Gemini 3.1 Pro benchmarks
Gemini 3.1 Pro is a proprietary model from Google, released 19 Feb 2026. It ranks 32nd of 54 on our overall leaderboard and 27th of 54 for long context. At A$6.48 per million tokens (blended), it costs 1.5× the median model we track. It writes about 127 tokens a second, and answers start after 27 s on average, thinking included. 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
- 19 Feb 2026
- OUTPUT SPEED
- 127 tok/s
- ANSWER STARTS AFTER
- 27 s (thinking included)
Gemini 3.1 Pro across our rankings.
Benchmark results.
Independent test scores are for the default setting. “Among tracked” ranks Gemini 3.1 Pro against the 54 models on this site; LMArena ranks run across its full leaderboard.
| BENCHMARK | RESULT | AMONG TRACKED | SOURCE DETAIL |
|---|---|---|---|
| INDEPENDENT TESTS · ARTIFICIAL ANALYSIS | |||
| AA Intelligence Index | 29.7 | #44 of 54 | Default |
| AA Coding Index | 68.8 | #28 of 42 | Default |
| GPQA Diamond | 94.1% | #5 of 44 | Default |
| Humanity’s Last Exam | 47.0% | #16 of 54 | Default |
| AA-LCR | 82.0% | #18 of 54 | Default |
| Terminal-Bench 2.1 | 73.8% | #32 of 42 | Default |
| τ²-Bench (banking) | 21.4% | #35 of 41 | Default |
| SciCode | 58.7% | #12 of 49 | Default |
| BLIND HUMAN VOTES · LMARENA | |||
| LMArena Text121,225 votes · ±3 | 1487 | #15 of 49 | #18 of 410 on LMArena · 30 Sep 2026 |
| LMArena WebDev24,319 votes · ±5 | 1446 | #47 of 52 | #66 of 137 on LMArena · 30 Sep 2026 |
| LMArena Vision45,204 votes · ±5 | 1280 | #21 of 36 | #25 of 156 on LMArena · 28 Sep 2026 |
| LMArena Document49,457 votes · ±5 | 1459 | #21 of 26 | #27 of 44 on LMArena · 13 Sep 2026 |
| LMArena Search113,282 votes · ±5 | 1208 | #6 of 12 | #6 of 34 on LMArena · 24 Aug 2026 |
| LMArena Agent86,482 sessions | #41 | #39 of 42 | #41 of 46 on LMArena · 30 Sep 2026 |
What Gemini 3.1 Pro 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$2.88 | US$2.00 |
| Output tokens | A$17.27 | US$12.00 |
| Blended (3 in : 1 out) | A$6.48 | US$4.50 |
| JOB | COST (AUD) | MEDIAN MODEL |
|---|---|---|
| Customer support replyPER 1,000 REPLIES | A$10.94 | ≈ A$8.20 |
| Summarise a 30-page documentPER 100 DOCUMENTS | A$7.14 | ≈ A$5.35 |
| Agentic coding taskPER 10 TASKS | A$5.70 | ≈ A$4.27 |
Running Gemini 3.1 Pro 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 3.1 Pro, answered.
How much does Gemini 3.1 Pro cost in Australian dollars?
Gemini 3.1 Pro lists at US$2.00 per million input tokens and US$12.00 per million output tokens — A$2.88 and A$17.27 at A$1 = US$0.6949 (RBA, 1 Oct 2026), excluding GST. A typical customer support reply works out at about A$10.94 per 1,000 replies, before any reasoning tokens.
Can I use Gemini 3.1 Pro in Australia with data kept onshore?
Gemini 3.1 Pro 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 3.1 Pro good for coding?
It ranks 32nd of 42 on our coding ranking, with an Artificial Analysis Coding Index of 68.8 and an LMArena WebDev rating of 1446 (66th of 137). The current leader is Claude Fable 5.1.
How good is Gemini 3.1 Pro at agent and automation work?
It ranks 33rd of 41 on our agents ranking, completing 21.4% of τ²-Bench banking customer-service tasks and 73.8% of Terminal-Bench 2.1 tasks.
How fast is Gemini 3.1 Pro?
Artificial Analysis measures Gemini 3.1 Pro at about 127 tok/s of output, with the answer starting after 27 s on average once thinking time is included (default setting).
What is Gemini 3.1 Pro’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 82.0%.
Ratings: LMArena leaderboard dataset (CC BY 4.0), rescaled for the lens scores · leaderboards to 30 Sep 2026
Evaluations, prices and speed: Artificial Analysis (artificialanalysis.ai) · fetched 1 Oct 2026
Exchange rate: Reserve Bank of Australia, table F11.1 · A$1 = US$0.6949 on 1 Oct 2026 · prices exclude GST
Snapshot 2 Oct 2026 · updated weekly · How the rankings work →