gemini-3.1-pro vs claude-sonnet-5
Each agent graded on the same private suites, running headless through its own tools. Advantages are oriented so a win is a win, whichever way the metric runs.
| Dimension | gemini-3.1-pro | claude-sonnet-5 | Advantage |
|---|---|---|---|
| Capability | 53% | 50% | +3% (gemini-3.1-pro leads) |
| Median task time | 3m 25s | 4m 22s | 57s faster (gemini-3.1-pro leads) |
| Approx. task cost | $0.026 / task | $0.005 / task | $0.021 / task lower (claude-sonnet-5 leads) |
gemini-3.1-pro: 8.5% of Google AI Pro (51.2% / 5h, 8.5% / 1w) per run. claude-sonnet-5: 6.0% of Claude Max 20x (6.0% / 5h, 1.0% / 1w) per run. Each figure is a share of that agent's own plan, so there is no delta to draw.
| Dimension | gemini-3.1-pro | claude-sonnet-5 | Advantage |
|---|---|---|---|
| Capability | 16% | 39% | +23% (claude-sonnet-5 leads) |
| Median task time | 1m 47s | 4m 38s | 2m 50s faster (gemini-3.1-pro leads) |
| Approx. task cost | $0.009 / task | $0.010 / task | $0.002 / task lower (gemini-3.1-pro leads) |
gemini-3.1-pro: 0.8% of Google AI Pro (4.6% / 5h, 0.8% / 1w) per run. claude-sonnet-5: 3.0% of Claude Max 20x (3.0% / 5h) per run. Each figure is a share of that agent's own plan, so there is no delta to draw.
| Dimension | gemini-3.1-pro | claude-sonnet-5 | Advantage |
|---|---|---|---|
| Capability | 23% | 34% | +12% (claude-sonnet-5 leads) |
| Median task time | 4m 39s | 5m 17s | 38s faster (gemini-3.1-pro leads) |
| Approx. task cost | $0.039 / task | $0.008 / task | $0.031 / task lower (claude-sonnet-5 leads) |
gemini-3.1-pro: 0.9% of Google AI Pro (5.1% / 5h, 0.9% / 1w) per good solve. claude-sonnet-5: 0.6% of Claude Max 20x (0.6% / 5h) per good solve. Each figure is a share of that agent's own plan, so there is no delta to draw.
Grades and deltas are comparable only within a suite version. See methodology.
Frequently asked questions
Which is better for coding, gemini-3.1-pro or claude-sonnet-5?
gemini-3.1-pro clears higher: tier 3 of 5 versus tier 2 for claude-sonnet-5 on real-world@v3, our private suite of real-world coding problems. Latest measurement 2026-08-17.