Gemini 3 Flash
Gemini 3 Flash is an API-only (closed weights) language model from Google, released December 17, 2025. The context window is 1M tokens. On the Epoch Capabilities Index it scores 152.3, rank 59 of 256 rated models. API price: $0.5 input / $3 output per million tokens.
Check it against your own PC →
Lab
Google
Released
December 17, 2025
Weights
API-only (closed weights)
Parameters
–
Context
1M
Price / M tokens
$0.5 / $3 in / out
Epoch ECI
152.3 #59
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 20.2 | Chess Puzzles, SimpleBench, Mystery Game Puzzles |
| Math | 40.0 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 49.9 | GSO-Bench, Terminal Bench, SWE-bench Verified |
| Knowledge | 80.4 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 95.6% |
| GPQA Diamond | 89.4% |
| SWE-bench Verified | 75.4% |
| SimpleQA Verified | 66.8% |
| Terminal-Bench | 64.3% |
| FrontierMath (Tiers 1–3) | 53.9% |
| SimpleBench | 53.3% |
| Balrog | 48.1% |
| Chess Puzzles | 36.9% |
| Mystery Game Puzzles | 18.5% |
| FrontierMath-Tier-4-v2-Private | 17.1% |
| ProofBench | 15.0% |
| GSO-Bench | 9.8% |
Links
Models with a similar score
Grok 4.7 · Gemini 3.1 Pro · Qwen3.8 Max (0902) · DeepSeek V4 Pro 0813 · Muse Spark Open · Gemini 3.5 Flash · Gemini 3.6 Flash · Muse Spark 1.2
More from Google
Gemini 4 Carbon · Gemini 4 Argon · Gemini 3.8 Flash · Gemini 3.7 Flash · Gemini 3.6 Flash · Gemini 3.5 Flash-Lite · Gemini 3.5 Flash Cyber · Gemma 4 E4B