Model AI Terbaik untuk Pemanggilan Alat
Peringkat model bahasa berdasarkan keandalan function calling. Diperbarui Agustus 2026. Berdasar data benchmark independen.
| # | Model | Penyedia | Skor | Kecepatan | Harga (output) |
|---|---|---|---|---|---|
| 1 | Kimi K3 | Moonshot AI | 94.6 | 37 t/s | $15/M |
| 2 | Claude Fable 5.1 | Anthropic | 93.2 | 85 t/s | $15/M |
| 3 | Claude Fable 5 | Anthropic | 90.1 | 71 t/s | $50/M |
| 4 | Claude Opus 5.5 | Anthropic | 82.4 | 68 t/s | $25/M |
| 5 | Claude Fable 5.1 (XHigh) | Anthropic | 82.0 | 78 t/s | $15/M |
| 6 | Claude Fable 5.1 (High) | Anthropic | 82.0 | 92 t/s | $15/M |
| 7 | GPT-6 Astra | OpenAI | 82.0 | 82 t/s | $50/M |
| 8 | Claude Fable 5.1 (Medium) | Anthropic | 82.0 | 104 t/s | $15/M |
| 9 | Claude Fable 5.1 (Low) | Anthropic | 82.0 | 118 t/s | $15/M |
| 10 | Claude Opus 4.8 | Anthropic | 78.1 | 50 t/s | $15/M |
| 11 | GPT-6 Astra (xhigh) | OpenAI | 76.8 | 76 t/s | $50/M |
| 12 | GPT-6 Astra (high) | OpenAI | 76.8 | 90 t/s | $50/M |
| 13 | GPT-6 Astra (medium) | OpenAI | 76.8 | 98 t/s | $50/M |
| 14 | GPT-6 Astra (low) | OpenAI | 76.8 | 110 t/s | $50/M |
| 15 | GPT-6 Luna | OpenAI | 74.8 | 120 t/s | $20/M |
| 16 | Claude Opus 4.7 | Anthropic | 73.9 | 80 t/s | $15/M |
| 17 | Claude Opus 5.5 (XHigh) | Anthropic | 73.2 | 62 t/s | $25/M |
| 18 | Claude Opus 5.5 (High) | Anthropic | 73.2 | 74 t/s | $25/M |
| 19 | Claude Opus 5.5 (Medium) | Anthropic | 73.2 | 82 t/s | $25/M |
| 20 | Claude Opus 5.5 (Low) | Anthropic | 73.2 | 92 t/s | $25/M |
Kimi K3
Claude Fable 5.1
GPT-6 AstraTop 5 \u2014 Perbandingan cepat
Metodologi
Peringkat berdasar evaluasi benchmark independen. Skor dihitung dari beberapa benchmark terstandar dan dinormalisasi ke 0–100.