GPT-5.6 Terra vs o4 Mini
| Benchmark | GPT-5.6 Terra | o4 Mini |
|---|---|---|
| Humanity's Last Exam | 33.3 | 16.5 |
| Terminal-Bench 4.0 | 1 | — |
| AutomationBench-AA | 33.5 | — |
| MMMU-Pro (vision) | 76.8 | 69.2 |
Specs
| Spec | GPT-5.6 Terra | o4 Mini |
|---|---|---|
| Input, per 1M | $2 | $1.10 |
| Output, per 1M | $12 | $4.40 |
| Cost per task? | $0.18 | — |
| Speed, tok/s | 113 | 165 |
| Context | 1.05M | 200K |
| Weights | Closed | Closed |
| Released | Jul 2026 | Apr 2025 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | Partial |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ✓ | ? |
| Run code | ✓ | ? |
| Use a computer | ✓ | ? |
What breaks when you switch
GPT-5.6 Terra → o4 Mini
Context: 1.05M → 200K
o4 Mini → GPT-5.6 Terra
Prompts with >272K input tokens›
Above 272K input tokens, input costs 2× and output 1.5× for the full request.