Google: Gemini 3 Flash Preview
google/gemini-3-flash-preview
Context: 1,048,576In: $0.50/1MOut: $3.00/1MUpdated 2026-08-05
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...
Intelligence
—
Coding
—
Agentic
—
Metric profile
Trend over time
Intelligence
—
Coding
—
Agentic
—
Only 1 snapshot so far (data refreshes daily) — the trend line appears after the 2nd snapshot.
Classic evals (curated from model cards)
Google Gemini — manually maintained, may lag releases
MMLU-Pro
80.4%
GPQA Diamond
81.7%
HumanEval
94%
AIME 2025
41.7%
Design Arena (ELO by category)
| Category | ELO | Win rate | Rank |
|---|---|---|---|
| 3d | 1239 | 62.7% | #36 |
| website | 1219 | 57% | #42 |
| codecategories | 1218 | 57.6% | #41 |
| gamedev | 1211 | 58.3% | #44 |
| godotgamedev | 1161 | 50.6% | #14 |
| webapps | 1160 | 48.4% | #25 |
| mobileapps | 1151 | 46.6% | #25 |
| fullstack | 1104 | 47.1% | #21 |
| androidnative | 1083 | 48.1% | #27 |
| agenticslides(python-pptx) | 1075 | 39.3% | #9 |
| agenticslides | 1073 | 39.3% | #9 |
| python-pptxslides | 1019 | 38.3% | #19 |