Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
shared result series
172
distinct benchmarks
19
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 and Gemini 3.5 Flash-Lite
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 and Gemini 3.5 Flash-Lite
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
Gemini 3.5 Flash-Lite
Coding: 100 / 77 (6 benchmark families)
Reasoning: 100 / 95.2 (2 benchmark families)
Mathematics: 100 / 98.4 (1 benchmark family)
Knowledge: 100 / 98.5 (2 benchmark families)
Finance: 99.9 / 97.4 (4 benchmark families)
Legal: 100 / 98.8 (3 benchmark families)
Multimodal: 100 / 95.5 (1 benchmark family)
Health: 98.2 / 97.1 (3 benchmark families)
45 matched rows from 17 benchmark families were considered. The radar shows 8 of 10 comparable categories.
GPT-5.4Gemini 3.5 Flash-Lite
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.4Winner34.984 %
Gemini 3.5 Flash-Lite6.148 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.4Winner65.268 %
Gemini 3.5 Flash-Lite60.684 %
CyberBench v1.1Patch. Higher is better. Test setup not documented as identical
GPT-5.4Higher measured value81.356 %
Gemini 3.5 Flash-Lite77.966 %
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.4Winner91.666 %
Gemini 3.5 Flash-Lite83.838 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.4Tie0 %
Gemini 3.5 Flash-LiteTie0 %
IOIIOI 2024. Higher is better. Test setup not documented as identical
GPT-5.4Higher measured value67.167 %
Gemini 3.5 Flash-Lite25 %
LegalBenchOverall. Higher is better. No documented setup difference
GPT-5.4Winner86.044 %
Gemini 3.5 Flash-Lite84.073 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
GPT-5.4Winner84.141 %
Gemini 3.5 Flash-Lite79.014 %
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
GPT-5.4Winner1,464.964
Gemini 3.5 Flash-Lite1,456.026
MedCodeOverall. Higher is better. No documented setup difference
GPT-5.441.292 %
Gemini 3.5 Flash-LiteWinner43.489 %
MedScribeOverall. Higher is better. No documented setup difference
GPT-5.4Winner77.549 %
Gemini 3.5 Flash-Lite70.886 %
MMLU-ProOverall. Higher is better. No documented setup difference
GPT-5.4Winner87.482 %
Gemini 3.5 Flash-Lite85.836 %
Key to the marks:better valuebetter, but not conclusivetie
Benchmark scores for GPT-5.4 and Gemini 3.5 Flash-Lite
Benchmark and task
GPT-5.4
Gemini 3.5 Flash-Lite
Source
Code MigrationOverallTest details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Gemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 67,632 anonymous pairwise votes.Gemini 3.5 Flash-Lite: Style-controlled Arena rating from 33,501 anonymous pairwise votes.
Winner1,464.964
95% confidence interval: ±3.702The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,456.026
95% confidence interval: ±4.576The 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: 1.1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Harness: OpenHands Gemini 3.5 Flash-Lite: Harness: OpenHands
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Gemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 64,479 anonymous pairwise votes.Gemini 3.5 Flash-Lite: Style-controlled Arena rating from 33,501 anonymous pairwise votes.
Higher measured value1,475.198
95% confidence interval: ±3.778The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,456.026
95% confidence interval: ±4.576The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
LMArena Text, Style ControlBusiness, management and financeTest details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Gemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,882 anonymous pairwise votes.Gemini 3.5 Flash-Lite: Style-controlled Arena rating from 6,238 anonymous pairwise votes.
Winner1,474.623
95% confidence interval: ±6.376The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,453.642
95% confidence interval: ±8.177The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
LMArena Text, Style ControlBusiness, management and financeTest details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Gemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,092 anonymous pairwise votes.Gemini 3.5 Flash-Lite: Style-controlled Arena rating from 6,238 anonymous pairwise votes.
Higher measured value1,481.559
95% confidence interval: ±6.485The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,453.642
95% confidence interval: ±8.177The 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Gemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 4,364 anonymous pairwise votes.Gemini 3.5 Flash-Lite: Style-controlled Arena rating from 2,584 anonymous pairwise votes.
No clear lead1,493.153
95% confidence interval: ±9.833The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,483.555
95% confidence interval: ±12.381The 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
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
openai/gpt-5.4
Reasoning setting
high
Pinned endpoint
OpenAI | openai/gpt-5.4-20260305
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.
Gemini 3.5 Flash-Lite
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-3.5-flash-lite
Reasoning setting
high
Pinned endpoint
Google AI Studio | google/gemini-3.5-flash-lite-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 and Gemini 3.5 Flash-Lite with other leading models using the same data and benchmark logic.