Week 11, 2026 • 9 models tested
AI Model Benchmarks
Find your perfect model in 60 seconds
9
models tested
40
tasks
5
categories
Weekly
updates
Overall Leaderboard
Top AI models across all categories
| Rank | Model | Score | Price/1M | Tasks | |
|---|---|---|---|---|---|
| 🥇 | Claude 3.5 Sonnet | 92.1 | $15.00 | 14 | |
| 🥈 | Qwen3 Max | 90.5 | $1.60 | 15 | |
| 🥉 | GPT-4o | 89.2 | $10.00 | 15 | |
| 4 | Qwen3 235B | 86.2 | $0.60 | 17 | |
| 5 | DeepSeek R1 | 85.6 | $2.19 | 17 | |
| 6 | Claude 3.5 Haiku | 85.2 | $4.00 | 17 | |
| 7 | Gemini 2.0 Flash | 81.2 | $0.40 | 19 | |
| 8 | GPT-4o Mini | 80.0 | $0.60 | 18 | |
| 9 | Llama 3.3 70B | 78.7 | $0.40 | 19 |
Browse by Category
Explore detailed performance comparisons across different task types
Weekly Reports
Read Detailed Analysis in Our Blog
Get weekly AI benchmark reports with insights, trends, and recommendations
Try Top Models
Test the Best AI Models Yourself
All benchmark winners available on our platform. Try for free!
Free tier available
No credit card required