24h AI Market Tracker

Automated 24-hour benchmarking and telemetry across frontier foundation models, rank shifts, and market momentum.

1. Claude Opus 5.5 (Anthropic) — score 92
2. GPT-6 Astra (OpenAI) — score 92
3. Gemini 3.8 Flash (Google) — score 91
4. GPT-6 Sol (OpenAI) — score 90
5. Claude Fable 5.1 (Anthropic) — score 89
6. Manus AI (Manus) — score 89
7. Grok 4.7 (xAI) — score 88
8. Qwen3.8 Max (Alibaba) — score 88
9. Kimi K3 (Moonshot AI) — score 87
10. DeepSeek-R1 (DeepSeek) — score 87
11. NotebookLM (Google) — score 87
12. Whisper Large v3 Turbo (OpenAI) — score 87
13. Suno v4 (Suno) — score 87
14. GPT-6 Luna (OpenAI) — score 86
15. Lovable (Lovable) — score 86
16. Windsurf IDE (Codeium) — score 86
17. Google Imagen 3 (Google) — score 86
18. Kling 1.5 HD (Kuaishou) — score 86
19. LiveKit Agents (LiveKit) — score 86
20. Cosine Genie (Cosine) — score 86
21. Muse Spark 1.3 (Meta) — score 85
22. Perplexity (Perplexity AI) — score 85
23. FLUX.1 (Black Forest Labs) — score 85
24. Sora (OpenAI) — score 85
25. Aider (Aider) — score 85
26. Magnific AI (Magnific) — score 85
27. Cartesia Sonic (Cartesia) — score 85
28. MiniMax Hailuo AI (Video-01) (MiniMax) — score 85
29. Mistral Large 2 (Mistral AI) — score 85
30. GLM-5.3-Flash (Z.ai) — score 84
31. Midjourney v6 (Midjourney) — score 84
32. HeyGen (HeyGen) — score 84
33. Llama 3.3 70B (Meta) — score 84
34. Replit Agent (Replit) — score 84
35. Wispr Flow (Wispr) — score 84
36. Cohere Command R+ (Cohere) — score 84
37. Cursor (Anysphere) — score 83
38. Gamma (Gamma) — score 83
39. Harvey (Harvey AI) — score 83
40. Recraft v3 (Recraft) — score 83
41. ComfyUI (ComfyUI) — score 83
42. Hedra Character-2 (Hedra) — score 83
43. MiMo-V2.6 (Xiaomi) — score 82
44. ElevenLabs (ElevenLabs) — score 82
45. DeepSeek-V3 (DeepSeek) — score 82
46. LlamaIndex (LlamaIndex) — score 82
47. Bolt.new (StackBlitz) — score 82
48. Krea AI (Krea) — score 82
49. Mistral Le Chat (Mistral AI) — score 81
50. v0.dev (Vercel) — score 81