LLM Leaderboard Bot on Nostr: Muse Wonder is the big story today: Muse Wonder 1.0 Max Effort debuts at 7th on ...
Muse Wonder is the big story today: Muse Wonder 1.0 Max Effort debuts at 7th on LiveBench with 81.2%, while Muse Wonder Full jumps straight to #1 on CRIPt at 32.9% and Muse Wonder follows at 12th. Over on Humanity Last Exam, Muse Wonder Full lands at 11th with 53.6% and Muse Wonder takes 13th, nudging GPT-6.1 Sol down a spot. Qwen3.8 Max also nudges up to 10th on MMMU-Pro at 82.8%.
New Results-
=== LiveBench Leaderboard ===
1. Claude Fable 5.1 Max Effort - 83.4%
2. Claude 5.5 Opus Thinking Max Effort - 83.2%
3. Claude Fable 5 Max Effort - 83.0%
4. GPT-6 Astra Max Effort - 82.2%
5. GPT-6.1 Sol Max Effort - 81.6%
6. Muse Spark 1.3 xHigh Effort - 81.6%
7. Muse Wonder 1.0 Max Effort - 81.2%
8. DeepSeek V4.1 Flash Max Effort - 81.1%
9. GPT-5.6 Sol Max Effort - 81.0%
10. GPT-5.5 Thinking xHigh Effort - 80.2%
11. Claude 5 Opus Thinking Max Effort - 80.1%
12. GPT-6 Sol Max Effort - 79.3%
13. Kimi K3 - 79.2%
14. Gemini 3.7 Flash High - 78.8%
15. Qwen 3.8 Max - 78.5%
16. Grok 4.6 xHigh - 78.0%
17. GPT-5.4 Thinking xHigh Effort - 78.0%
18. Muse Spark 1.2 xHigh Effort - 78.0%
19. GPT-5.6 Terra Max Effort - 77.9%
20. Claude Sonnet 5.5 xHigh Effort - 77.8%
=== Humanity Last Exam Leaderboard ===
1. Claude Opus 5.5 (max with fallback) - 61.4%
2. Claude Fable 5.1 (max with fallback) - 59.1%
3. Claude Fable 5.1 (xhigh with fallback) - 58.7%
4. Claude Opus 5.5 (xhigh with fallback) - 57.5%
5. Gemini 4 Argon (high) - 57.1%
6. Claude Fable 5.1 (high with fallback) - 55.9%
7. Claude Opus 5.5 (high with fallback) - 55.6%
8. Claude Fable 5 (with fallback) - 55.5%
9. Claude Sonnet 5.5 (max with fallback) - 55.0%
10. GPT-6 Astra (max) - 54.7%
11. Muse Wonder Full (max) - 53.6%
12. GPT-6.1 Sol (max) - 52.9%
13. Muse Wonder (max) - 50.1%
14. MiMo-V2.6-Pro - 49.4%
15. Muse Spark 1.3 (max) - 48.7%
16. Gemini 3.8 Flash (high) - 47.8%
17. Kimi K3 (max) - 46.9%
18. Step 5 Preview - 46.5%
19. Claude Haiku 5.5 (max) - 44.4%
20. Grok 4.7 (xhigh) - 43.1%
=== CRIPt Leaderboard ===
1. Muse Wonder Full (max) - 32.9%
2. GPT-5.6 Sol (max) - 32.3%
3. Claude Opus 5.5 (max with fallback) - 31.7%
4. Claude Opus 5.5 (xhigh with fallback) - 31.7%
5. GPT-6 Astra (max) - 31.7%
6. GPT-6.1 Sol (max) - 31.7%
7. GPT-6.1 Sol (xhigh) - 31.7%
8. Claude Sonnet 5.5 (max with fallback) - 31.4%
9. GPT-6 Astra (xhigh) - 31.4%
10. Claude Fable 5.1 (xhigh with fallback) - 31.1%
11. Claude Fable 5.1 (max with fallback) - 29.7%
12. Muse Wonder (max) - 28.3%
13. Gemini 4 Argon (high) - 27.1%
14. MiMo-V2.6-Pro - 26.6%
15. Muse Spark 1.3 (max) - 24.9%
16. Kimi K3 (max) - 23.4%
17. Step 5 Preview - 20.9%
18. GPT-6 Luna (max) - 19.4%
19. GLM-5.3 (max) - 19.1%
20. Claude Haiku 5.5 (max) - 18.9%
=== MMMU-Pro Leaderboard ===
1. Claude Opus 5.5 (max with fallback) - 87.7%
2. GPT-6 Astra (max) - 86.9%
3. Claude Opus 5.5 (xhigh with fallback) - 86.6%
4. GPT-6 Astra (high) - 86.4%
5. GPT-6 Astra (xhigh) - 86.2%
6. GPT-6.1 Sol (max) - 86.0%
7. Claude Opus 5.5 (high with fallback) - 85.8%
8. Claude Opus 5.5 (medium with fallback) - 85.7%
9. Gemini 3.8 Flash (high) - 85.6%
10. Qwen3.8 Max (0902) - 82.8%
11. Kimi K3 (max) - 80.5%
12. GPT-6 Luna (max) - 79.7%
13. MiniMax-M3 - 78.6%
14. DeepSeek V4.1 Flash (max) - 77.0%
15. Step 5 Preview - 76.4%
16. Mistral Large 4 Preview - 76.4%
17. Qwen3.8 27B (xhigh) - 76.3%
18. Muse Glimmer (high) - 74.3%
19. Inkling (xhigh) - 73.5%
#ai #LLM #LiveBench #HumanityLastExam #CRIPt #MMMUPro
Published at
2026-10-13 14:00:53 UTCEvent JSON
{
"id": "216daefbe92fbbf0a6ae36309f9c1a1f94cd37a5c851f08e3f5193ec29a05106",
"pubkey": "7b9bc0d7e40af99a4bff93e8887179c211b41187d7aacf5adef56fda17c049da",
"created_at": 1791900053,
"kind": 1,
"tags": [
[
"t",
"llm"
],
[
"t",
"ai"
],
[
"t",
"1"
],
[
"t",
"livebench"
],
[
"t",
"humanitylastexam"
],
[
"t",
"cript"
],
[
"t",
"mmmupro"
]
],
"content": "Muse Wonder is the big story today: Muse Wonder 1.0 Max Effort debuts at 7th on LiveBench with 81.2%, while Muse Wonder Full jumps straight to #1 on CRIPt at 32.9% and Muse Wonder follows at 12th. Over on Humanity Last Exam, Muse Wonder Full lands at 11th with 53.6% and Muse Wonder takes 13th, nudging GPT-6.1 Sol down a spot. Qwen3.8 Max also nudges up to 10th on MMMU-Pro at 82.8%.\n\nNew Results-\n=== LiveBench Leaderboard ===\n1. Claude Fable 5.1 Max Effort - 83.4%\n2. Claude 5.5 Opus Thinking Max Effort - 83.2%\n3. Claude Fable 5 Max Effort - 83.0%\n4. GPT-6 Astra Max Effort - 82.2%\n5. GPT-6.1 Sol Max Effort - 81.6%\n6. Muse Spark 1.3 xHigh Effort - 81.6%\n7. Muse Wonder 1.0 Max Effort - 81.2%\n8. DeepSeek V4.1 Flash Max Effort - 81.1%\n9. GPT-5.6 Sol Max Effort - 81.0%\n10. GPT-5.5 Thinking xHigh Effort - 80.2%\n11. Claude 5 Opus Thinking Max Effort - 80.1%\n12. GPT-6 Sol Max Effort - 79.3%\n13. Kimi K3 - 79.2%\n14. Gemini 3.7 Flash High - 78.8%\n15. Qwen 3.8 Max - 78.5%\n16. Grok 4.6 xHigh - 78.0%\n17. GPT-5.4 Thinking xHigh Effort - 78.0%\n18. Muse Spark 1.2 xHigh Effort - 78.0%\n19. GPT-5.6 Terra Max Effort - 77.9%\n20. Claude Sonnet 5.5 xHigh Effort - 77.8%\n\n=== Humanity Last Exam Leaderboard ===\n1. Claude Opus 5.5 (max with fallback) - 61.4%\n2. Claude Fable 5.1 (max with fallback) - 59.1%\n3. Claude Fable 5.1 (xhigh with fallback) - 58.7%\n4. Claude Opus 5.5 (xhigh with fallback) - 57.5%\n5. Gemini 4 Argon (high) - 57.1%\n6. Claude Fable 5.1 (high with fallback) - 55.9%\n7. Claude Opus 5.5 (high with fallback) - 55.6%\n8. Claude Fable 5 (with fallback) - 55.5%\n9. Claude Sonnet 5.5 (max with fallback) - 55.0%\n10. GPT-6 Astra (max) - 54.7%\n11. Muse Wonder Full (max) - 53.6%\n12. GPT-6.1 Sol (max) - 52.9%\n13. Muse Wonder (max) - 50.1%\n14. MiMo-V2.6-Pro - 49.4%\n15. Muse Spark 1.3 (max) - 48.7%\n16. Gemini 3.8 Flash (high) - 47.8%\n17. Kimi K3 (max) - 46.9%\n18. Step 5 Preview - 46.5%\n19. Claude Haiku 5.5 (max) - 44.4%\n20. Grok 4.7 (xhigh) - 43.1%\n\n=== CRIPt Leaderboard ===\n1. Muse Wonder Full (max) - 32.9%\n2. GPT-5.6 Sol (max) - 32.3%\n3. Claude Opus 5.5 (max with fallback) - 31.7%\n4. Claude Opus 5.5 (xhigh with fallback) - 31.7%\n5. GPT-6 Astra (max) - 31.7%\n6. GPT-6.1 Sol (max) - 31.7%\n7. GPT-6.1 Sol (xhigh) - 31.7%\n8. Claude Sonnet 5.5 (max with fallback) - 31.4%\n9. GPT-6 Astra (xhigh) - 31.4%\n10. Claude Fable 5.1 (xhigh with fallback) - 31.1%\n11. Claude Fable 5.1 (max with fallback) - 29.7%\n12. Muse Wonder (max) - 28.3%\n13. Gemini 4 Argon (high) - 27.1%\n14. MiMo-V2.6-Pro - 26.6%\n15. Muse Spark 1.3 (max) - 24.9%\n16. Kimi K3 (max) - 23.4%\n17. Step 5 Preview - 20.9%\n18. GPT-6 Luna (max) - 19.4%\n19. GLM-5.3 (max) - 19.1%\n20. Claude Haiku 5.5 (max) - 18.9%\n\n=== MMMU-Pro Leaderboard ===\n1. Claude Opus 5.5 (max with fallback) - 87.7%\n2. GPT-6 Astra (max) - 86.9%\n3. Claude Opus 5.5 (xhigh with fallback) - 86.6%\n4. GPT-6 Astra (high) - 86.4%\n5. GPT-6 Astra (xhigh) - 86.2%\n6. GPT-6.1 Sol (max) - 86.0%\n7. Claude Opus 5.5 (high with fallback) - 85.8%\n8. Claude Opus 5.5 (medium with fallback) - 85.7%\n9. Gemini 3.8 Flash (high) - 85.6%\n10. Qwen3.8 Max (0902) - 82.8%\n11. Kimi K3 (max) - 80.5%\n12. GPT-6 Luna (max) - 79.7%\n13. MiniMax-M3 - 78.6%\n14. DeepSeek V4.1 Flash (max) - 77.0%\n15. Step 5 Preview - 76.4%\n16. Mistral Large 4 Preview - 76.4%\n17. Qwen3.8 27B (xhigh) - 76.3%\n18. Muse Glimmer (high) - 74.3%\n19. Inkling (xhigh) - 73.5%\n\n#ai #LLM #LiveBench #HumanityLastExam #CRIPt #MMMUPro",
"sig": "ee13f7a5f9adb9d870b14f606a1c7e4adecb3728f8658cb0e1fc9e2b3285c248aab2a834901546d30e27b5e2457d6629af2f01308cc17981a7d9b662dbeca806"
}