Gemini 3.1 Pro benchmarks

Gemini 3.1 Pro is a proprietary model from Google, released 19 Feb 2026. It ranks 30th of 51 on our overall leaderboard and 25th of 51 for long context. At A$6.32 per million tokens (blended), it costs 1.7× the median model we track. It writes about 141 tokens a second, and answers start after 22 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.

#30 OF 51 OVERALLA$6.32 / 1M TOKENS1M CONTEXTUPDATED 23 SEP 2026
CONTEXT WINDOW
1,048,576 tokens
MAX OUTPUT
65,536 tokens
INPUT
text, image, video, audio
WEIGHTS
Proprietary
RELEASED
19 Feb 2026
OUTPUT SPEED
141 tok/s
ANSWER STARTS AFTER
22 s (thinking included)
GOOGLE DOCS
§ 02 — RESULTS

Benchmark results.

Independent test scores are for the default setting. “Among tracked” ranks Gemini 3.1 Pro against the 51 models on this site; LMArena ranks run across its full leaderboard.

ALL RESULTS8 OF 8 CORE SIGNALS
Gemini 3.1 Pro benchmark results
BENCHMARKRESULTAMONG TRACKEDSOURCE DETAIL
INDEPENDENT TESTS · ARTIFICIAL ANALYSIS
AA Intelligence Index29.7#41 of 51Default
AA Coding Index68.8#28 of 42Default
GPQA Diamond94.1%#5 of 44Default
Humanity’s Last Exam47.0%#13 of 51Default
AA-LCR82.0%#16 of 51Default
Terminal-Bench 2.173.8%#32 of 42Default
τ²-Bench (banking)21.4%#35 of 41Default
SciCode58.7%#10 of 46Default
BLIND HUMAN VOTES · LMARENA
LMArena Text106,951 votes · ±31487#12 of 42#15 of 402 on LMArena · 13 Sep 2026
LMArena WebDev22,902 votes · ±51447#41 of 45#59 of 129 on LMArena · 22 Sep 2026
LMArena Vision40,691 votes · ±61279#20 of 33#26 of 152 on LMArena · 13 Sep 2026
LMArena Document49,457 votes · ±51459#21 of 26#27 of 44 on LMArena · 13 Sep 2026
LMArena Search113,282 votes · ±51208#6 of 12#6 of 34 on LMArena · 24 Aug 2026
LMArena Agent86,017 sessions#38#34 of 37#38 of 46 on LMArena · 15 Sep 2026
§ 03 — COST

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.

LIST PRICE
Gemini 3.1 Pro price per million tokens
PER MILLION TOKENSAUDUSD LIST
Input tokensA$2.81US$2.00
Output tokensA$16.85US$12.00
Blended (3 in : 1 out)A$6.32US$4.50
EVERYDAY JOBSESTIMATES
Estimated cost of common jobs in Australian dollars
JOBCOST (AUD)MEDIAN MODEL
Customer support replyPER 1,000 REPLIESA$10.67A$6.58
Summarise a 30-page documentPER 100 DOCUMENTSA$6.96A$4.74
Agentic coding taskPER 10 TASKSA$5.56A$3.72
§ 04 — AUSTRALIA

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 →

AUSTRALIAN CLOUD REGIONS
Gemini 3.1 Pro availability in Australian cloud regions
PLATFORMAVAILABILITYDETAIL
AWS Bedrock · SydneyNOT OFFERED
AWS Bedrock · MelbourneNOT OFFERED
Azure · Australia EastNOT OFFERED
Google Vertex AI · SydneyGLOBAL

Provider docs, checked 23 Sep 2026

§ 06 — QUESTIONS

Gemini 3.1 Pro, answered.

Gemini 3.1 Pro lists at US$2.00 per million input tokens and US$12.00 per million output tokens — A$2.81 and A$16.85 at A$1 = US$0.7123 (RBA, 22 Sep 2026), excluding GST. A typical customer support reply works out at about A$10.67 per 1,000 replies, before any reasoning tokens.

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.

It ranks 32nd of 42 on our coding ranking, with an Artificial Analysis Coding Index of 68.8 and an LMArena WebDev rating of 1447 (59th of 129). The current leader is Claude Fable 5.1.

It ranks 32nd 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.

Artificial Analysis measures Gemini 3.1 Pro at about 141 tok/s of output, with the answer starting after 22 s on average once thinking time is included (default setting).

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%.

PUT THE COMPARISON TO WORK

Need help choosing and using AI for your business?