Gemini 3 Flash Preview
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
- Strongest at
- Reading & documents Top 14% of the past year's models · one benchmark so far
- Price per 1M tokens
- $0.5 / $3 input / output · Google
- Context window
- 1.05M tokens in · 65.5K out
- Since the last one
- 183 days after Gemini 2.5 Flash
Capability profile
Scored against 91 models released in the past year. 50 is the average model; further out is better.
No results yet: Computer use
Where these scores come from
Each capability combines the published benchmarks listed here, rescaled so 50 is the reference average and 15 points is one standard deviation. A hollow dot rests on a single benchmark.
- Coding SWE-Bench verified, GSO-Bench
- Writing EQ-Bench Longform Writing
- Reading & documents Vision Evals: OCR & extraction (low effort)
- Reasoning SimpleBench, ARC-AGI-2, Chess Puzzles, Mystery Game Puzzles
- Math OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private, ProofBench
- Science GPQA diamond, WeirdML v2
- Visual reasoning Vision Evals (low effort)
Price against capability
The shaded corner holds anything better and cheaper. Prices blend input and output 3 to 1.
Nothing from the past year scores higher on Reading & documents for less.
8 models from the past year score higher on Coding for less: DeepSeek V4.1 Flash, DeepSeek V3.2, Claude Haiku 5.5 and 5 more.
16 models from the past year score higher on Writing for less: Kimi K2.5, Kimi K2 Thinking, Muse Glimmer 30B and 13 more.
5 models from the past year score higher on Reasoning for less: DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash, DeepSeek V4 Pro 0813 and 2 more.
13 models from the past year score higher on Math for less: Claude Haiku 5.5, DeepSeek V3.2, GPT-6 Luna and 10 more.
7 models from the past year score higher on Science for less: DeepSeek V4.1 Flash 1017, GPT-6 Luna, GLM-5.3-Flash and 4 more.
3 models from the past year score higher on Visual reasoning for less: Claude Haiku 5.5, GPT-6 Luna, DeepSeek V4.1 Flash.
Google $0.5 / $3 · OpenRouter $0.5 / $3 · Cached input $0.05
Since Gemini 2.5 Flash
8 releases in the Gemini line.
A newer release is out: Gemini 3.8 Flash.
Epoch benchmark boards
Best result on each board it has run. The tick marks the leader.
12 more boards
Google's past year
37 release days in the past year, about one every 10 days. The next is expected around Nov 3, 2026. Forecasts ↗
Specifications
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.