Head to head
GPT-5.4 vs Claude Opus 4.6
GPT-5.4: currentClaude Opus 4.6: legacyheavy tier
Verdict · modelled basis
GPT-5.4 costs 2.1x less per solved task.
On output token price alone, GPT-5.4 looks 1.7x cheaper (2.0x on input). The ranking holds, but the margin changes.
Source: Scale SEAL leaderboard, SWE-bench Pro · verified 2026-08-21 · prices from each provider's pricing page
Input $/M tokens
lower is better
Output $/M tokens
lower is better
Cost per solved task
modelled basis · lower is better
| GPT-5.4 | Claude Opus 4.6 | |
|---|---|---|
| Input $/Mtok | $2.5 | $5 |
| Output $/Mtok | $15 | $25 |
| Cached input $/Mtok | $0.25 | $0.5 |
| Pass rate | 59% | 52% |
| Pass rate source | SEAL | SEAL |
| Cost basis | modelled | modelled |
| Cost per solved task | $4.19 | $8.67 |
verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· GPT-5.4· Claude Opus 4.6