Head-to-head comparison

GPT-5.4 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: 138
distinct benchmarks: 25
latest retrieval: 2026-09-04

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-5.4 and Gemini 3.1 Pro Preview
Attribute	GPT-5.4	Gemini 3.1 Pro Preview
Provider	OpenAI	Google
Released	Mar 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	August 31, 2025	Not published
Technical sources	Model	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-5.4 and Gemini 3.1 Pro Preview
Price type	GPT-5.4	Gemini 3.1 Pro Preview
API input	$2.5 ≤272K / $5 >272K	$2 ≤200K / $4 >200K
API output	$15 ≤272K / $22.5 >272K	$12 ≤200K / $18 >200K
Cache read	$0.25 ≤272K / $0.5 >272K	$0.2 ≤200K / $0.4 >200K
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	07/30/2026 Source	07/30/2026 Source

GPT-5.4Gemini 3.1 Pro Preview

API inputUSD per 1M tokens, base tier

GPT-5.4$2.5

Gemini 3.1 Pro Preview$2

API outputUSD per 1M tokens, base tier

GPT-5.4$15

Gemini 3.1 Pro Preview$12

Cache readUSD per 1M tokens, base tier

GPT-5.4$0.25

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-5.4 and Gemini 3.1 Pro Preview
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
GPT-5.4	OpenAI	Direct from developerUp to 272,000 context tokens	$2.5	$15	Source07/30/2026
	OpenAI	Direct from developerAbove 272,000 context tokens	$5	$22.5	Source07/30/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us-east-1	$2.75	$16.5	Source09/07/2026
	Azure	Via OpenRouterazure	$2.5	$15	Source09/07/2026
	Azure	Via OpenRouterazure/eu	$2.75	$16.5	Source09/07/2026
	Azure	Via OpenRouterazure/us	$2.75	$16.5	Source09/07/2026
	OpenAI	Via OpenRouteropenai	$2.5	$15	Source09/07/2026
	OpenAI	Via OpenRouteropenai/fast	$5	$30	Source09/07/2026
	OpenAI	Via OpenRouteropenai/flex	Lowest listed price: $1.25	Lowest listed price: $7.5	Source09/07/2026
Gemini 3.1 Pro Preview	Google	Direct from developerUp to 200,000 context tokens	$2	$12	Source07/30/2026
	Google	Direct from developerAbove 200,000 context tokens	$4	$18	Source07/30/2026
	Google	Via OpenRoutergoogle-vertex/global	$2	$12	Source09/07/2026
	Google	Via OpenRoutergoogle-vertex/global/flex	Lowest listed price: $1	Lowest listed price: $6	Source09/07/2026
	Google	Via OpenRoutergoogle-vertex/global/priority	$3.6	$21.6	Source09/07/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio	$2	$12	Source09/07/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/flex	Lowest listed price: $1	Lowest listed price: $6	Source09/07/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/priority	$3.6	$21.6	Source09/07/2026

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-5.4

Gemini 3.1 Pro Preview

Coding: 99 / 82.8 (6 benchmark families)

Reasoning: 97.4 / 100 (2 benchmark families)

Mathematics: 98.7 / 100 (1 benchmark family)

Knowledge: 90.9 / 100 (3 benchmark families)

Finance: 99.6 / 99.3 (4 benchmark families)

Legal: 99 / 100 (3 benchmark families)

Agentic tasks: 86.7 / 100 (1 benchmark family)

Multimodal: 99.2 / 100 (1 benchmark family)

51 matched rows from 21 benchmark families were considered. The radar shows 8 of 12 comparable categories.

GPT-5.4Gemini 3.1 Pro Preview

Code MigrationOverall. Higher is better. No documented setup difference

GPT-5.434.984 %

Gemini 3.1 Pro Preview17.313 %

CorpFin v2Overall. Higher is better. No documented setup difference

GPT-5.465.268 %

Gemini 3.1 Pro Preview64.491 %

CyberBenchOverall. Higher is better. No documented setup difference

GPT-5.472.881 %

Gemini 3.1 Pro Preview36.441 %

GPQA DiamondOverall. Higher is better. No documented setup difference

GPT-5.491.666 %

Gemini 3.1 Pro Preview95.454 %

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

GPT-5.40 %

Gemini 3.1 Pro Preview0 %

Humanity's Last ExamOverall. Higher is better. No documented setup difference

GPT-5.436.24% ± 1.88

Gemini 3.1 Pro Preview46.44% ± 1.96

LegalBenchOverall. Higher is better. No documented setup difference

GPT-5.486.044 %

Gemini 3.1 Pro Preview87.398 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

GPT-5.484.141 %

Gemini 3.1 Pro Preview88.485 %

LMArena Text, Style ControlOverall. Higher is better. No documented setup difference

GPT-5.41,465.527

Gemini 3.1 Pro Preview1,486.746

MedCodeOverall. Higher is better. No documented setup difference

GPT-5.441.292 %

Gemini 3.1 Pro Preview59.062 %

MedQAOverall. Higher is better. No documented setup difference

GPT-5.496.092 %

Gemini 3.1 Pro Preview96.367 %

MedScribeOverall. Higher is better. No documented setup difference

GPT-5.477.549 %

Gemini 3.1 Pro Preview76.114 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-5.4 and Gemini 3.1 Pro Preview
Benchmark and task	GPT-5.4	Gemini 3.1 Pro Preview	Source
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner34.984 %	17.313 %	Vals AI Source details Data as of: 09/03/2026
CorpFin v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner65.268 %	64.491 %	Vals AI Source details Data as of: 08/12/2026
CyberBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner72.881 %	36.441 %	Vals AI Source details Data as of: 09/01/2026
GPQA DiamondOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	91.666 %	Winner95.454 %	Vals AI Source details Data as of: 09/01/2026
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: Snapshot: gpt-5.4-2026-03-05	Tie0 %	Tie0 %	Vals AI Source details Data as of: 09/03/2026
Humanity's Last ExamOverall Test details No documented difference in the test setupVersion: final 2,500-question public setMetric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Attempts: pass@1 Gemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview-thinking-high, Attempts: pass@1All 2,500 public questions, temperature 0, and an automatic answer extractor.	36.24% ± 1.88 95% confidence interval: ±1.88	Winner46.44% ± 1.96 95% confidence interval: ±1.96	Scale AI Source details Data as of: 09/02/2026
LegalBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	86.044 %	Winner87.398 %	Vals AI Source details Data as of: 09/01/2026
LiveCodeBench v6Overall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	84.141 %	Winner88.485 %	Vals AI Source details Data as of: 09/01/2026
LMArena Text, Style ControlOverall Test 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 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 63,615 anonymous pairwise votes.Gemini 3.1 Pro Preview: Style-controlled Arena rating from 102,763 anonymous pairwise votes.	1,465.527 95% confidence interval: ±3.807The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,486.746 95% confidence interval: ±3.217The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
MedCodeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	41.292 %	Winner59.062 %	Vals AI Source details Data as of: 09/03/2026
MedQAOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	96.092 %	Winner96.367 %	Vals AI Source details Data as of: 04/16/2026
MedScribeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner77.549 %	76.114 %	Vals AI Source details Data as of: 09/03/2026
MMLU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	87.482 %	Winner90.987 %	Vals AI Source details Data as of: 09/01/2026
MMMU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	87.514 %	Winner88.208 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	68.323 %	Winner69.396 %	Vals AI Source details Data as of: 09/01/2026
MultiNRCOverall Test details Test setup not documented as identicalNo direct winnerVersion: French, Spanish, and Chinese releaseMetric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-xhigh, Reasoning: xhigh, Attempts: pass@1 Gemini 3.1 Pro Preview: Attempts: pass@1Native, non-translated reasoning tasks with automatic evaluation.	58.29% ± 2.98 95% confidence interval: ±2.98	Higher measured value64.74% ± 2.88 95% confidence interval: ±2.88	Scale AI Source details Data as of: 08/26/2026
PRBench FinanceOverall Test details Test setup not documented as identicalNo direct winnerVersion: full finance setMetric: weighted rubric scoreScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Attempts: pass@1 Gemini 3.1 Pro Preview: Attempts: pass@1600 finance tasks with task-specific rubrics and o4-mini as judge.	Higher measured value45.63% ± 0.56 95% confidence interval: ±0.56	41.87% ± 1.22 95% confidence interval: ±1.22	Scale AI Source details Data as of: 08/26/2026
PRBench LegalOverall Test details Test setup not documented as identicalNo direct winnerVersion: full legal setMetric: weighted rubric scoreScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Attempts: pass@1 Gemini 3.1 Pro Preview: Attempts: pass@1500 legal tasks with task-specific rubrics and o4-mini as judge.	Higher measured value44.35% ± 0.28 95% confidence interval: ±0.28	44.02% ± 1.12 95% confidence interval: ±1.12	Scale AI Source details Data as of: 08/26/2026
ProgramBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Tie0 %	Tie0 %	Vals AI Source details Data as of: 09/01/2026
SAGEOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	43.312 %	Winner48.677 %	Vals AI Source details Data as of: 09/03/2026
SWE-bench VerifiedOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	78.2 %	Winner78.8 %	Vals AI Source details Data as of: 09/01/2026
TaxEval v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner73.958 %	72.882 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Overall Test details No documented difference in the test setupVersion: 2.0Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	58.427 %	Winner67.416 %	Vals AI Source details Data as of: 06/04/2026
Vibe Code Bench v1.1Overall Test details 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 3.1 Pro Preview: Harness: OpenHands	Winner67.421 %	32.034 %	Vals AI Source details Data as of: 09/03/2026
VisualToolBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1,204-task releaseMetric: average pass rateScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Attempts: pass@1 Gemini 3.1 Pro Preview: Attempts: pass@11,204 tasks, six tools, and at most 20 tool calls per task.	Higher measured value29.17% ± 0.13 95% confidence interval: ±0.13	28.97% ± 0.91 95% confidence interval: ±0.91	Scale AI Source details Data as of: 08/26/2026
Code MigrationCLI Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value23.788 %	10.833 %	Vals AI Source details Data as of: 08/09/2026
CorpFin v2Exact Pages Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value64.103 %	60.839 %	Vals AI Source details Data as of: 08/06/2026
CyberBenchPatch Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner81.356 %	69.492 %	Vals AI Source details Data as of: 08/03/2026
GPQA DiamondFew-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,535 tokens	91.414 %	Higher measured value95.96 %	Vals AI Source details Data as of: 08/09/2026
LegalBenchConclusion Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	88.939 %	Higher measured value89.257 %	Vals AI Source details Data as of: 08/09/2026
LiveCodeBench v6Easy Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	No direct winner99.068 %	No direct winner99.068 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlOverall Test 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 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 60,657 anonymous pairwise votes.Gemini 3.1 Pro Preview: Style-controlled Arena rating from 102,763 anonymous pairwise votes.	1,476.488 95% confidence interval: ±3.881The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Higher measured value1,486.746 95% confidence interval: ±3.217The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
MedQAAsian Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	96.15 %	Higher measured value96.3 %	Vals AI Source details Data as of: 04/16/2026
MMLU-ProBiology Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,535 tokens	92.887 %	Higher measured value95.258 %	Vals AI Source details Data as of: 08/09/2026
MortgageTaxNumerical Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	75.994 %	Higher measured value76.391 %	Vals AI Source details Data as of: 08/09/2026
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value7 %	1 %	Vals AI Source details Data as of: 08/09/2026
SAGEAutomata Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens	21.428 %	Higher measured value32.143 %	Vals AI Source details Data as of: 08/09/2026
SWE-bench Verified<15 min fix Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	88.144 %	Higher measured value88.66 %	Vals AI Source details Data as of: 08/08/2026
TaxEval v2Correctness Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,535 tokens	Higher measured value64.922 %	60.749 %	Vals AI Source details Data as of: 08/09/2026
Terminal-Bench 2.0Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: high, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	No direct winner100 %	No direct winner100 %	Vals AI Source details Data as of: 06/04/2026
Code MigrationCOBOL Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value68.571 %	36.753 %	Vals AI Source details Data as of: 08/09/2026
CorpFin v2Max Fitting Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	64.918 %	Higher measured value66.9 %	Vals AI Source details Data as of: 08/06/2026
CyberBenchPoC Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner64.407 %	3.39 %	Vals AI Source details Data as of: 08/03/2026
GPQA DiamondZero-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,535 tokens	91.919 %	Higher measured value94.949 %	Vals AI Source details Data as of: 08/09/2026
LegalBenchInterpretation Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value83.921 %	83.823 %	Vals AI Source details Data as of: 08/09/2026
LiveCodeBench v6Hard Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	67.714 %	Higher measured value76.571 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlBusiness, management and finance Test details 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 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,060 anonymous pairwise votes.Gemini 3.1 Pro Preview: Style-controlled Arena rating from 20,283 anonymous pairwise votes.	1,474.871 95% confidence interval: ±6.534The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,476.52 95% confidence interval: ±5.472The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
MedQABlack Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	96.5 %	Higher measured value96.8 %	Vals AI Source details Data as of: 04/16/2026
MMLU-ProBusiness Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,535 tokens	91.762 %	Higher measured value93.409 %	Vals AI Source details Data as of: 08/09/2026
MortgageTaxSemantic Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	60.652 %	Higher measured value62.401 %	Vals AI Source details Data as of: 08/09/2026
ProgramBenchFully Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 08/09/2026
SAGECalculus Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens	70.988 %	Higher measured value78.395 %	Vals AI Source details Data as of: 08/09/2026
SWE-bench Verified>4 hours Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	0 %	Higher measured value33.333 %	Vals AI Source details Data as of: 08/08/2026
TaxEval v2Stepwise Reasoning Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,535 tokens	82.993 %	Higher measured value85.016 %	Vals AI Source details Data as of: 08/09/2026
Terminal-Bench 2.0Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: high, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	33.333 %	Higher measured value53.333 %	Vals AI Source details Data as of: 06/04/2026
Code MigrationCode Quality Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value3.632 / 5	2.538 / 5	Vals AI Source details Data as of: 08/09/2026
CorpFin v2Shared Max Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value66.783 %	65.734 %	Vals AI Source details Data as of: 08/06/2026
LegalBenchIssue Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	90.526 %	Higher measured value91.48 %	Vals AI Source details Data as of: 08/09/2026
LiveCodeBench v6Medium Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	85.64 %	Higher measured value89.817 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlBusiness, management and finance Test 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 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,346 anonymous pairwise votes.Gemini 3.1 Pro Preview: Style-controlled Arena rating from 20,283 anonymous pairwise votes.	Higher measured value1,483.779 95% confidence interval: ±6.654The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,476.52 95% confidence interval: ±5.472The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
MedQAHispanic Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	95.7 %	Higher measured value95.95 %	Vals AI Source details Data as of: 04/16/2026
MMLU-ProChemistry Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,535 tokens	91.078 %	Higher measured value93.286 %	Vals AI Source details Data as of: 08/09/2026
ProgramBenchRaw Pass Rate Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value68.596 %	39.468 %	Vals AI Source details Data as of: 08/09/2026
SAGELinear Algebra Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens Gemini 3.1 Pro Preview: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens	68.826 %	Higher measured value74.205 %	Vals AI Source details Data as of: 08/09/2026
Key to the marks:better valuebetter, but not conclusivetie

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-5.4 and Gemini 3.1 Pro Preview with other leading models using the same data and benchmark logic.

View the complete LLM comparison