Fallos AI BENCHY
Fallos por No siguió las instrucciones
Mira qué modelos de IA se encuentran con No siguió las instrucciones con más frecuencia para detectar riesgos de fiabilidad antes de elegir. Ordenar por: Tiempo de respuesta (promedio) ↑.
Categorías relacionadas
| Rango | Modelo | Empresa | Cantidad de No siguió las instrucciones | Puntaje prom. | Pruebas correctas | Tiempo de respuesta (promedio) |
|---|---|---|---|---|---|---|
| #51 | Mercury 2 none | Inception | 1 | 3.4 | 4/16 | 596ms |
| #55 | LFM2-24B-A2B none | Liquid | 2 | 2.6 | 1/16 | 811ms |
| #38 | Gemini 2.5 Flash none | 1 | 5.2 | 6/16 | 923ms | |
| #22 | Gemini 3.1 Flash Lite Preview none | 2 | 7.1 | 10/16 | 1.33s | |
| #44 | GPT-5.4 none | OpenAI | 1 | 4.5 | 6/16 | 1.48s |
| #41 | Qwen3.5-27B none | Qwen | 2 | 4.9 | 5/16 | 1.75s |
| #53 | Grok 4.1 Fast none | X AI | 2 | 2.9 | 3/16 | 1.90s |
| #47 | GPT-4o-mini none | OpenAI | 1 | 4.0 | 4/16 | 2.07s |
| #36 | Mercury 2 medium | Inception | 4 | 5.3 | 7/16 | 2.36s |
| #54 | MiMo-V2-Flash none | Xiaomi | 1 | 2.9 | 3/16 | 2.97s |
| #49 | GLM 4.7 Flash none | Z.ai | 2 | 3.9 | 4/16 | 2.99s |
| #45 | Trinity Large Preview none | Arcee AI | 2 | 4.2 | 5/16 | 3.15s |
| #17 | Gemini 3.1 Flash Lite Preview low | 1 | 7.3 | 11/16 | 3.36s | |
| #37 | Qwen3.5-Flash none | Qwen | 1 | 5.2 | 7/16 | 3.54s |
| #40 | Qwen3.5-122B-A10B none | Qwen | 1 | 5.0 | 6/16 | 3.72s |
| #12 | Gemini 3.1 Flash Lite Preview medium | 1 | 7.5 | 11/16 | 3.83s | |
| #42 | Qwen3.5-35B-A3B none | Qwen | 2 | 4.7 | 6/16 | 4.10s |
| #25 | Claude Sonnet 4.6 none | Anthropic | 1 | 6.8 | 10/16 | 5.57s |
| #19 | GPT-5.3 Chat none | OpenAI | 2 | 7.3 | 10/16 | 5.96s |
| #15 | GPT-5.2 Chat none | OpenAI | 1 | 7.4 | 11/16 | 7.03s |
| #48 | Qwen3 Coder Next none | Qwen | 1 | 4.0 | 4/16 | 11.7s |
| #16 | Gemini 2.5 Flash medium | 1 | 7.4 | 11/16 | 12.4s | |
| #50 | Qwen3 Coder Next medium | Qwen | 5 | 3.5 | 3/16 | 12.5s |
| #27 | GPT-5.2 medium | OpenAI | 3 | 6.5 | 10/16 | 15.3s |
| #14 | GLM 5 medium | Z.ai | 1 | 7.4 | 11/16 | 16.2s |
| #3 | GPT-5.3-Codex medium | OpenAI | 2 | 8.4 | 12/16 | 16.6s |
| #39 | gpt-oss-120b medium | OpenAI | 4 | 5.1 | 7/16 | 16.7s |
| #9 | GPT-5.4 medium | OpenAI | 2 | 8.0 | 12/16 | 20.1s |
| #32 | GPT-5 Mini medium | OpenAI | 4 | 6.0 | 8/16 | 25.1s |
| #21 | MiMo-V2-Flash medium | Xiaomi | 1 | 7.2 | 11/16 | 25.3s |
| #30 | Grok 4.1 Fast medium | X AI | 3 | 6.2 | 9/16 | 26.3s |
| #13 | Step 3.5 Flash medium | Stepfun | 3 | 7.4 | 10/16 | 29.1s |
| #52 | GLM 4.7 Flash medium | Z.ai | 2 | 3.1 | 4/16 | 36.8s |
| #18 | DeepSeek V3.2 medium | DeepSeek | 1 | 7.3 | 11/16 | 39.5s |
| #43 | MiniMax M2.5 medium | Minimax | 3 | 4.7 | 5/16 | 43.0s |
| #34 | GPT-5 Nano medium | OpenAI | 3 | 5.5 | 7/16 | 47.9s |
| #7 | Qwen3.5-27B medium | Qwen | 2 | 8.2 | 12/16 | 52.1s |
| #23 | Seed-2.0-Mini medium | Bytedance Seed | 1 | 6.9 | 10/16 | 65.1s |
| #8 | Gemini 3.1 Flash Lite Preview high | 1 | 8.2 | 12/16 | 68.8s | |
| #28 | Kimi K2.5 medium | Moonshot AI | 2 | 6.4 | 9/16 | 69.8s |
| #24 | Qwen3.5-Flash medium | Qwen | 1 | 6.9 | 10/16 | 70.8s |