AI BENCHY Categorie
Programmeren-ranglijst
Zie welke AI-modellen het best presteren op Programmeren, welke betrouwbaar blijven en waar de grootste verschillen zitten. Sorteren op: Totale kosten ↑.
189/189
Modellen filteren
Geen modellen komen overeen met de huidige zoekopdracht en filters.
| Rang | Model | Bedrijf | Programmeren-score | Score | Totale kosten | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|---|
| #56 | Kimi K2.5 medium | Moonshot AI | 6.1 | 7.5 | $0.348 | 1/3 | 217.5s |
| #8 | Gemini 3.5 Flash low | 7.8 | 9.2 | $0.349 | 2/3 | 6.71s | |
| #23 | Step 3.7 Flash medium | Stepfun | 8.8 | 8.5 | $0.376 | 2/3 | 27.4s |
| #28 | Gemini 2.5 Flash medium | 7.8 | 8.2 | $0.379 | 2/3 | 41.0s | |
| #106 | Gemini 3 PRO Preview medium | 3.0 | 6.2 | $0.385 | 0/3 | 0ms | |
| #22 | GPT-5.2 Chat none | OpenAI | 8.8 | 8.5 | $0.393 | 2/3 | 9.82s |
| #104 | Qwen3.5-35B-A3B medium | Qwen | 5.9 | 6.3 | $0.401 | 1/3 | 206.6s |
| #58 | GPT-5.3 Chat none | OpenAI | 5.6 | 7.5 | $0.433 | 1/3 | 10.5s |
| #69 | GLM 5V Turbo medium | Z.ai | 6.0 | 7.3 | $0.457 | 1/3 | 63.4s |
| #38 | GPT-5.6 Terra medium | OpenAI | 6.1 | 7.8 | $0.496 | 1/3 | 7.19s |
| #62 | Claude Opus 4.7 none | Anthropic | 3.3 | 7.4 | $0.505 | 1/1 | 2.84s |
| #4 | Qwen3.7 Max medium | Qwen | 10.0 | 9.4 | $0.523 | 3/3 | 35.3s |
| #33 | GPT-5.4 Mini medium | OpenAI | 8.4 | 8.0 | $0.526 | 2/3 | 57.9s |
| #35 | Qwen3.5-27B medium | Qwen | 6.2 | 7.9 | $0.536 | 1/3 | 160.7s |
| #70 | Claude Opus 4.8 none | Anthropic | 5.5 | 7.2 | $0.539 | 1/3 | 3.29s |