Head to head
Claude Haiku 4.5 vs Gemini 3.1 Pro (preview)
Claude Haiku 4.5: currentGemini 3.1 Pro (preview): currentheavy tier
No verdict
Cost per solved task needs a published pass rate for both models. At least one has none, so it is reported as missing rather than estimated.
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
needs a pass rate for both
| Claude Haiku 4.5 | Gemini 3.1 Pro (preview) | |
|---|---|---|
| Input $/Mtok | $1 | $2 |
| Output $/Mtok | $5 | $12 |
| Cached input $/Mtok | $0.1 | $0.2 |
| Pass rate | missing | 46% |
| Pass rate source | missing | SEAL |
| Cost basis | missing | modelled |
| Cost per solved task | missing | $4.30 |
verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· Claude Haiku 4.5· Gemini 3.1 Pro (preview)