gemini-3.7-flash vs claude-haiku-4-5
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-3.7-flash | claude-haiku-4-5 | Advantage |
|---|---|---|---|
| Capability | 53% | 63% | +10% (claude-haiku-4-5 leads) |
| Median task time | 2m 50s | 3m 58s | 1m 7s faster (gemini-3.7-flash leads) |
| Approx. task cost | $0.035 / task | $0.005 / task | $0.030 / task lower (claude-haiku-4-5 leads) |
gemini-3.7-flash: 11.3% of Google AI Pro (67.8% / 5h, 11.3% / 1w) per run. claude-haiku-4-5: 5.0% of Claude Max 20x (5.0% / 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-3.7-flash | claude-haiku-4-5 | Advantage |
|---|---|---|---|
| Capability | 40% | 24% | +16% (gemini-3.7-flash leads) |
| Median task time | 1m 59s | 3m 4s | 1m 5s faster (gemini-3.7-flash leads) |
| Approx. task cost | $0.014 / task | $0.003 / task | $0.011 / task lower (claude-haiku-4-5 leads) |
gemini-3.7-flash: 1.2% of Google AI Pro (7.3% / 5h, 1.2% / 1w) per run. claude-haiku-4-5: 1.0% of Claude Max 20x (1.0% / 5h) per run. Each figure is a share of that agent's own plan, so there is no delta to draw.
| Dimension | gemini-3.7-flash | claude-haiku-4-5 | Advantage |
|---|---|---|---|
| Capability | 79% | 23% | +56% (gemini-3.7-flash leads) |
| Median task time | 4m 7s | 4m 18s | 11s faster (gemini-3.7-flash leads) |
| Approx. task cost | $0.029 / task | not measured | - |
gemini-3.7-flash: 0.6% of Google AI Pro (3.7% / 5h, 0.6% / 1w) per good solve. claude-haiku-4-5: 0.0% of Claude Max 20x 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-3.7-flash or claude-haiku-4-5?
gemini-3.7-flash clears higher: tier 3 of 5 versus tier 2 for claude-haiku-4-5 on real-world@v3, our private suite of real-world coding problems. Latest measurement 2026-08-16.