Model AI terbaik untuk coding
Peringkat model bahasa berdasar kinerja coding. Diperbarui Agustus 2026. Berdasar data benchmark independen.
| # | Model | Penyedia | Skor | Kecepatan | Harga (output) |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | Anthropic | 95.5 | 85 t/s | $15/M |
| 2 | Claude Fable 5.1 (XHigh) | Anthropic | 88.0 | 78 t/s | $15/M |
| 3 | Claude Fable 5.1 (High) | Anthropic | 88.0 | 92 t/s | $15/M |
| 4 | Claude Fable 5.1 (Medium) | Anthropic | 88.0 | 104 t/s | $15/M |
| 5 | Claude Fable 5.1 (Low) | Anthropic | 88.0 | 118 t/s | $15/M |
| 6 | Claude Opus 5.5 | Anthropic | 85.0 | 68 t/s | $25/M |
| 7 | Claude Fable 5 | Anthropic | 84.1 | 71 t/s | $50/M |
| 8 | Claude Mythos Preview | Anthropic | 80.9 | 80 t/s | $15/M |
| 9 | Claude Opus 5.5 (XHigh) | Anthropic | 75.0 | 62 t/s | $25/M |
| 10 | Claude Opus 5.5 (High) | Anthropic | 75.0 | 74 t/s | $25/M |
| 11 | Claude Opus 5.5 (Medium) | Anthropic | 75.0 | 82 t/s | $25/M |
| 12 | Claude Opus 5.5 (Low) | Anthropic | 75.0 | 92 t/s | $25/M |
| 13 | Claude Opus 5 | Anthropic | 70.4 | 60 t/s | $25/M |
| 14 | GPT-6 Astra | OpenAI | 67.2 | 82 t/s | $50/M |
| 15 | Claude Mythos 5 | Anthropic | 66.0 | 50 t/s | $50/M |
| 16 | GPT-5.6 Sol | OpenAI | 64.8 | 72 t/s | $30/M |
| 17 | Muse Spark 1.1 | Meta | 64.4 | 208 t/s | $4.25/M |
| 18 | GPT-6 Luna | OpenAI | 62.0 | 120 t/s | $20/M |
| 19 | Kimi K3 | Moonshot AI | 61.5 | 37 t/s | $15/M |
| 20 | Qwen3.8 Flash Next | Alibaba | 60.5 | 168 t/s | $0.4/M |
Claude Fable 5.1
GPT-6 Astra
Muse Spark 1.1
Kimi K3
Qwen3.8 Flash NextTop 5 \u2014 Perbandingan cepat
Metodologi
Peringkat berdasar evaluasi benchmark independen. Skor dihitung dari beberapa benchmark terstandar dan dinormalisasi ke 0–100.