Electricity Bench

gemini-3.6-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.

gemini-3.6-flashClears tier 4 (partial tier 5) at 12.6% of Google AI Pro per runCOVERALLclaude-haiku-4-5Clears tier 1 (partial tier 5) at 3.0% of Claude Max 20x per runFOVERALL
real-world@v3CvsF
Dimensiongemini-3.6-flashclaude-haiku-4-5Advantage
Capability60%28%+32% (gemini-3.6-flash leads)
Median task time2m 17s3m 31s1m 14s faster (gemini-3.6-flash leads)
Approx. task cost$0.039 / task$0.003 / task$0.036 / task lower (claude-haiku-4-5 leads)

gemini-3.6-flash: 12.6% of Google AI Pro (about 72.1% / 5h, 12.6% / 1w) per run. claude-haiku-4-5: 3.0% of Claude Max 20x (3.0% / 5h, 1.0% / 1w) per run. Each figure is a share of that agent's own plan, so there is no delta to draw.

vibe-coding@v1CvsF
Dimensiongemini-3.6-flashclaude-haiku-4-5Advantage
Capability72%23%+48% (gemini-3.6-flash leads)
Median task time1m 54s3m 50s1m 56s faster (gemini-3.6-flash leads)
Approx. task cost$0.038 / task$0.007 / task$0.031 / task lower (claude-haiku-4-5 leads)

gemini-3.6-flash: 0.8% of Google AI Pro (4.9% / 5h, 0.8% / 1w) per good solve. claude-haiku-4-5: 0.5% of Claude Max 20x (0.5% / 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-3.6-flash or claude-haiku-4-5?

gemini-3.6-flash clears higher: tier 4 of 5 versus tier 1 for claude-haiku-4-5 on real-world@v3, our private suite of real-world coding problems. Latest measurement 2026-08-10.