Head-to-head comparison

GPT-6 Sol vs. Gemini 3.1 Pro Preview

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series: 14
distinct benchmarks: 14
latest retrieval: 2026-09-23

First modelSecond model

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for GPT-6 Sol and Gemini 3.1 Pro Preview
Attribute	GPT-6 Sol	Gemini 3.1 Pro Preview
Provider	OpenAI	Google
Released	Sep 22, 2026	Feb 19, 2026
Availability	Active	Preview
Model type	Proprietary	Proprietary
Parameters	Not published	Not published
Architecture	Not published	Not published
Context window	1,050,000 tokens	1,048,576 tokens
Knowledge cutoff	April 20, 2026	Not published
Technical sources	Model, Context	Model

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for GPT-6 Sol and Gemini 3.1 Pro Preview
Price type	GPT-6 Sol	Gemini 3.1 Pro Preview
API input	$2 ≤272K / $4 >272K	$2 ≤200K / $4 >200K
API output	$10 ≤272K / $15 >272K	$12 ≤200K / $18 >200K
Cache read	$0.2 ≤272K / $0.4 >272K	$0.2 ≤200K / $0.4 >200K
Cache write (5 min.)	$2.5 ≤272K / $5 >272K	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

GPT-6 SolGemini 3.1 Pro Preview

API inputUSD per 1M tokens, base tier

GPT-6 Sol$2

Gemini 3.1 Pro Preview$2

API outputUSD per 1M tokens, base tier

GPT-6 Sol$10

Gemini 3.1 Pro Preview$12

Cache readUSD per 1M tokens, base tier

GPT-6 Sol$0.2

Gemini 3.1 Pro Preview$0.2

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

Provider pricing for GPT-6 Sol and Gemini 3.1 Pro Preview
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
GPT-6 Sol	OpenAI	Direct from developerUp to 272,000 context tokens	$2	$10	Source09/22/2026
	OpenAI	Direct from developerAbove 272,000 context tokens	$4	$15	Source09/22/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us-east-1	$2.2	$11	Source09/23/2026
	Azure	Via OpenRouterazure	$2	$10	Source09/23/2026
	Azure	Via OpenRouterazure/eu	$2.2	$11	Source09/23/2026
	Azure	Via OpenRouterazure/us	$2.2	$11	Source09/23/2026
	OpenAI	Via OpenRouteropenai	$2	$10	Source09/23/2026
	OpenAI	Via OpenRouteropenai/fast	$4	$20	Source09/23/2026
	OpenAI	Via OpenRouteropenai/flex	Lowest listed price: $1	Lowest listed price: $5	Source09/23/2026
Gemini 3.1 Pro Preview	Google	Direct from developerUp to 200,000 context tokens	$2	$12	Source09/22/2026
	Google	Direct from developerAbove 200,000 context tokens	$4	$18	Source09/22/2026
	Google	Via OpenRoutergoogle-vertex/global	$2	$12	Source09/23/2026
	Google	Via OpenRoutergoogle-vertex/global/flex	Lowest listed price: $1	Lowest listed price: $6	Source09/23/2026
	Google	Via OpenRoutergoogle-vertex/global/priority	$3.6	$21.6	Source09/23/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio	$2	$12	Source09/23/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/flex	Lowest listed price: $1	Lowest listed price: $6	Source09/23/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/priority	$3.6	$21.6	Source09/23/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

GPT-6 Sol

Gemini 3.1 Pro Preview

Coding: 100 / 22.2 (3 benchmark families)

Mathematics: 100 / 31.3 (1 benchmark family)

Finance: 100 / 80.6 (2 benchmark families)

Legal: 100 / 35.8 (2 benchmark families)

Agentic tasks: 100 / 85.1 (1 benchmark family)

Productivity: 100 / 95 (1 benchmark family)

Health: 89.8 / 96.4 (2 benchmark families)

Education: 92 / 100 (1 benchmark family)

14 matched rows from 14 benchmark families were considered. The radar shows 8 of 9 comparable categories.

GPT-6 SolGemini 3.1 Pro Preview

Code MigrationOverall. Higher is better. No documented setup difference

GPT-6 Sol57.195 %

Gemini 3.1 Pro Preview17.313 %

EMBOverall. Higher is better. No documented setup difference

GPT-6 Sol71.53 %

Gemini 3.1 Pro Preview52.616 %

Finance Agent (v2)Overall. Higher is better. No documented setup difference

GPT-6 Sol49.05 %

Gemini 3.1 Pro Preview42.982 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference

GPT-6 Sol1.667 %

Gemini 3.1 Pro Preview0 %

Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference

GPT-6 Sol28.846 %

Gemini 3.1 Pro Preview20.673 %

MedCodeOverall. Higher is better. No documented setup difference

GPT-6 Sol47.072 %

Gemini 3.1 Pro Preview59.062 %

MedScribeOverall. Higher is better. No documented setup difference

GPT-6 Sol82.034 %

Gemini 3.1 Pro Preview76.114 %

ProgramBenchOverall. Higher is better. No documented setup difference

GPT-6 Sol2 %

Gemini 3.1 Pro Preview0 %

ProofBenchOverall. Higher is better. No documented setup difference

GPT-6 Sol83 %

Gemini 3.1 Pro Preview26 %

Public Benefits Bench v1.1Overall. Higher is better. No documented setup difference

GPT-6 Sol56.631 %

Gemini 3.1 Pro Preview53.789 %

SAGEOverall. Higher is better. No documented setup difference

GPT-6 Sol44.793 %

Gemini 3.1 Pro Preview48.677 %

Terminal-Bench 2.1Overall. Higher is better. No documented setup difference

GPT-6 Sol83.146 %

Gemini 3.1 Pro Preview70.787 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-6 Sol and Gemini 3.1 Pro Preview
Benchmark and task	GPT-6 Sol	Gemini 3.1 Pro Preview	Source
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner57.195 %	17.313 %	Vals AI Source details Data as of: 09/22/2026
EMBOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner71.53 %	52.616 %	Vals AI Source details Data as of: 09/22/2026
Finance Agent (v2)Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner49.05 %	42.982 %	Vals AI Source details Data as of: 09/22/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better	Winner1.667 %	0 %	Vals AI Source details Data as of: 09/22/2026
Legal Research BenchOverall · All-pass Test details No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better	Winner28.846 %	20.673 %	Vals AI Source details Data as of: 09/22/2026
MedCodeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	47.072 %	Winner59.062 %	Vals AI Source details Data as of: 09/22/2026
MedScribeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner82.034 %	76.114 %	Vals AI Source details Data as of: 09/22/2026
ProgramBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner2 %	0 %	Vals AI Source details Data as of: 09/22/2026
ProofBenchOverall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better	Winner83 %	26 %	Vals AI Source details Data as of: 09/22/2026
Public Benefits Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better	Winner56.631 %	53.789 %	Vals AI Source details Data as of: 09/22/2026
SAGEOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	44.793 %	Winner48.677 %	Vals AI Source details Data as of: 09/22/2026
Terminal-Bench 2.1Overall Test details No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better	Winner83.146 %	70.787 %	Vals AI Source details Data as of: 09/22/2026
Vals IndexOverall Test details No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better	Winner62.569 %	41.903 %	Vals AI Source details Data as of: 09/22/2026
Vibe Code Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands	Winner87.824 %	32.034 %	Vals AI Source details Data as of: 09/22/2026
Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

GPT-6 Sol

Not tested yet

Gemini 3.1 Pro Preview

API access was unavailable for this run. The model was not evaluated.

Reasoning (requested): high

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: google/gemini-3.1-pro-preview
Reasoning setting: high
Pinned endpoint: Google AI Studio | google/gemini-3.1-pro-preview-20260219
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Compare GPT-6 Sol and Gemini 3.1 Pro Preview with other leading models using the same data and benchmark logic.

View the complete LLM comparison