Gemini 3.5 Flash
Gemini 3.5 Flash is an API-only (closed weights) language model from Google, released May 19, 2026. The context window is 1M tokens. On the Epoch Capabilities Index it scores 155.3, rank 43 of 256 rated models. API price: $1.5 input / $9 output per million tokens.
Check it against your own PC →
Lab
Google
Released
May 19, 2026
Weights
API-only (closed weights)
Parameters
–
Context
1M
Price / M tokens
$1.5 / $9 in / out
Epoch ECI
155.3 #43
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 27.7 | Chess Puzzles, SimpleBench, Mystery Game Puzzles |
| Math | 47.2 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 48.2 | SWE-bench Verified, DeepSWE |
| Knowledge | 81.4 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 95.6% |
| GPQA Diamond | 94.2% |
| SWE-bench Verified | 79.3% |
| SimpleBench | 72.0% |
| SimpleQA Verified | 66.2% |
| FrontierMath (Tiers 1–3) | 66.1% |
| Chess Puzzles | 42.1% |
| DeepSWE | 37.4% |
| ProofBench | 31.0% |
| FrontierMath-Tier-4-v2-Private | 26.8% |
| Mystery Game Puzzles | 25.1% |
| EBR-bench | 4.8% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
Gemini 3.8 Flash · Kimi K3 · Gemini 3.7 Flash · Muse Spark 1.3 · GPT-5.4 · Grok 4.6 · Qwen 3.8 Max · Claude Opus 4.7
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