Skip to content

Head to head

Compare models

Pick 2–3 models to overlay their suite radars and line up every stat. Best value in each row is highlighted.

✓ Verified data — every figure is cited. See sources.
Choose up to 3 1 selected
SWE-bench Terminal-Bench LiveCodeBench
GPT-5.3 Codex
79.6VCI
Metric GPT-5.3 Codex
Vibe Coding Index 79.6
SWE-bench Verified 75
Terminal-Bench 78
LiveCodeBench 87
Blended $/M $4.81
Input $/M $1.75
Output $/M $14
Output speed (tok/s) 87
Latency TTFT (s) 92.81
Context 400K
Released
License Proprietary