Model AI paling cerdas
Peringkat model berdasar inteligensi keseluruhan. Diperbarui Agustus 2026. Berdasar data benchmark independen.
| # | Model | Penyedia | Skor | Kecepatan | Harga (output) |
|---|---|---|---|---|---|
| 1 | Claude Mythos Preview | Anthropic | 97.4 | 80 t/s | $15/M |
| 2 | Claude Fable 5.1 | Anthropic | 88.0 | 85 t/s | $15/M |
| 3 | Claude Mythos 5 | Anthropic | 79.0 | 50 t/s | $50/M |
| 4 | Claude Opus 4 6 Thinking | Anthropic | 75.0 | 50 t/s | $15/M |
| 5 | Claude Opus 4 7 Thinking | Anthropic | 75.0 | 50 t/s | $15/M |
| 6 | Claude Opus 5 Max | Anthropic | 75.0 | 50 t/s | $15/M |
| 7 | Gemini 3.1 Pro Preview | 74.0 | 50 t/s | $5/M | |
| 8 | Kimi K3 Max | Moonshot AI | 74.0 | 50 t/s | $3/M |
| 9 | Claude Opus 4 8 Thinking | Anthropic | 74.0 | 50 t/s | $15/M |
| 10 | GPT 5.6 Sol Xhigh | OpenAI | 74.0 | 50 t/s | $10/M |
| 11 | GPT 5.5 High | OpenAI | 74.0 | 50 t/s | $10/M |
| 12 | GPT 5.4 High | OpenAI | 74.0 | 50 t/s | $10/M |
| 13 | Gemini 3.5 Flash High | 74.0 | 50 t/s | $5/M | |
| 14 | GPT 5.2 Chat Latest 20260210 | OpenAI | 74.0 | 50 t/s | $10/M |
| 15 | Qwen3.7 Max Preview | Alibaba | 74.0 | 50 t/s | $2/M |
| 16 | Grok 4.20 Beta1 | xAI | 74.0 | 50 t/s | $15/M |
| 17 | Gemini 3.5 Flash Medium | 74.0 | 50 t/s | $5/M | |
| 18 | GPT 5.5 Instant | OpenAI | 74.0 | 50 t/s | $10/M |
| 19 | Claude Opus 4 5 20251101 Thinking 32k | Anthropic | 74.0 | 50 t/s | $15/M |
| 20 | Grok 4.20 Beta 0309 Reasoning | xAI | 74.0 | 50 t/s | $15/M |
Claude Mythos Preview
Gemini 3.1 Pro Preview
Kimi K3 Max
GPT 5.6 Sol Xhigh
Qwen3.7 Max Preview
Grok 4.20 Beta1Top 5 \u2014 Perbandingan cepat
Metodologi
Peringkat berdasar evaluasi benchmark independen. Skor dihitung dari beberapa benchmark terstandar dan dinormalisasi ke 0–100.