🤖 Model AI terbaik untuk agen
Peringkat model berdasar tugas agentik. Diperbarui Agustus 2026. Berdasar data benchmark independen.
| # | Model | Penyedia | Skor | Kecepatan | Harga (output) |
|---|---|---|---|---|---|
| 1 | Kimi K3 | Moonshot AI | 100.0 | 37 t/s | $15/M |
| 2 | Claude Fable 5 | Anthropic | 96.2 | 71 t/s | $50/M |
| 3 | Gemini 3.5 Flash | 75.9 | 267 t/s | $9/M | |
| 4 | Claude Opus 4.8 | Anthropic | 74.9 | 50 t/s | $15/M |
| 5 | Claude Opus 4.7 | Anthropic | 74.3 | 80 t/s | $15/M |
| 6 | Qwen3.7 Max | Alibaba | 71.5 | 203 t/s | $7.5/M |
| 7 | MiMo V2.5 Pro | Xiaomi | 69.0 | 65 t/s | $0.87/M |
| 8 | GLM-5.2 | Z.ai | 66.9 | 164 t/s | $4.29/M |
| 9 | Gemini 3.1 Pro | 62.6 | 136 t/s | $12/M | |
| 10 | Claude Mythos 5 | Anthropic | 62.0 | 50 t/s | $50/M |
| 11 | GPT-5.5 | OpenAI | 61.1 | 60 t/s | $10/M |
| 12 | Qwen3.7 Plus | Alibaba | 59.0 | 54 t/s | $1.6/M |
| 13 | Qwen3.6 Plus | Alibaba | 52.6 | 55 t/s | $3/M |
| 14 | Claude Sonnet 4.6 (max) | Anthropic | 52.0 | 50 t/s | $15/M |
| 15 | Muse Spark | Meta | 51.9 | 80 t/s | $0/M |
| 16 | GLM-5.1 | Z.ai | 51.0 | 74 t/s | $4.4/M |
| 17 | MiniMax-M2.7 | MiniMax | 50.0 | 40 t/s | $2/M |
| 18 | DeepSeek V4 Pro | DeepSeek | 49.7 | 66 t/s | $0.87/M |
| 19 | GPT-5.6 Luna | OpenAI | 43.3 | 175 t/s | $1.2/M |
| 20 | Claude Opus 4.6 | Anthropic | 43.1 | 50 t/s | $15/M |
Top 5 \u2014 Perbandingan cepat
Metodologi
Peringkat berdasar evaluasi benchmark independen. Skor dihitung dari beberapa benchmark terstandar dan dinormalisasi ke 0–100.