gemini-3.1-pro vs claude-fable-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-fable-5 | Advantage |
|---|---|---|---|
| Capability | 53% | 60% | +7% (claude-fable-5 leads) |
| Median task time | 3m 25s | 3m 12s | 13s faster (claude-fable-5 leads) |
| Approx. task cost | $0.026 / task | $0.031 / task | $0.005 / task lower (gemini-3.1-pro leads) |
gemini-3.1-pro: 8.5% of Google AI Pro (51.2% / 5h, 8.5% / 1w) per run. claude-fable-5: 34.0% of Claude Max 20x (34.0% / 5h, 5.0% / 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-fable-5 | Advantage |
|---|---|---|---|
| Capability | 16% | 64% | +48% (claude-fable-5 leads) |
| Median task time | 1m 47s | 5m 54s | 4m 7s faster (gemini-3.1-pro leads) |
| Approx. task cost | $0.009 / task | $0.041 / task | $0.032 / 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-fable-5: 12.0% of Claude Max 20x (12.0% / 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-fable-5 | Advantage |
|---|---|---|---|
| Capability | 23% | 69% | +46% (claude-fable-5 leads) |
| Median task time | 4m 39s | 5m 25s | 47s faster (gemini-3.1-pro leads) |
| Approx. task cost | $0.039 / task | $0.038 / task | $0.001 / task lower (claude-fable-5 leads) |
gemini-3.1-pro: 0.9% of Google AI Pro (5.1% / 5h, 0.9% / 1w) per good solve. claude-fable-5: 2.8% of Claude Max 20x (2.8% / 5h, 0.6% / 1w) 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-fable-5?
claude-fable-5 clears higher: tier 4 of 5 versus tier 3 for gemini-3.1-pro on real-world@v3, our private suite of real-world coding problems. Latest measurement 2026-08-17.