Gemini 3.7 Flash vs Gemini 3.8 Flash
Gemini 3.7 Flash was superseded by Gemini 3.8 Flash. The grades below are the last ones measured, so read them as history rather than as this week's board. See the current roster.
Gemini 3.8 Flash leads overall, C- to D+. Gemini 3.7 Flash is about 2.5x cheaper per task. By suite, real-world issues is even at C- and Gemini 3.8 Flash takes spec planning (D+ to D-). Take Gemini 3.7 Flash anyway when you want the side that is cheaper per task and faster on real-world issues.Measured
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.
Verdict: Gemini 3.8 Flash vs Gemini 3.7 Flash
Gemini 3.8 Flash leads overall, C- to D+. By suite: real-world issues is even at C- (60% vs 60% capability); Gemini 3.8 Flash takes spec planning, D+ to D- (50% vs 40% capability); vibe coding is even at C- (61% vs 56% capability). Gemini 3.7 Flash used 9.4% of Google AI Pro's weekly limit per pass, $0.023 per task at the listed price. Gemini 3.8 Flash used 23.7% of Google AI Pro's weekly limit per pass, $0.057 per task at the listed price. Per task, Gemini 3.7 Flash is about 2.5x cheaper ($0.023 vs $0.057). Gemini 3.7 Flash is faster on real-world issues: a median task takes 2m 38s against 5m 21s. Both finished every task on it. Reasons to pick Gemini 3.7 Flash anyway: it is cheaper per task ($0.023 vs $0.057) and it is faster on real-world issues (2m 38s vs 5m 21s median).
Changed since the previous graded week: Gemini 3.7 Flash: real-world issues usage 8.5% to 8.2% of the weekly limit, spec planning D to D-, spec planning usage 1.3% to 1.2% of the weekly limit; Gemini 3.8 Flash: real-world issues F to C-, real-world issues usage 18.0% to 21.9% of the weekly limit, spec planning usage 2.0% to 1.8% of the weekly limit, vibe coding D+ to C-, vibe coding usage 1.2% to 1.1% of the weekly limit.
| Dimension | Gemini 3.7 Flash | Gemini 3.8 Flash | Advantage |
|---|---|---|---|
| Capability | 60% | 60% | Even |
| Median task time | 2m 38s | 5m 21s | 2m 42s faster (Gemini 3.7 Flash leads) |
| Approx. task cost | $0.025 / task | $0.067 / task | $0.042 / task lower (Gemini 3.7 Flash leads) |
Gemini 3.7 Flash: 8.2% of Google AI Pro (49.1% / 5h, 8.2% / 1w) per run. Its weekly limit holds 6 of the week's 33.6 5h windows. Gemini 3.8 Flash: 21.9% of Google AI Pro (131.3% / 5h, 21.9% / 1w) per run. Its weekly limit holds 6 of the week's 33.6 5h windows. Each figure is a share of that agent's own plan, so there is no delta to draw.
| Dimension | Gemini 3.7 Flash | Gemini 3.8 Flash | Advantage |
|---|---|---|---|
| Capability | 40% | 50% | +11% (Gemini 3.8 Flash leads) |
| Median task time | 1m 38s | 3m 0s | 1m 23s faster (Gemini 3.7 Flash leads) |
| Approx. task cost | $0.014 / task | $0.021 / task | $0.007 / task lower (Gemini 3.7 Flash leads) |
Gemini 3.7 Flash: 1.2% of Google AI Pro (7.1% / 5h, 1.2% / 1w) per run. Its weekly limit holds 6 of the week's 33.6 5h windows. Gemini 3.8 Flash: 1.8% of Google AI Pro (11.0% / 5h, 1.8% / 1w) per run. Its weekly limit holds 6 of the week's 33.6 5h windows. Each figure is a share of that agent's own plan, so there is no delta to draw.
| Dimension | Gemini 3.7 Flash | Gemini 3.8 Flash | Advantage |
|---|---|---|---|
| Capability | 61% | 56% | +5% (Gemini 3.7 Flash leads) |
| Median task time | 3m 37s | 7m 51s | 4m 13s faster (Gemini 3.7 Flash leads) |
| Approx. task cost | $0.028 / task | $0.048 / task | $0.020 / task lower (Gemini 3.7 Flash leads) |
Gemini 3.7 Flash: 0.6% of Google AI Pro (3.6% / 5h, 0.6% / 1w) per good solve. Its weekly limit holds 6 of the week's 33.6 5h windows. Gemini 3.8 Flash: 1.1% of Google AI Pro (6.3% / 5h, 1.1% / 1w) per good solve. Its weekly limit holds 6 of the week's 33.6 5h windows. 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 Gemini 3.8 Flash?
They are even on our ladder: both clear tier 4 of 5 at 60% capability on real-world@v3, our private suite of real-world coding problems. Latest measurement 2026-08-30.
Which is cheaper per task, Gemini 3.7 Flash or Gemini 3.8 Flash?
Gemini 3.7 Flash used 9.4% of Google AI Pro's weekly limit per pass, $0.023 per task at the listed price. Gemini 3.8 Flash used 23.7% of Google AI Pro's weekly limit per pass, $0.057 per task at the listed price. Per task, Gemini 3.7 Flash is about 2.5x cheaper ($0.023 vs $0.057).