head-to-head

Google: Gemini 3.7 Flash vs Google: Gemini 3.6 Flash (batch)

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-09-28.

Google: Gemini 3.7 Flash Google: Gemini 3.6 Flash (batch)
Vendorgooglegoogle
Quality Score100100
Benchmark Score65.556.1
Input Price$0.75/M$0.38/M
Output Price$3.75/M$1.88/M
Context Window1,048,5761,048,576
Max Output65,53665,536
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio✓✓
Benchmark Scores
ai_index64.456.1

The verdict

For a sample job of 1 million input tokens and 250,000 output tokens, Gemini 3.6 Flash (batch) costs $0.84 and Gemini 3.7 Flash costs $1.69, so Gemini 3.6 Flash (batch) is about 2.0 times cheaper for the same work.

Both read up to 1,048,576 tokens at once, roughly 1,573 pages of text.

On our blended benchmark score Gemini 3.7 Flash leads 65.5 to 56.1.

Across the 20 tasks where they differ, Gemini 3.7 Flash scores higher on 16 (SQL Generation, Code Review, Code Refactoring and others), Gemini 3.6 Flash (batch) on 4 (Code Completion, JSON Extraction, Bulk Data Labeling and others).

Gemini 3.7 Flash was released in August 2026 and Gemini 3.6 Flash (batch) in July 2026.

Pick Gemini 3.7 Flash if you need benchmark performance or the stronger all-round task scores; pick Gemini 3.6 Flash (batch) if you need lower cost.

Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.

Who wins by task?

TaskGoogle: Gemini 3.7 FlashGoogle: Gemini 3.6 Flash (batch)
SQL Generation 141 140
Code Review 144 142
Code Completion 132 132
Code Refactoring 146 145
Bug Fixing 148 146
Unit Test Generation 131 130
Code Documentation 136 136
Regex Writing 125 125
CI/CD Pipelines 127 126
Frontend Component Design 129 128
Data Analysis 133 132
CSV / Spreadsheet Cleanup 136 136
ETL Scripting 137 135
JSON Extraction 131 131
Bulk Data Labeling 128 129
OCR / Document Parsing 134 133
Table Extraction from PDFs 134 133
Long-Document Summarization 147 146
Short-Form Summarization 126 126
Blog Post Writing 129 128

Scores reflect capability match + benchmark data + pricing for each task. Methodology →

Related comparisons

Anthropic: Claude Opus 5.5 (batch) vs Google: Gemini 3.7 Flash Anthropic: Claude Opus 5 (batch) vs Google: Gemini 3.6 Flash (batch) ByteDance Seed: Seed-2.0-Code vs Google: Gemini 3.6 Flash (batch) ByteDance Seed: Seed 2.1 Turbo vs Google: Gemini 3.6 Flash (batch) Cohere: Command A+ vs Google: Gemini 3.7 Flash DeepSeek: DeepSeek Flash Latest vs Google: Gemini 3.6 Flash (batch) DeepSeek: DeepSeek Flash Latest vs Google: Gemini 3.7 Flash DeepSeek: DeepSeek V4.1 Flash (batch) vs Google: Gemini 3.7 Flash

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.