Find the right AI model
What will you use it for?
Choose every type of task you plan to do
Choose one or more use cases to get evidence-based recommendations. How recommendations work
| Model | Company | Links | |||||||
|---|---|---|---|---|---|---|---|---|---|
| 1 | 1.Claude Opus 5 |  🇺🇸Anthropic | 60.7 | 63 t/s | 1M | $0.018 | $5.00 | $25.00 | |
| 2 | 2.GPT-5.6 Sol |  🇺🇸OpenAI | 58.9 | 85 t/s | 1.1M | $0.020 | $5.00 | $30.00 | |
| 3 | 3.Kimi K3 |  🇨🇳Moonshot AI | 57.1 | 73 t/s | 1M | $0.011 | $3.00 | $15.00 | |
| 4 | 4.Grok 4.5 |  🇺🇸xAI | 53.8 | 54 t/s | 500K | $0.0050 | $2.00 | $6.00 | |
| 5 | 5.Claude Sonnet 5 | 🇺🇸Anthropic | 53.4 | 96.5 t/s | 1M | $0.0070 | $2.00 | $10.00 | |
| 6 | 6.GLM 5.2 |  🇨🇳Z.ai | 51.1 | 159 t/s | 1M | $0.0020 | $0.77 | $2.42 | |
| 7 | 7.Muse Spark 1.1 |  🇺🇸Meta | 50.6 | 143 t/s | 1M | $0.0034 | $1.25 | $4.25 | |
| 8 | 8.Gemini 3.5 Flash |  🇺🇸Google | 50.2 | 119 t/s | 1M | $0.0060 | $1.50 | $9.00 | |
| 9 | 9.Gemini 3.6 Flash | 🇺🇸Google | 50.1 | 148 t/s | 1M | $0.0053 | $1.50 | $7.50 | |
| 10 | 10.Qwen3.7 Max |  🇨🇳Alibaba | 46 | 35 t/s | 1M | $0.0031 | $1.25 | $3.75 | |
| 11 | 11.MiniMax M3 |  🇨🇳MiniMax | 44.4 | 83 t/s | 1M | $0.0009 | $0.30 | $1.20 | |
| 12 | 12.DeepSeek V4 Pro |  🇨🇳DeepSeek | 44.3 | 87 t/s | 1M | $0.0009 | $0.43 | $0.87 | |
| 13 | 13.MiMo-V2.5-Pro |  🇨🇳Xiaomi | 42.2 | 68 t/s | 1.1M | $0.0009 | $0.43 | $0.87 | |
| 14 | 14.Kimi K2.7 Code | 🇨🇳Moonshot AI | 41.9 | 168 t/s | 262.1K | $0.0025 | $0.73 | $3.50 | |
| 15 | 15.Hy3 preview |  🇨🇳Tencent | 41.2 | 27 t/s | 262.1K | $0.0002 | $0.06 | $0.21 | |
| 16 | 16.Inkling |  🇺🇸Thinking Machines | 40.7 | 136 t/s | 1M | $0.0030 | $1.00 | $4.05 | |
| 17 | 17.DeepSeek V4 Flash | 🇨🇳DeepSeek | 40.3 | 92 t/s | 1M | $0.0003 | $0.14 | $0.28 | |
| 18 | 18.GLM 5.1 | 🇨🇳Z.ai | 40.2 | 146 t/s | 204.8K | $0.0025 | $0.97 | $3.04 | |
| 19 | 19.Grok Build 0.1 | 🇺🇸xAI | 39.8 | 115 t/s | 256K | $0.0020 | $1.00 | $2.00 | |
| 20 | 20.Qwen3.7 Plus | 🇨🇳Alibaba | 39 | 13 t/s | 1M | $0.0010 | $0.32 | $1.28 |
Showing 1–20 of 67
1 / 4
Cost per task estimates 1,000 input tokens and 500 output tokens using the listed API prices. Recommendation scores include an uncertainty penalty when relevant benchmark evidence is incomplete.