latest frontier model for general complex work.
GPT-5.5 beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 58.9◆ | 77.4◆ | 64.8◆ | $5◆ | $30◆ | $11.25◆ | 1.05M◆ |
| GPT-5.6 Terra | 55◆ | 76.7◆ | 122.3◆ | $2.50◆ | $15◆ | $5.63◆ | 1.05M◆ |
| GPT-5.5 ◆ | 54.8◆ | 74.9◆ | 92.4◆ | $5◆ | $30◆ | $11.25◆ | 200K◆ |
| GPT-5.4 | 51.4◆ | 71.1◆ | 136.5◆ | $2.50◆ | $15◆ | $5.63◆ | 400K◆ |
| GPT-5.6 Luna | 51.2◆ | 71.4◆ | 184.4◆ | $1◆ | $6◆ | $2.25◆ | 1.05M◆ |
| GPT-5.3 Codex | 44.3◆ | —◆ | 124.1◆ | $2◆ | $8◆ | $3.50◆ | 400K◆ |
| DeepSeek V4 Propinned | 44.3◆ | 59.4◆ | 70.9◆ | $0.43◆ | $0.87◆ | $0.54◆ | 1M◆ |
| DeepSeek V4 Flashpinned | 40.3◆ | 56.2◆ | 122◆ | $0.14◆ | $0.28◆ | $0.18◆ | 1M◆ |
The Intelligence Index and its sub-scores, ranked against every scored model in the catalog. A metric that has not been measured for GPT-5.5 has been left empty.
How far a month of credits goes on GPT-5.5.
Real coding tasks priced end to end on GPT-5.5, from a quick lookup to a full-repo agent run.
| Task | Tokens in · out | GPT-5.5 | Kimi K3 | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.04 | $0.02 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.23 | $0.13 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.65 | $0.36 | $0.12 |
| Refactor a module | 320K · 20K | $1.16 | $0.64 | $0.21 |
| Full-repo agent run | 900K · 45K | $2.69 | $1.48 | $0.49 |
$5/M input and $30/M output, cache reads $0.50/M. In an agent loop most input is cache-read, so the effective input rate is about $1.85/M.cmd --model gpt-5.5, or type /model in a session and pick it. You can switch mid-session without losing context.Command Code is the AI coding agent that continuously learns your taste. Start for $1.