Gemini 3.6 Flash vs MAI-Code-1.1-Flash: Specs & Benchmark Comparison

Gemini 3.6 Flash is developed by Google, while MAI-Code-1.1-Flash comes from Microsoft. Gemini 3.6 Flash was released in July 2026, and MAI-Code-1.1-Flash followed a month later in August 2026. MAI-Code-1.1-Flash has a published size of about 138 billion parameters; Google has not disclosed the parameter count of Gemini 3.6 Flash.

We have 7 benchmark results for Gemini 3.6 Flash and 2 benchmark results for MAI-Code-1.1-Flash, but they overlap on a single test: Terminal-Bench 2.1, where Gemini 3.6 Flash scores 78.0% against 62.9%.

MAI-Code-1.1-Flash is the cheaper API at $0.20 per million input tokens and $1.20 per million output tokens, roughly 8 times cheaper than Gemini 3.6 Flash at $1.50 and $7.50. Gemini 3.6 Flash takes the larger context window at 1M tokens, compared with 256K for MAI-Code-1.1-Flash. Both accept text and images as input. On tooling, only Gemini 3.6 Flash supports function calling and only Gemini 3.6 Flash offers structured output.

CharacteristicGemini 3.6 FlashMAI-Code-1.1-Flash
CompanyGoogleMicrosoft
Release DateJuly 21, 2026August 11, 2026
Parameters138B
MultimodalYesYes
Context (input)1.0M256K
Context (output)66K
Input Price / 1M$1.50$0.20
Output Price / 1M$7.50$1.20
Average Score68.0%67.8%
Benchmarks
Terminal-Bench 2.178.0%62.9%

Visual Benchmark Comparison

Gemini 3.6 Flash
MAI-Code-1.1-Flash
Terminal-Bench 2.10.8 vs 0.6
0.8
0.6

Verdict

MAI-Code-1.1-Flash leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: Gemini 3.6 Flash — 0.7, MAI-Code-1.1-Flash — 0.7.

API Cost

MAI-Code-1.1-Flash is 6.4x cheaper: input $0.20/1M vs $1.50/1M tokens.

Context Window

Gemini 3.6 Flash supports a larger context: 1M vs 256K tokens.

Recency

MAI-Code-1.1-Flash is newer: released 8/11/2026 vs 7/21/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Gemini 3.6 Flash or MAI-Code-1.1-Flash?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — Gemini 3.6 Flash or MAI-Code-1.1-Flash?
MAI-Code-1.1-Flash is cheaper for input: $0.20 per 1M tokens vs $1.50.
Which has a larger context window — Gemini 3.6 Flash or MAI-Code-1.1-Flash?
Gemini 3.6 Flash supports a larger context: 1,048,576 tokens vs 256,000.

The Gemini 3.6 Flash and MAI-Code-1.1-Flash comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Gemini 3.6 Flash or MAI-Code-1.1-Flash page. See also the complete list of AI model comparisons.