Agenttaken-ranglijst
Zie welke AI-modellen het best presteren op Agenttaken, welke betrouwbaar blijven en waar de grootste verschillen zitten. Sorteren op: Responstijd (gem.) ↓.
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.) |
|---|---|---|---|---|---|---|---|
| #368 | Command A+ high | Cohere | 3.9 | 3.2 | $0.079 | 0/1 | 156.0s |
| #127 | Grok 4.7 low | X AI | 5.0 | 7.4 | $2.263 | 0/1 | 154.9s |
| #221 | Space Bunny Alpha medium | Stealth | 6.1 | 6.3 | $0.000 | 0/1 | 153.1s |
| #346 | Qwen3.5-9B medium | Qwen | 5.2 | 4.0 | $0.106 | 0/1 | 152.9s |
| #324 | Laguna S 2.1 low | Poolside | 2.8 | 4.6 | $0.109 | 0/1 | 152.1s |
| #68 | Qwen3.8 2.4T A95B low | Qwen | 10.0 | 8.4 | $3.172 | 1/1 | 151.8s |
| #319 | Qwen3 Coder Next medium | Qwen | 5.0 | 4.7 | $0.069 | 0/1 | 151.4s |
| #87 | Claude Opus 4.7 medium | Anthropic | 5.2 | 8.1 | $3.636 | 0/1 | 150.6s |
| #235 | Granite 4.2 8B medium | IBM Granite | 10.0 | 6.1 | $0.029 | 1/1 | 149.5s |
| #317 | Laguna S 2.1 none | Poolside | 5.4 | 4.7 | $0.047 | 0/1 | 149.3s |
| #186 | Qwen3.7 Flash medium | Qwen | 5.2 | 6.6 | $0.076 | 0/1 | 149.0s |
| #88 | DeepSeek V4 Flash 0423 high | DeepSeek | 10.0 | 8.1 | $0.056 | 1/1 | 148.1s |
| #96 | Qwen3.5-27B medium | Qwen | 10.0 | 7.9 | $1.135 | 1/1 | 146.5s |
| #148 | Qwen3.6 27B medium | Qwen | 10.0 | 7.2 | $1.006 | 1/1 | 145.9s |
| #187 | LongCat 2.0 low | Meituan | 6.1 | 6.6 | $0.495 | 0/1 | 145.6s |