Side-by-side comparison of GPT-4o (OpenAI) and Devin (Cognition) — benchmarks, pricing, and capabilities.
| GPT-4o OpenAI | Devin Cognition | |
|---|---|---|
| Category | LLMs | AI Agents |
| Specifications | ||
| Context Window | 128K | — |
| Pricing (per 1M tokens) | ||
| Input Cost | $2.50 | — |
| Output Cost | $10.00 | — |
| Performance | ||
| Overall Score | 92.5 | 84.0 |
| ARC-Challenge | 96.9 | — |
| BigBench Hard | 87.2 | — |
| Chatbot Arena ELO | 1270.0 | — |
| DROP | 88.1 | — |
| GSM8K | 95.3 | — |
| HumanEval | 92.0 | — |
| MATH | 76.6 | — |
| MMLU | 88.2 | — |
| SWE-bench Verified | — | 41.5 |
| TruthfulQA | 79.5 | — |
| WinoGrande | 89.6 | — |
| Community | ||
| User Rating | ★ 4.7 | ★ 4.1 |
| Reviews | 1240 | 180 |