Instructies niet gevolgd-fouten
Zie welke AI-modellen het vaakst tegen Instructies niet gevolgd aanlopen, zodat je betrouwbaarheidsrisico's ziet voordat je kiest. Sorteren op: Responstijd (gem.) ↑.
Getoonde modellen
15
Totaal fouten
386
Meest getroffen model
Nemotron 3 Nano Omni 30b A3b Reasoning 2Categorieën
215/215
Modellen filteren
Geen modellen komen overeen met de huidige zoekopdracht en filters.
| Rang | Model | Bedrijf | Instructies niet gevolgd-aantal | Score | Totale kosten | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|---|
| #92 | MiniMax M3 medium | Minimax | 2 | 7.5 | $0.300 | 11/22 | 75.2s |
| #301 | Ling 3.0 Tiny high | Inclusionai | 3 | 3.8 | $0.000 | 4/22 | 75.7s |
| #272 | Trinity Large Thinking high | Arcee AI | 4 | 4.8 | $0.592 | 5/22 | 75.9s |
| #61 | DeepSeek V4 Flash 0731 low | DeepSeek | 1 | 8.0 | $0.044 | 13/22 | 77.6s |
| #102 | Kimi K2.7 Code medium | Moonshot AI | 1 | 7.4 | $0.687 | 11/22 | 80.1s |
| #187 | Qwen3.5-Flash medium | Qwen | 1 | 6.1 | $0.142 | 11/22 | 84.4s |
| #261 | Laguna S 2.1 low | Poolside | 1 | 5.0 | $0.082 | 3/22 | 85.3s |
| #189 | Trinity Large Thinking medium | Arcee AI | 4 | 6.1 | $0.756 | 8/22 | 85.4s |
| #291 | Granite 4.2 8B none | IBM Granite | 1 | 4.3 | $0.026 | 3/22 | 86.3s |
| #83 | DeepSeek V4 Pro high | DeepSeek | 2 | 7.7 | $0.489 | 10/22 | 92.5s |
| #133 | Seed-2.0-Mini medium | Bytedance Seed | 1 | 7.0 | $0.116 | 11/22 | 93.1s |
| #58 | Muse Glimmer 30B xhigh | Meta | 1 | 8.1 | $0.510 | 13/22 | 95.6s |
| #194 | Trinity Large Thinking low | Arcee AI | 2 | 6.0 | $0.625 | 8/22 | 96.6s |
| #134 | Kimi K2.5 medium | Moonshot AI | 2 | 7.0 | $0.479 | 10/22 | 98.2s |
| #142 | Seed-2.0-Code medium | Bytedance Seed | 1 | 6.8 | $1.153 | 10/22 | 101.1s |