Gemini 3.6 Flash benchmarks
Gemini 3.6 Flash is a proprietary model from Google, released 21 Jul 2026. It ranks 29th of 51 on our overall leaderboard and 30th of 51 for reasoning. At A$2.11 per million tokens (blended), it costs about 1.7× cheaper than the median model we track. It can be called from Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia.
- CONTEXT WINDOW
- 1,048,576 tokens
- MAX OUTPUT
- 65,536 tokens
- INPUT
- text, image, video, audio
- WEIGHTS
- Proprietary
- RELEASED
- 21 Jul 2026
Gemini 3.6 Flash across our rankings.
Benchmark results.
Independent test scores are for the high effort setting. “Among tracked” ranks Gemini 3.6 Flash against the 51 models on this site; LMArena ranks run across its full leaderboard.
| BENCHMARK | RESULT | AMONG TRACKED | SOURCE DETAIL |
|---|---|---|---|
| INDEPENDENT TESTS · ARTIFICIAL ANALYSIS | |||
| AA Intelligence Index | 34.0 | #33 of 51 | high effort |
| AA Coding Index | 69.2 | #26 of 42 | high effort |
| GPQA Diamond | 92.8% | #14 of 44 | high effort |
| Humanity’s Last Exam | 40.8% | #31 of 51 | high effort |
| AA-LCR | 80.0% | #27 of 51 | high effort |
| Terminal-Bench 2.1 | 77.5% | #30 of 42 | high effort |
| τ²-Bench (banking) | 29.9% | #31 of 41 | high effort |
| SciCode | 53.4% | #28 of 46 | high effort |
| BLIND HUMAN VOTES · LMARENA | |||
| LMArena Text26,445 votes · ±5 | 1480 | #20 of 42 | #23 of 402 on LMArena · 13 Sep 2026 |
| LMArena WebDev8,263 votes · ±8 | 1537 | #27 of 45 | #34 of 129 on LMArena · 22 Sep 2026 |
| LMArena Vision5,159 votes · ±10 | 1283 | #17 of 33 | #21 of 152 on LMArena · 13 Sep 2026 |
| LMArena Document2,975 votes · ±11 | 1453 | #22 of 26 | #28 of 44 on LMArena · 13 Sep 2026 |
| LMArena Agent20,773 sessions | #39 | #35 of 37 | #39 of 46 on LMArena · 15 Sep 2026 |
What Gemini 3.6 Flash costs in Australian dollars.
List prices converted at the snapshot’s RBA rate, excluding GST. Reasoning models are billed for their thinking as output tokens, so heavier settings cost more than the job estimates show.
| PER MILLION TOKENS | AUD | USD LIST |
|---|---|---|
| Input tokens | A$1.05 | US$0.75 |
| Output tokens | A$5.26 | US$3.75 |
| Blended (3 in : 1 out) | A$2.11 | US$1.50 |
| JOB | COST (AUD) | MEDIAN MODEL |
|---|---|---|
| Customer support replyPER 1,000 REPLIES | A$3.69 | ≈ A$6.58 |
| Summarise a 30-page documentPER 100 DOCUMENTS | A$2.53 | ≈ A$4.74 |
| Agentic coding taskPER 10 TASKS | A$2.00 | ≈ A$3.72 |
Running Gemini 3.6 Flash in Australia.
It can be called from Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia. How the platforms compare →
| PLATFORM | AVAILABILITY | DETAIL |
|---|---|---|
| AWS Bedrock · Sydney | NOT OFFERED | |
| AWS Bedrock · Melbourne | NOT OFFERED | |
| Azure · Australia East | NOT OFFERED | |
| Google Vertex AI · Sydney | GLOBAL |
Compare it with.
Gemini 3.6 Flash, answered.
How much does Gemini 3.6 Flash cost in Australian dollars?
Gemini 3.6 Flash lists at US$0.75 per million input tokens and US$3.75 per million output tokens — A$1.05 and A$5.26 at A$1 = US$0.7123 (RBA, 22 Sep 2026), excluding GST. A typical customer support reply works out at about A$3.69 per 1,000 replies, before any reasoning tokens.
Can I use Gemini 3.6 Flash in Australia with data kept onshore?
Gemini 3.6 Flash can be called from Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.
Is Gemini 3.6 Flash good for coding?
It ranks 28th of 42 on our coding ranking, with an Artificial Analysis Coding Index of 69.2 and an LMArena WebDev rating of 1537 (34th of 129). The current leader is Claude Fable 5.1.
How good is Gemini 3.6 Flash at agent and automation work?
It ranks 31st of 41 on our agents ranking, completing 29.9% of τ²-Bench banking customer-service tasks and 77.5% of Terminal-Bench 2.1 tasks.
What is Gemini 3.6 Flash’s context window?
Google documents a context window of 1,048,576 tokens (1M), with up to 65,536 output tokens. On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 80.0%.
Ratings: LMArena leaderboard dataset (CC BY 4.0), rescaled for the lens scores · leaderboards to 22 Sep 2026
Evaluations, prices and speed: Artificial Analysis (artificialanalysis.ai) · fetched 23 Sep 2026
Exchange rate: Reserve Bank of Australia, table F11.1 · A$1 = US$0.7123 on 22 Sep 2026 · prices exclude GST
Snapshot 23 Sep 2026 · updated weekly · How the rankings work →