Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
shared result series
140
distinct benchmarks
21
latest retrieval
2026-09-29
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-5.4 mini and Gemini 3.6 Flash
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.
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-5.4 mini and Gemini 3.6 Flash
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-5.4 mini
Gemini 3.6 Flash
Coding: 83.2 / 100 (6 benchmark families)
Reasoning: 93.5 / 100 (2 benchmark families)
Mathematics: 96.7 / 100 (1 benchmark family)
Knowledge: 96.1 / 100 (2 benchmark families)
Finance: 86.8 / 100 (7 benchmark families)
Legal: 49.4 / 100 (3 benchmark families)
Agentic tasks: 74.1 / 100 (1 benchmark family)
Multimodal: 89.7 / 100 (1 benchmark family)
51 matched rows from 21 benchmark families were considered. The radar shows 8 of 12 comparable categories.
GPT-5.4 miniGemini 3.6 Flash
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.4 mini12.936 %
Gemini 3.6 FlashWinner30.928 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.4 mini60.917 %
Gemini 3.6 FlashWinner63.326 %
EMBOverall. Higher is better. No documented setup difference
GPT-5.4 mini45.426 %
Gemini 3.6 FlashWinner65.411 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
GPT-5.4 mini45.36 %
Gemini 3.6 FlashWinner56.296 %
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.4 mini83.08 %
Gemini 3.6 FlashWinner93.434 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.4 mini0 %
Gemini 3.6 FlashWinner3.333 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
GPT-5.4 mini12.5 %
Gemini 3.6 FlashWinner25 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
GPT-5.4 mini81.465 %
Gemini 3.6 FlashWinner88.08 %
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
GPT-5.4 mini1,447.017
Gemini 3.6 FlashWinner1,481.934
MMLU-ProOverall. Higher is better. No documented setup difference
GPT-5.4 mini84.554 %
Gemini 3.6 FlashWinner89.276 %
MMMU-ProOverall. Higher is better. No documented setup difference
GPT-5.4 mini79.249 %
Gemini 3.6 FlashWinner88.382 %
MortgageTaxOverall. Higher is better. No documented setup difference
GPT-5.4 mini63.514 %
Gemini 3.6 FlashWinner67.608 %
Key to the marks:better valuebetter, but not conclusivetie
Benchmark scores for GPT-5.4 mini and Gemini 3.6 Flash
Benchmark and task
GPT-5.4 mini
Gemini 3.6 Flash
Source
Code MigrationOverallTest details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
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
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena text, style control Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 63,140 anonymous pairwise votes.Gemini 3.6 Flash: Style-controlled Arena rating from 33,739 anonymous pairwise votes.
1,447.017
95% confidence interval: ±3.76The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,481.934
95% confidence interval: ±4.524The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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
No documented difference in the test setupVersion: 1.2Metric: weighted index scoreScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Harness: OpenHands Gemini 3.6 Flash: Harness: OpenHands
LMArena Text, Style ControlBusiness, management and financeTest details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena text, style control Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 12,859 anonymous pairwise votes.Gemini 3.6 Flash: Style-controlled Arena rating from 6,456 anonymous pairwise votes.
1,459.736
95% confidence interval: ±6.499The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,472.22
95% confidence interval: ±8.085The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena text, style control Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 3,931 anonymous pairwise votes.Gemini 3.6 Flash: Style-controlled Arena rating from 2,546 anonymous pairwise votes.
1,473.944
95% confidence interval: ±10.215The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,529.331
95% confidence interval: ±12.228The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena text, style control Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 17,234 anonymous pairwise votes.Gemini 3.6 Flash: Style-controlled Arena rating from 9,823 anonymous pairwise votes.
1,494.645
95% confidence interval: ±5.907The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,518.119
95% confidence interval: ±6.946The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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-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.
Gemini 3.6 Flash
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-3.6-flash
Reasoning setting
high
Pinned endpoint
Google AI Studio | google/gemini-3.6-flash-20260721
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.
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-5.4 mini and Gemini 3.6 Flash with other leading models using the same data and benchmark logic.