Agenttaken-ranglijst
Zie welke AI-modellen het best presteren op Agenttaken, welke betrouwbaar blijven en waar de grootste verschillen zitten. Sorteren op: Totale kosten ↓.
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.) |
|---|---|---|---|---|---|---|---|
| #388 | Qwen3.6 35B A3B none | Qwen | 0.5 | 0.5 | $0.105 | 0/1 | 65.6s |
| #297 | LongCat 2.0 none | Meituan | 0.6 | 0.6 | $0.104 | 0/1 | 81.8s |
| #349 | Ring 2.6 1t medium | Inclusionai | 0.3 | 0.6 | $0.102 | 0/1 | 21ms |
| #201 | Gemma 4 26B A4B medium | 1.0 | 0.7 | $0.101 | 1/1 | 107.1s | |
| #256 | Solar Pro 4 low | Upstage | 0.6 | 0.7 | $0.101 | 0/1 | 345.4s |
| #286 | Solar Pro 4 medium | Upstage | 0.5 | 0.6 | $0.098 | 0/1 | 272.3s |
| #401 | Laguna S 2.1 medium | Poolside | 0.3 | 0.5 | $0.092 | 0/1 | 165.0s |
| #317 | Gemini 3.1 Flash Lite Preview none | 0.5 | 0.6 | $0.090 | 0/1 | 48.6s | |
| #255 | Qwen3.5-Flash none | Qwen | 1.0 | 0.7 | $0.089 | 1/1 | 53.8s |
| #186 | Qwen3.8 27B low | Qwen | 0.6 | 0.8 | ~$0.089 | 0/1 | 211.3s |
| #71 | GLM 5.3 Flash max | Z.ai | 1.0 | 0.9 | $0.089 | 1/1 | 96.7s |
| #128 | Claude Haiku 5.5 high | Anthropic | 1.0 | 0.8 | $0.088 | 1/1 | 52.6s |
| #464 | Grok 4.20 Beta default | X AI | 0.0 | 0.4 | $0.087 | 0/0 | 0ms |
| #450 | LFM3-1.7B default | Liquid | 0.3 | 0.4 | $0.084 | 0/1 | 56.5s |
| #282 | Laguna XS 2.1 medium | Poolside | 0.6 | 0.6 | $0.083 | 0/1 | 66.4s |