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
Claude Opus 4.8
85.5VCI
Metric Claude Opus 4.8
Vibe Coding Index 85.5
SWE-bench Verified 89
Terminal-Bench 79
LiveCodeBench 88
Blended $/M $10
Input $/M $5
Output $/M $25
Output speed (tok/s) 60
Latency TTFT (s) 23.13
Context 1M
Released May 2026
License Proprietary