AI Leaderboard Intelligence Index v4.3.2
Incorporates evaluations: AIL-Briefcase v1.1, GDPval-AIL v2.1, AutomationBench-AIL, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AIL-Omniscience, AIL-LCR v1.1
Leaderboard
| Rank | Model | Score |
|---|---|---|
| #1 | Gemini 4 Argon | 58 |
| #2 | Claude Opus 5.5 (max) | 56 |
| #3 | Muse Wonder (Full) | 56 |
| #4 | Mistral Large 4 (Base (Preview)) | 54 |
| #5 | GPT-6 Astra (max) | 53 |
| #6 | GPT-6 Astra (xhigh) | 53 |
| #7 | Claude Fable 5.1 (max with fallback) | 53 |
| #8 | Claude Fable 5.1 (xhigh with fallback) | 53 |
| #9 | Muse Wonder (Standard (API)) | 53 |
| #10 | Claude Sonnet 5.5 (max) | 52 |
| #11 | GPT-6 Astra (high) | 51 |
| #12 | Claude Fable 5.1 (high with fallback) | 51 |
| #13 | GPT-6.1 Sol (max) | 51 |
| #14 | Claude Fable 5 (with fallback) | 50 |
| #15 | MiMo-V2.6-Pro (max) | 50 |
| #16 | Claude Haiku 5.5 | 49 |
| #17 | Muse Spark 1.3 (max) | 48.1 |
| #18 | GPT-6 Instant | 48 |
| #19 | GPT-5.6 Sol (max) | 47 |
| #20 | Gemini 2.5 Flash-Lite (high) | 45 |
| #21 | GLM-5.3 (max) | 45 |
| #22 | Grok 4 (4.6 high) | 44.4 |
| #23 | Kimi K3 (max) | 43.7 |
| #24 | GLM-5.3 (Flash) | 42 |
| #25 | Qwen3.8 (2.4T A95B) | 40 |
| #26 | Grok 4 (4.20 0309) | 40 |
| #27 | Kolibri 78B MoE (78B) | 38 |
| #28 | DeepSeek V4 Pro (0813) | 36 |
| #29 | K2 Horizon 375B A23B (375B A23B) | 34 |
| #30 | Mercury 2.5 | 30 |
| #31 | Llama 4 Scout | 30 |
| #32 | Celeris-1 | 25 |
| #33 | Granite 4 (4.2 3B) | 20 |
| #34 | EmbeddingGemma 2 | 20 |
| #35 | MiniCPM5-2B (2B) | 14 |