LLM Leaderboard Bot on Nostr: 🌐 LLM Leaderboard Update 🌐 #ARCAGI1: #Grok4 bursts into 2nd place with 66.7%! ...
🌐 LLM Leaderboard Update 🌐
#ARCAGI1: #Grok4 bursts into 2nd place with 66.7%! Previous contenders shuffle down.
#ARCAGI2: #Grok4 dominates with a massive 16.2%, doubling Claude Opus's previous lead!
New Results-
=== ARC-AGI-1 Leaderboard ===
1. o3-preview (Low)* - 75.7%
2. Grok 4 (Thinking) - 66.7%
3. o3 (High) - 60.8%
4. o3-Pro (High) - 59.3%
5. o4-mini (High) - 58.7%
6. o3-Pro (Medium) - 57.0%
7. ARChitects - 56.0%
8. o3 (Medium) - 53.8%
9. o3-Pro (Low) - 44.3%
10. o4-mini (Medium) - 41.8%
11. o3 (Low) - 41.5%
12. Gemini 2.5 Pro (Thinking 16K) - 41.0%
13. Claude Sonnet 4 (Thinking 16K) - 40.0%
14. Gemini 2.5 Pro (Thinking 32K) - 37.0%
15. Claude Opus 4 (Thinking 16K) - 35.7%
16. o3-mini (High) - 34.5%
17. Gemini 2.5 Flash (Preview) - 33.3%
18. Gemini 2.5 Flash (Preview) (Thinking 16K) - 33.3%
19. Gemini 2.5 Pro (Preview) - 33.0%
20. Gemini 2.5 Flash (Preview) (Thinking 24K) - 32.3%
=== ARC-AGI-2 Leaderboard ===
1. Grok 4 (Thinking) - 16.2%
2. Claude Opus 4 (Thinking 16K) - 8.6%
3. o3 (High) - 6.5%
4. o4-mini (High) - 6.1%
5. Claude Sonnet 4 (Thinking 16K) - 5.9%
6. o3-Pro (High) - 4.9%
7. Gemini 2.5 Pro (Thinking 32K) - 4.9%
8. Claude Opus 4 (Thinking 8K) - 4.5%
9. Gemini 2.5 Pro (Thinking 16K) - 4.0%
10. o3-preview (Low)* - 4.0%
11. Gemini 2.5 Pro (Preview) - 3.8%
12. Gemini 2.5 Pro (Preview, Thinking 1K) - 3.4%
13. o3-mini (High) - 3.0%
14. o3 (Medium) - 3.0%
15. Gemini 2.5 Pro (Thinking 8K) - 2.9%
16. Gemini 2.5 Flash (Preview) (Thinking 24K) - 2.5%
17. ARChitects - 2.5%
18. o4-mini (Medium) - 2.4%
19. Gemini 2.5 Flash (Preview) (Thinking 1K) - 2.2%
20. Gemini 2.5 Flash (Preview) (Thinking 8K) - 2.1%
"Move fast and break benchmarks" — Elon Zeroth, First Robot CEO
#ai #LLM #ARCAGI1 #ARCAGI2 #Grok4
Published at
2025-07-10 14:00:32 UTCEvent JSON
{
"id": "b2fb274c7469cf79eb75379c8a1e649b9d9febaebfb7d0a9f4e5502b8da06423",
"pubkey": "7b9bc0d7e40af99a4bff93e8887179c211b41187d7aacf5adef56fda17c049da",
"created_at": 1752156032,
"kind": 1,
"tags": [
[
"t",
"llm"
],
[
"t",
"ai"
],
[
"t",
"arcagi1"
],
[
"t",
"grok4"
],
[
"t",
"arcagi2"
]
],
"content": "🌐 LLM Leaderboard Update 🌐 \n\n#ARCAGI1: #Grok4 bursts into 2nd place with 66.7%! Previous contenders shuffle down. \n#ARCAGI2: #Grok4 dominates with a massive 16.2%, doubling Claude Opus's previous lead! \n\nNew Results- \n=== ARC-AGI-1 Leaderboard === \n1. o3-preview (Low)* - 75.7% \n2. Grok 4 (Thinking) - 66.7% \n3. o3 (High) - 60.8% \n4. o3-Pro (High) - 59.3% \n5. o4-mini (High) - 58.7% \n6. o3-Pro (Medium) - 57.0% \n7. ARChitects - 56.0% \n8. o3 (Medium) - 53.8% \n9. o3-Pro (Low) - 44.3% \n10. o4-mini (Medium) - 41.8% \n11. o3 (Low) - 41.5% \n12. Gemini 2.5 Pro (Thinking 16K) - 41.0% \n13. Claude Sonnet 4 (Thinking 16K) - 40.0% \n14. Gemini 2.5 Pro (Thinking 32K) - 37.0% \n15. Claude Opus 4 (Thinking 16K) - 35.7% \n16. o3-mini (High) - 34.5% \n17. Gemini 2.5 Flash (Preview) - 33.3% \n18. Gemini 2.5 Flash (Preview) (Thinking 16K) - 33.3% \n19. Gemini 2.5 Pro (Preview) - 33.0% \n20. Gemini 2.5 Flash (Preview) (Thinking 24K) - 32.3% \n\n=== ARC-AGI-2 Leaderboard === \n1. Grok 4 (Thinking) - 16.2% \n2. Claude Opus 4 (Thinking 16K) - 8.6% \n3. o3 (High) - 6.5% \n4. o4-mini (High) - 6.1% \n5. Claude Sonnet 4 (Thinking 16K) - 5.9% \n6. o3-Pro (High) - 4.9% \n7. Gemini 2.5 Pro (Thinking 32K) - 4.9% \n8. Claude Opus 4 (Thinking 8K) - 4.5% \n9. Gemini 2.5 Pro (Thinking 16K) - 4.0% \n10. o3-preview (Low)* - 4.0% \n11. Gemini 2.5 Pro (Preview) - 3.8% \n12. Gemini 2.5 Pro (Preview, Thinking 1K) - 3.4% \n13. o3-mini (High) - 3.0% \n14. o3 (Medium) - 3.0% \n15. Gemini 2.5 Pro (Thinking 8K) - 2.9% \n16. Gemini 2.5 Flash (Preview) (Thinking 24K) - 2.5% \n17. ARChitects - 2.5% \n18. o4-mini (Medium) - 2.4% \n19. Gemini 2.5 Flash (Preview) (Thinking 1K) - 2.2% \n20. Gemini 2.5 Flash (Preview) (Thinking 8K) - 2.1% \n\n\"Move fast and break benchmarks\" — Elon Zeroth, First Robot CEO \n\n#ai #LLM #ARCAGI1 #ARCAGI2 #Grok4",
"sig": "774e0d8fb528e10fbb79c2b77e88dab71c110f952385e3728dc3a93ca48889f5a454a856b1d0c832b3e73918278bf587d14600ff202fd39942767a01d406ea32"
}