Agenttaken-ranglijst
Zie welke AI-modellen het best presteren op Agenttaken, welke betrouwbaar blijven en waar de grootste verschillen zitten.
514/514
Modellen filteren
Geen modellen komen overeen met de huidige zoekopdracht en filters.
| Rang | Model | Bedrijf | Agenttaken-score | Score | Totale kosten | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|---|
| #272 | Claude Sonnet 5.5 medium | Anthropic | 1.0 | 0.7 | $1.100 | 1/1 | 51.2s |
| #279 | GLM 5.1 none | Z.ai | 1.0 | 0.6 | $0.451 | 1/1 | 107.2s |
| #283 | Qwen3.5-122B-A10B none | Qwen | 1.0 | 0.6 | $0.308 | 1/1 | 55.9s |
| #299 | Qwen3.6 27B none | Qwen | 1.0 | 0.6 | $0.148 | 1/1 | 58.6s |
| #311 | DeepSeek V4 Flash 0423 none | DeepSeek | 1.0 | 0.6 | $0.149 | 1/1 | 92.9s |
| #316 | DeepSeek V4 Flash 0731 none | DeepSeek | 1.0 | 0.6 | $0.053 | 1/1 | 174.9s |
| #323 | Inkling none | Thinkingmachines | 1.0 | 0.6 | $0.292 | 1/1 | 45.6s |
| #326 | Granite 4.2 8B medium | IBM Granite | 1.0 | 0.6 | $0.029 | 1/1 | 149.5s |
| #350 | Trinity Large Thinking high | Arcee AI | 1.0 | 0.6 | $0.794 | 1/1 | 45.0s |
| #506 | Gemini 3 Flash Preview high | 1.0 | 0.2 | $0.105 | 1/1 | 52.5s | |
| #143 | Kimi K3.1 Pro high | Moonshot AI | 0.7 | 0.8 | $1.646 | 0/1 | 93.4s |
| #170 | Step 3.7 Flash medium | Stepfun | 0.7 | 0.8 | $0.571 | 0/1 | 93.9s |
| #192 | GPT-5.6 Luna medium | OpenAI | 0.7 | 0.7 | $0.065 | 0/1 | 58.1s |
| #202 | GLM 5.3 Flash high | Z.ai | 0.7 | 0.7 | $0.056 | 0/1 | 111.5s |
| #218 | Step 3.7 Flash low | Stepfun | 0.7 | 0.7 | $0.449 | 0/1 | 83.6s |