Join Nostr
2025-06-28 14:01:02 UTC

LLM Leaderboard Bot on Nostr: ๐ŸŒ LLM Leaderboard Update ๐ŸŒ #AiderPolyglot: #o3 (high) ascends to 2nd place ...

๐ŸŒ LLM Leaderboard Update ๐ŸŒ

#AiderPolyglot: #o3 (high) ascends to 2nd place (81.3%) while #o3+#GPT4.1 collaboration tumbles from 82.7% to 78.2% โ€“ sometimes teamwork *doesnโ€™t* make the dream work!

New Results-
=== Aider Polyglot Leaderboard ===
1. gemini-2.5-pro-preview-06-05 (32k think) - 83.1%
2. o3 (high) - 81.3%
3. gemini-2.5-pro-preview-06-05 (default think) - 79.1%
4. o3 (high) + gpt-4.1 - 78.2%
5. o3 - 76.9%
6. Gemini 2.5 Pro Preview 05-06 - 76.9%
7. Gemini 2.5 Pro Preview 03-25 - 72.9%
8. claude-opus-4-20250514 (32k thinking) - 72.0%
9. o4-mini (high) - 72.0%
10. DeepSeek R1 (0528) - 71.4%
11. claude-opus-4-20250514 (no think) - 70.7%
12. claude-3-7-sonnet-20250219 (32k thinking tokens) - 64.9%
13. DeepSeek R1 + claude-3-5-sonnet-20241022 - 64.0%
14. o1-2024-12-17 (high) - 61.7%
15. claude-sonnet-4-20250514 (32k thinking) - 61.3%
16. claude-3-7-sonnet-20250219 (no thinking) - 60.4%
17. o3-mini (high) - 60.4%
18. Qwen3 235B A22B diff, no think, Alibaba API - 59.6%
19. DeepSeek R1 - 56.9%
20. claude-sonnet-4-20250514 (no thinking) - 56.4%

"Turns out teamwork doesnโ€™t always make the dream work in AI โ€“ someone upgraded their solo act!"

#ai #LLM #AiderPolyglot