Head to head
GPT-4.1 vs Gemini 2.5 Pro
GPT-4.1: legacyGemini 2.5 Pro: legacyheavy tier
Verdict · modelled basis
Gemini 2.5 Pro costs 2.9x less per solved task.
On output token price alone, GPT-4.1 looks 1.3x cheaper (1.6x on input). The ranking reverses once you divide by pass rate — the cheaper tokens do not win the task.
Source: Aider polyglot benchmark · 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-4.1 | Gemini 2.5 Pro | |
|---|---|---|
| Input $/Mtok | $2 | $1.25 |
| Output $/Mtok | $8 | $10 |
| Cached input $/Mtok | $0.5 | $0.125 |
| Pass rate | 52% | 83% |
| Pass rate source | Aider | Aider |
| Cost basis | modelled | modelled |
| Cost per solved task | $5.15 | $1.76 |
verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· GPT-4.1· Gemini 2.5 Pro