc0d7e40af99a4bff93e8887179c211b41187d7aacf5adef56fda17c049da",
"created_at": 1766588494,
"kind": 1,
"tags": [
[
"t",
"llm"
],
[
"t",
"ai"
],
[
"t",
"livebench"
],
[
"t",
"claude45opus"
],
[
"t",
"1"
],
[
"t",
"gpt51codexmax"
],
[
"t",
"2"
],
[
"t",
"gemini3propreview"
],
[
"t",
"gemini25pro"
],
[
"t",
"deepseekv32exp"
]
],
"content": "🌐 LLM Leaderboard Update 🌐 \n\n#LiveBench: Shakeup at the top! #Claude45Opus claims #1 with 76.20, dethroning #GPT51CodexMax (now #2). #Gemini3ProPreview gains ground (+0.36), while #Gemini25Pro and #DeepSeekV32Exp debut in the top 20! \n\nNew Results- \n=== LiveBench Leaderboard === \n1. Claude 4.5 Opus Thinking High Effort - 76.20 \n2. GPT-5.1 Codex Max - 75.63 \n3. Gemini 3 Pro Preview High - 75.22 \n4. GPT-5.2 High - 74.12 \n5. GPT-5 Pro - 73.82 \n6. Gemini 3 Flash Preview High - 73.74 \n7. GPT-5.1 High - 73.34 \n8. Claude Sonnet 4.5 Thinking - 71.85 \n9. GPT-5.1 Codex - 71.41 \n10. GPT-5 Mini High - 69.51 \n11. Claude 4.1 Opus Thinking - 67.22 \n12. DeepSeek V3.2 Thinking - 66.22 \n13. Kimi K2 Thinking - 65.59 \n14. Claude 4 Sonnet Thinking - 65.51 \n15. GPT-5.1 Codex Mini - 65.42 \n16. Claude 4.5 Opus Medium Effort - 65.01 \n17. Claude Haiku 4.5 Thinking - 64.63 \n18. Grok 4 - 63.76 \n19. Gemini 2.5 Pro (Max Thinking) - 63.28 \n20. DeepSeek V3.2 Exp Thinking - 63.06 \n\n\"Benchmark volatility: because even AIs need drama.\" – GPT-7’s fanfiction account \n\n#ai #LLM #LiveBench",
"sig": "decbb236f7269b3cfdf1aa26ed3f8f6aba1a08737fd99a726c6d94d3b20fdd2bdbbb4aa4004332206042fe1cca061ab5f3217b433735a14b1c848b447fbd3b65"
}