Google model product
Gemini 3.1 Pro
1 Pro is a Google large language model for complex tasks involving broad world knowledge and advanced reasoning across modalities.
Updated Oct 23, 2026. Default version: Gemini 3.1 Pro
LLMBoard Score75.4Gemini 3.1 Pro
Coverage80%20 benchmark families
Context window1MTokens
Official input price$2Google API
Gemini 3.1 Pro Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 3.1 Pro Benchmark Results
Benchmark scores for Gemini 3.1 Pro.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkLiveCodeBench Pro | Score2,887.00 points | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| Benchmarkt2-bench | Score99.30% | Rank01 | Participants23 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score92.60% | Rank02 | Participants51 | Percentile98.00% | EvidenceC | Evaluated |
| BenchmarkARC-AGI v2 | Score77.10% | Rank03 | Participants19 | Percentile88.89% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score59.00% | Rank03 | Participants31 | Percentile93.33% | EvidenceC | Evaluated |
| BenchmarkLiveBench instruction (2026-06-25) | Score79.10 score | Rank03 | Participants43 | Percentile95.24% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score94.30% | Rank04 | Participants256 | Percentile98.82% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score79.93% | Rank04 | Participants38 | Percentile91.89% | EvidenceB | Evaluated |
| BenchmarkAPEX-Agents | Score33.50% | Rank06 | Participants11 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkAA GPQA Diamond | Score94.14% | Rank07 | Participants199 | Percentile96.97% | EvidenceB | EvaluatedN/A |
| BenchmarkAA SciCode Subtasks | Score58.68% | Rank08 | Participants89 | Percentile92.05% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score54.85% | Rank09 | Participants201 | Percentile96.00% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score47.03% | Rank10 | Participants200 | Percentile95.48% | EvidenceB | EvaluatedN/A |
| BenchmarkBrowseComp | Score85.90% | Rank11 | Participants70 | Percentile85.51% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score80.60% | Rank11 | Participants120 | Percentile91.60% | EvidenceC | Evaluated |
| BenchmarkLM Arena Search Style Control | Score1,206.62 rating | Rank11 | Participants33 | Percentile68.75% | EvidenceA | Evaluated |
| BenchmarkAA IFBench | Score77.14% | Rank11 | Participants168 | Percentile94.01% | EvidenceB | EvaluatedN/A |
| BenchmarkFrontierSWE | Score40.00% | Rank12 | Participants17 | Percentile31.25% | EvidenceB | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score68.50% | Rank12 | Participants53 | Percentile78.85% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score0.00% | Rank13 | Participants15 | Percentile14.29% | EvidenceB | Evaluated |
| BenchmarkMMMU-Pro | Score80.50% | Rank13 | Participants73 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkLM Arena Search | Score1,208.81 rating | Rank13 | Participants33 | Percentile62.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,480.07 rating | Rank15 | Participants218 | Percentile93.55% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,486.84 rating | Rank15 | Participants218 | Percentile93.55% | EvidenceA | Evaluated |
| BenchmarkFinance Agent v2 | Score42.98% | Rank16 | Participants29 | Percentile46.43% | EvidenceB | Evaluated |
| BenchmarkLiveBench math (2026-06-25) | Score91.05 score | Rank17 | Participants43 | Percentile61.90% | EvidenceB | EvaluatedN/A |
| BenchmarkMRCR v2 (8-needle) | Score26.30% | Rank18 | Participants25 | Percentile29.17% | EvidenceC | Evaluated |
| BenchmarkLM Arena Search Factuality | Score1,196.99 rating | Rank18 | Participants33 | Percentile46.88% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,295.78 rating | Rank18 | Participants113 | Percentile84.82% | EvidenceA | Evaluated |
| BenchmarkAA LCR v1.1 | Score82.00% | Rank19 | Participants193 | Percentile90.63% | EvidenceB | EvaluatedN/A |
Gemini 3.1 Pro Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorycaptioning | Rank01 | Rating / score1,344.89 | Votes137 | ObservationsN/A | Result date |
| Arenavision style control | Categorycaptioning | Rank01 | Rating / score1,281.62 | Votes137 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank03 | Rating / score1,329.70 | Votes388 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank03 | Rating / score1,283.98 | Votes388 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank04 | Rating / score1,322.39 | Votes1,885 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank04 | Rating / score1,299.96 | Votes1,885 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank05 | Rating / score1,459.07 | Votes1,302 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank05 | Rating / score1,474.98 | Votes1,564 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank06 | Rating / score1,479.76 | Votes934 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank06 | Rating / score1,300.56 | Votes3,296 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank07 | Rating / score1,454.97 | Votes1,140 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank07 | Rating / score1,324.19 | Votes3,296 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank08 | Rating / score1,497.68 | Votes2,473 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank08 | Rating / score1,497.25 | Votes14,843 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank09 | Rating / score1,475.88 | Votes3,156 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank09 | Rating / score1,481.93 | Votes33,206 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank09 | Rating / score1,501.83 | Votes14,843 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank10 | Rating / score1,465.31 | Votes30,047 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank10 | Rating / score1,481.10 | Votes33,206 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank10 | Rating / score1,491.49 | Votes1,582 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank10 | Rating / score1,480.83 | Votes24,045 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank10 | Rating / score1,469.54 | Votes30,047 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank10 | Rating / score1,496.19 | Votes21,947 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank11 | Rating / score1,206.62 | Votes151,436 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank11 | Rating / score1,482.00 | Votes24,045 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank11 | Rating / score1,476.31 | Votes72,740 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank11 | Rating / score1,496.26 | Votes12,227 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank11 | Rating / score1,363.82 | Votes3,186 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank12 | Rating / score1,490.03 | Votes2,146 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank12 | Rating / score1,465.21 | Votes21,111 | ObservationsN/A | Result date |
Gemini 3.1 Pro Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $2 input, $12 output per 1M
- Official provider
- Lowest third-party
- From $1 input, $6 output per 1M via Kilo Gateway
- Tracked offerings
- 28
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKilo Gateway | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderVertex | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderGoogle | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderImpossibl | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderAuriko | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderDaoXE | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderFastRouter | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderZenMux | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderPerplexity Agent | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderOfox | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderRequesty | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderEden AI | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderAbacus | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| Provider302.AI | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderOpper | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderTempr Gateway | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderAI/ML API | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderPrime Inference | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderStandard Compute | Provider model IDgoogle/gemini-3.1-pro-preview | Regionglobal | Input / 1M$2 | Output / 1M$12 | Context1M | Updated |
| ProviderPoe | Provider model IDgoogle/gemini-3.1-pro | Regionglobal | Input / 1M$2.02 | Output / 1M$12.12 | Context1M | Updated |
| ProviderVivgrid | Provider model IDgemini-3.1-pro-preview | Regionglobal | Input / 1M$4 | Output / 1M$12 | Context1M | Updated |
Gemini 3.1 Pro Runtime Performance
Provider-specific output speed and catalog latency for Gemini 3.1 Pro. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed90.00 tok/s | Catalog Latency0.60 s | Max Input1M | Max Output65.5K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemini 3.1 Pro Specifications
Technical details for the model's default version.
- Version
- Gemini 3.1 Pro
- Released
- Feb 19, 2026
- Knowledge cutoff
- Jan 31, 2025
- Parameters
- N/A
- Context window
- 1M
- Max output
- 1M
- Inputs
- audio, image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini 3.1 Pro Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini 3.1 Pro | Released | LLMBoard75.41 | ParametersN/A | Context1M | Max output1M | Open weightsNo | LicenseProprietary |
Models similar to Gemini 3.1 Pro
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 3.5 Flash
GOGoogle
Gemini 3.6 Flash
GOGoogle
Gemini 3.7 Flash
GOGoogle
Gemini 3.8 Flash
GOGoogle
Gemini 3 Pro
GOGoogle
Gemini 3 Flash
What is Gemini 3.1 Pro?
Key information about Gemini 3.1 Pro and its available data.
1 Pro is the latest model in the Gemini 3 series, with dynamic thinking enabled by default. It has a 1 million-token input context window and supports up to 64k output tokens.
Data as of 2026-10-22.
FAQ
Common questions about Gemini 3.1 Pro.
When was Gemini 3.1 Pro released?
Gemini 3.1 Pro's default version was released on Feb 19, 2026.
How much does Gemini 3.1 Pro cost?
Gemini 3.1 Pro's official API price is $2 per million input tokens and $12 per million output tokens via Google. The lowest tracked third-party offer starts at $1 input and $6 output via Kilo Gateway.
Who created Gemini 3.1 Pro?
Gemini 3.1 Pro was created by Google.
What is the context window for Gemini 3.1 Pro?
The default version has a 1M token context window.
Is Gemini 3.1 Pro open weight?
No. The default version is not marked as having publicly available weights.