Skip to main content

Head-to-head comparison

GPT-6 Sol vs. GPT-5.4 mini

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

shared result series
10
distinct benchmarks
10
latest retrieval
2026-09-23

Change model selection

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 GPT-5.4 mini
AttributeGPT-6 SolGPT-5.4 mini
ProviderOpenAIOpenAI
ReleasedSep 22, 2026Mar 17, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,050,000 tokens400,000 tokens
Knowledge cutoffApril 20, 2026August 31, 2025
Technical sourcesModel, ContextModel

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 GPT-5.4 mini
Price typeGPT-6 SolGPT-5.4 mini
API input$2 ≤272K / $4 >272K$0.75
API output$10 ≤272K / $15 >272K$4.5
Cache read$0.2 ≤272K / $0.4 >272K$0.07
Cache write (5 min.)$2.5 ≤272K / $5 >272KNot listed
Cache write (1 hr.)Not listedNot listed
Price verified09/22/2026 Source09/22/2026 Source
GPT-6 SolGPT-5.4 mini
API inputUSD per 1M tokens, base tier
GPT-6 Sol$2
GPT-5.4 miniLower price$0.75
API outputUSD per 1M tokens, base tier
GPT-6 Sol$10
GPT-5.4 miniLower price$4.5
Cache readUSD per 1M tokens, base tier
GPT-6 Sol$0.2
GPT-5.4 miniLower price$0.075

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 GPT-5.4 mini
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
GPT-6 SolOpenAIDirect from developerUp to 272,000 context tokens$2$10Source09/22/2026
OpenAIDirect from developerAbove 272,000 context tokens$4$15Source09/22/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$2.2$11Source09/23/2026
AzureVia OpenRouterazure$2$10Source09/23/2026
AzureVia OpenRouterazure/eu$2.2$11Source09/23/2026
AzureVia OpenRouterazure/us$2.2$11Source09/23/2026
OpenAIVia OpenRouteropenai$2$10Source09/23/2026
OpenAIVia OpenRouteropenai/fast$4$20Source09/23/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $1Lowest listed price: $5Source09/23/2026
GPT-5.4 miniOpenAIDirect from developerStandard API$0.75$4.5Source09/22/2026
AzureVia OpenRouterazure$0.75$4.5Source09/23/2026
AzureVia OpenRouterazure/us$0.825$4.95Source09/23/2026
OpenAIVia OpenRouteropenai$0.75$4.5Source09/23/2026
OpenAIVia OpenRouteropenai/fast$1.5$9Source09/23/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $0.375Lowest listed price: $2.25Source09/23/2026

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.

255075100CodingFinanceLegalAgentic tasksEducationOverall
GPT-6 Sol
GPT-5.4 mini
Coding: 100 / 25.7 (3 benchmark families)
Finance: 100 / 78 (2 benchmark families)
Legal: 100 / 21.7 (2 benchmark families)
Agentic tasks: 100 / 65.8 (1 benchmark family)
Education: 88.2 / 100 (1 benchmark family)
Overall: 100 / 63.3 (1 benchmark family)

10 matched rows from 10 benchmark families were considered. The radar shows 6 of 6 comparable categories.

GPT-6 SolGPT-5.4 mini
Code MigrationOverall. Higher is better. No documented setup difference
GPT-6 SolWinner57.195 %
GPT-5.4 mini12.936 %
EMBOverall. Higher is better. No documented setup difference
GPT-6 SolWinner71.53 %
GPT-5.4 mini45.426 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
GPT-6 SolWinner49.05 %
GPT-5.4 mini45.36 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-6 SolWinner1.667 %
GPT-5.4 mini0 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
GPT-6 SolWinner28.846 %
GPT-5.4 mini12.5 %
ProgramBenchOverall. Higher is better. No documented setup difference
GPT-6 SolWinner2 %
GPT-5.4 mini0 %
SAGEOverall. Higher is better. No documented setup difference
GPT-6 Sol44.793 %
GPT-5.4 miniWinner50.813 %
Terminal-Bench 2.1Overall. Higher is better. No documented setup difference
GPT-6 SolWinner83.146 %
GPT-5.4 mini54.682 %
Vals IndexOverall. Higher is better. No documented setup difference
GPT-6 SolWinner62.569 %
GPT-5.4 mini39.632 %
Vibe Code Bench v1.1Overall. Higher is better. No documented setup difference
GPT-6 SolWinner87.824 %
GPT-5.4 mini47.969 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-6 Sol and GPT-5.4 mini
Benchmark and taskGPT-6 SolGPT-5.4 miniSource
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner57.195 %
12.936 %
Vals AI
Source details
Data as of: 09/22/2026
EMBOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner71.53 %
45.426 %
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 betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner49.05 %
45.36 %
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 betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
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 betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner28.846 %
12.5 %
Vals AI
Source details
Data as of: 09/22/2026
ProgramBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner2 %
0 %
Vals AI
Source details
Data as of: 09/22/2026
SAGEOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
44.793 %
Winner50.813 %
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 betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner83.146 %
54.682 %
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 betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner62.569 %
39.632 %
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 betterGPT-6 Sol: Harness: OpenHands
GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Harness: OpenHands
Winner87.824 %
47.969 %
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

GPT-5.4 mini

The response reached the token limit. No complete recording is available.

Reasoning (requested): high

First attempt
Run date
7 Sept 2026
API provider
openrouter
Requested API model
openai/gpt-5.4-mini
API model reported in response
openai/gpt-5.4-mini
Reasoning setting
high
Pinned endpoint
OpenAI | openai/gpt-5.4-mini-20260317
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Failed
Response time
67 s

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

Related LLM comparisons

Compare GPT-6 Sol and GPT-5.4 mini with other leading models using the same data and benchmark logic.

View the complete LLM comparison