Agenttaken-ranglijst
Zie welke AI-modellen het best presteren op Agenttaken, welke betrouwbaar blijven en waar de grootste verschillen zitten. Sorteren op: Totale kosten ↑.
380/380
Modellen filteren
Geen modellen komen overeen met de huidige zoekopdracht en filters.
| Rang | Model | Bedrijf | Agenttaken-score | Score | Totale kosten | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|---|
| #186 | GLM 5.2 none | Z.ai | 6.1 | 6.6 | $0.152 | 0/1 | 46.9s |
| #90 | DeepSeek V4.1 Flash low | DeepSeek | 6.1 | 8.0 | $0.153 | 0/1 | 56.0s |
| #162 | Gemini 3.1 Flash Lite medium | 5.0 | 6.9 | $0.153 | 0/1 | 47.8s | |
| #202 | Gemini 3 Flash Preview none | 5.0 | 6.4 | $0.155 | 0/1 | 57.8s | |
| #295 | MiMo-V2.5-Pro none | Xiaomi | 3.9 | 5.1 | $0.157 | 0/1 | 49.6s |
| #238 | GLM 5.3 FlashX low | Z.ai | 4.7 | 6.0 | $0.157 | 0/1 | 78.0s |
| #155 | Gemini 3.1 Flash Lite Preview medium | 5.0 | 7.0 | $0.158 | 0/1 | 54.9s | |
| #310 | Hy4 preview none | Tencent | 5.0 | 4.9 | $0.161 | 0/1 | 65.5s |
| #318 | Granite 4.2 8B high | IBM Granite | 5.0 | 4.7 | $0.161 | 0/1 | 223.5s |
| #217 | Solar Pro 4 high | Upstage | 2.8 | 6.3 | $0.164 | 0/1 | 312.3s |
| #174 | Solar Pro 4 xhigh | Upstage | 3.0 | 6.7 | $0.167 | 0/1 | 316.6s |
| #255 | GPT-5.4 Mini none | OpenAI | 5.0 | 5.7 | $0.170 | 0/1 | 42.0s |
| #178 | Solar Pro 4 low | Upstage | 6.1 | 6.7 | $0.174 | 0/1 | 345.4s |
| #203 | Solar Pro 4 medium | Upstage | 4.7 | 6.4 | $0.174 | 0/1 | 272.3s |
| #218 | Qwen3.5 Plus 2026-02-15 none | Qwen | 5.2 | 6.3 | $0.176 | 0/1 | 183.5s |