Gemini 3.8 FlashvsGemini 3.6 Flash
Across 4 shared benchmarks, Gemini 3.8 Flash leads overall: Gemini 3.8 Flash wins 3, Gemini 3.6 Flash wins 1, with 0 ties and an average score difference of +39.22.
Gemini 3.8 Flash
Google Deep Mind · 2026-09-02 · Multimodal model
Gemini 3.6 Flash
Google Deep Mind · 2026-07-21 · Multimodal model
Gemini 3.8 Flash3 wins(75%)(25%)1 winGemini 3.6 Flash
Benchmark scores
Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.
AI Agent - Tool Usage
Gemini 3.8 Flash 1/1| Benchmark | Gemini 3.8 Flash | Gemini 3.6 Flash | Diff |
|---|---|---|---|
| Terminal-Bench 2.1 | 89.401 / 48Thinking (With Tools) | 7826 / 48Thinking (With Tools) | +11.40 |
Coding and Software Engineer
Gemini 3.8 Flash 1/1| Benchmark | Gemini 3.8 Flash | Gemini 3.6 Flash | Diff |
|---|---|---|---|
| DeepSWE | 73.701 / 33Thinking (With Tools) | 4926 / 33Thinking (With Tools) | +24.70 |
Multimodal Understanding
Gemini 3.6 Flash 1/1| Benchmark | Gemini 3.8 Flash | Gemini 3.6 Flash | Diff |
|---|---|---|---|
| CharXiv RQ | 86.208 / 19Thinking Medium (No Tools) | 89.404 / 19Thinking (With Tools) | -3.20 |
Productivity Knowledge
Gemini 3.8 Flash 1/1| Benchmark | Gemini 3.8 Flash | Gemini 3.6 Flash | Diff |
|---|---|---|---|
| GDPval-AA v2 | 1,54513 / 24Thinking (No Tools) | 1,42117 / 24Thinking (No Tools) | +124 |
Specs
| Field | Gemini 3.8 Flash | Gemini 3.6 Flash |
|---|---|---|
| Publisher | Google Deep Mind | Google Deep Mind |
| Release date | 2026-09-02 | 2026-07-21 |
| Model type | Multimodal model | Multimodal model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1M |
| Max output | 64K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Gemini 3.8 Flash | Gemini 3.6 Flash |
|---|---|---|
| Text input | $0.75 / 1M tokens | $1.5 / 1M tokens |
| Text output | $3.75 / 1M tokens | $7.5 / 1M tokens |
| Cache read | $0.075 / 1M tokens | $0.15 / 1M tokens |
Summary
- Gemini 3.8 Flashleads in:AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1), Productivity Knowledge (1/1)
- Gemini 3.6 Flashleads in:Multimodal Understanding (1/1)
On average across the 4 shared benchmarks, Gemini 3.8 Flash scores 39.22 higher.
Largest single-benchmark gap: GDPval-AA v2 — Gemini 3.8 Flash 1,545 vs Gemini 3.6 Flash 1,421 (+124).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.