Model evidence profile

Gemini 3.1 Pro

Name: Gemini 3.1 Pro benchmark evidence
Creator: Google
Published: 2026-08-30T02:15:58.000Z

Google · Proprietary · Reasoning

currentestimated

Overall public score: 56.25
Source rank: #99
Evidence coverage: 7 benchmarks · 2 sources

Strongest published evidencePublic overall score 56.25 at source rank #99.

Validate before choosingValidate the selected route price, context limits, and evidence freshness before choosing.

Revision benchmark_3b14dc55ef5307cfe91356d3ea348101 · Published Aug 30, 2026 · Checked Aug 30, 2026 · stale

Relative field position

Capability radar

Percentiles use eligible source ranks. Missing axes remain unavailable and never become zero.

Agentic percentile: 9.4 percentileRank #127 of 140
Coding percentile: 41.7 percentileRank #85 of 145
Knowledge percentile: 44.4 percentileRank #31 of 55
Math percentile: Math: Unavailable
Multimodal grounded percentile: 79.4 percentileRank #8 of 35
Overall percentile: Overall: Unavailable
Reasoning percentile: Reasoning: Unavailable

Published measurements

Category scores

Scores retain their source units; percentile and rank appear only for eligible fields.

Agenticestimated

33.8

Rank: #127 of 140
Percentile: 9.4%
Benchmarks: 7

Codingestimated

49.3

Rank: #85 of 145
Percentile: 41.7%
Benchmarks: 7

Knowledgeestimated

66.7

Rank: #31 of 55
Percentile: 44.4%
Benchmarks: 7

Mathestimated

55.1

Rank: Not ranked
Percentile: Unavailable
Benchmarks: 7

Multimodal groundedestimated

76.8

Rank: #8 of 35
Percentile: 79.4%
Benchmarks: 7

Overallestimated

56.3

Rank: #99
Percentile: Unavailable
Benchmarks: 7

Reasoningestimated

72.4

Rank: Not ranked
Percentile: Unavailable
Benchmarks: 7

Route-specific facts

Pricing and specifications

Conflicting routes remain separate and attributable.

googlebenchlm:gemini-3-1-pro

primary

Input / 1M: $2.00
Cached input / 1M: $0.20
Output / 1M: $12.00
Context: 1,000,000

View price source

Context window: 1,000,000
Maximum output: Unavailable
Input modalities: Unavailable
Output modalities: Unavailable
Release date: 2026-02-19
Self hosting: Not verified

Auditable evidence

Benchmark ledger

Display values, source ranks, and provenance remain visible without implying unsupported aggregate weight.

agentic

Score	Rank	Weight	Last Updated	Source
33.84	#127	Not published	Aug 29, 2026	BenchLM

coding

Score	Rank	Weight	Last Updated	Source
49.30	#85	Not published	Aug 29, 2026	BenchLM

knowledge

Score	Rank	Weight	Last Updated	Source
66.70	#31	Not published	Aug 29, 2026	BenchLM

math

Score	Rank	Weight	Last Updated	Source
55.10	Not ranked	Not published	Aug 29, 2026	BenchLM

multimodalGrounded

Score	Rank	Weight	Last Updated	Source
76.80	#8	Not published	Aug 29, 2026	BenchLM

reasoning

Score	Rank	Weight	Last Updated	Source
72.40	Not ranked	Not published	Aug 29, 2026	BenchLM

overall

Score	Rank	Weight	Last Updated	Source
56.25	#99	Not published	Aug 29, 2026	BenchLM