Head to head
Claude Opus 5 leads on 3 of 4 shared benchmarks; Gemini 3.1 Pro is ~53% cheaper per blended million tokens.
Claude Opus 5 leads on 3 of 4 shared benchmarks; Gemini 3.1 Pro is ~53% cheaper per blended million tokens.
| Dimension | Claude Opus 5 | Gemini 3.1 Pro |
|---|---|---|
| GPQA Diamond | 93.4% | 94.3% |
| HLE | 56.3% | 44.4% |
| MathArena Apex | — | 60.9% |
| Terminal-Bench 2.1 | 89.1% | — |
| Terminal-Bench 3.0 | 43.3% | — |
| Terminal-Bench 4.0 | 51.8% | — |
| DeepSWE v1.1 | 74% | — |
| ProgramBench | 37% | — |
| NL2Repo-Bench | 75.3% | — |
| ExploitGym | 22.1% | — |
| HLE (w/tools) | 63.6% | 51.4% |
| Automation-Bench | 50.3% | 35.4% |
| Agents' Last Exam | 28.6% | — |
| Chartography (w/tools) | 84% | — |
| BabyVision (w/tools) | 94.1% | — |
| ZeroBench-main (w/tools) | 52% | — |
| Blended price | $15.00 /1M | $7.00 /1M |
| Full priceInput · Output · Cached input | $5.00 · $25.00 · $0.500 | $2.00 · $12.00 · $0.200 |
| Context window | 1,000K | 1,000K |
Adjust the monthly volume — every model recomputes instantly.
Estimates use list prices and ignore cached input, batch discounts, and off-peak rates.