Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
shared result series
47
distinct benchmarks
20
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 Mistral Medium 3.5
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 mini and Mistral Medium 3.5
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 Mistral Medium 3.5
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
Mistral Medium 3.5
Coding: 100 / 45.5 (3 benchmark families)
Reasoning: 100 / 41.9 (1 benchmark family)
Knowledge: 100 / 89.1 (1 benchmark family)
Finance: 100 / 67.9 (6 benchmark families)
Legal: 50 / 86.5 (2 benchmark families)
Agentic tasks: 100 / 81.7 (2 benchmark families)
Education: 100 / 74 (1 benchmark family)
Overall: 100 / 54.7 (2 benchmark families)
19 matched rows from 18 benchmark families were considered. The radar shows 8 of 8 comparable categories.
GPT-5.4 miniMistral Medium 3.5
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.4 miniWinner12.936 %
Mistral Medium 3.55.127 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.4 miniWinner60.917 %
Mistral Medium 3.558.78 %
EMBOverall. Higher is better. No documented setup difference
GPT-5.4 miniWinner45.426 %
Mistral Medium 3.511.185 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
GPT-5.4 miniWinner45.36 %
Mistral Medium 3.532.103 %
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.4 miniWinner83.08 %
Mistral Medium 3.534.848 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.4 mini0 %
Mistral Medium 3.5Winner0.417 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
GPT-5.4 miniWinner12.5 %
Mistral Medium 3.59.135 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.4 miniHigher measured value1,447.017
Mistral Medium 3.51,426.128
MMLU-ProOverall. Higher is better. No documented setup difference
GPT-5.4 miniWinner84.554 %
Mistral Medium 3.575.335 %
MortgageTaxOverall. Higher is better. No documented setup difference
GPT-5.4 miniWinner63.514 %
Mistral Medium 3.528.895 %
SAGEOverall. Higher is better. No documented setup difference
GPT-5.4 miniWinner50.813 %
Mistral Medium 3.537.613 %
SWE-bench VerifiedOverall. Higher is better. No documented setup difference
GPT-5.4 miniWinner73 %
Mistral Medium 3.566.4 %
Key to the marks:better valuebetter, but not conclusivetie
Benchmark scores for GPT-5.4 mini and Mistral Medium 3.5
Benchmark and task
GPT-5.4 mini
Mistral Medium 3.5
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
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 63,140 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 11,693 anonymous pairwise votes.
Higher measured value1,447.017
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.
1,426.128
95% confidence interval: ±6.42The 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: arxiv:2609.25804v2Metric: both-orders-correct, engineering/research macro averageScoring: Higher is betterSettings: Reasoning: high, Output limit: 65,536 tokens, Attempts: 502 questions, two option orders eachSame prompt for all models. Each of 502 questions is shown twice with the options reversed. Average of engineering and research success rates, requiring both orders to be correct. 65,536-token output budget; unparseable answers count as wrong.
Winner40.1 %
112 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
37.7 %
24 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
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 Mistral Medium 3.5: Harness: OpenHands
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 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 12,859 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,256 anonymous pairwise votes.
Higher measured value1,459.736
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.
1,430.173
95% confidence interval: ±12.827The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 3,931 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 621 anonymous pairwise votes.
Higher measured value1,473.944
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.
1,446.524
95% confidence interval: ±23.931The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 17,234 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,282 anonymous pairwise votes.
Higher measured value1,494.645
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.
1,477.898
95% confidence interval: ±10.854The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 10,564 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,999 anonymous pairwise votes.
Higher measured value1,401.555
95% confidence interval: ±7.102The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,397.828
95% confidence interval: ±13.94The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 28,849 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,562 anonymous pairwise votes.
Higher measured value1,450.286
95% confidence interval: ±4.967The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,442.84
95% confidence interval: ±8.53The 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 ControlEntertainment, sports and mediaTest details
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 13,659 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,618 anonymous pairwise votes.
Higher measured value1,408.868
95% confidence interval: ±6.512The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,394.24
95% confidence interval: ±12.151The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 48,487 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 8,856 anonymous pairwise votes.
Higher measured value1,448.518
95% confidence interval: ±4.905The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,419.562
95% confidence interval: ±8.482The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 6,308 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,205 anonymous pairwise votes.
Higher measured value1,480.018
95% confidence interval: ±8.274The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,433.7
95% confidence interval: ±17.235The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 2,234 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 453 anonymous pairwise votes.
Higher measured value1,476.191
95% confidence interval: ±14.698The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,435.855
95% confidence interval: ±29.943The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 927 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 173 anonymous pairwise votes.
1,441.968
95% confidence interval: ±20.407The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,447.96
95% confidence interval: ±43.885The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 41,588 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 7,627 anonymous pairwise votes.
Higher measured value1,468.625
95% confidence interval: ±4.5The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,444.677
95% confidence interval: ±7.686The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 19,761 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,821 anonymous pairwise votes.
Higher measured value1,466.189
95% confidence interval: ±5.698The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,455.806
95% confidence interval: ±10.148The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 21,722 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,827 anonymous pairwise votes.
Higher measured value1,433.909
95% confidence interval: ±5.448The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,420.763
95% confidence interval: ±10.011The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 986 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 188 anonymous pairwise votes.
Higher measured value1,393.674
95% confidence interval: ±20.242The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,392.677
95% confidence interval: ±43.291The 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 ControlLegal and governmentTest details
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 5,041 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 893 anonymous pairwise votes.
Higher measured value1,456.95
95% confidence interval: ±9.32The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,437.755
95% confidence interval: ±20.721The 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 ControlLife, physical and social scienceTest details
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 10,507 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,939 anonymous pairwise votes.
Higher measured value1,464.766
95% confidence interval: ±6.9The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,435.825
95% confidence interval: ±13.971The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 27,667 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,065 anonymous pairwise votes.
Higher measured value1,446.891
95% confidence interval: ±5.283The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,428.117
95% confidence interval: ±9.119The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 3,367 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 565 anonymous pairwise votes.
Higher measured value1,438.647
95% confidence interval: ±10.756The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,428.606
95% confidence interval: ±24.143The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 3,425 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 653 anonymous pairwise votes.
Higher measured value1,452.154
95% confidence interval: ±10.839The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,438.481
95% confidence interval: ±22.896The 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 ControlMedicine and healthcareTest details
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 4,764 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 844 anonymous pairwise votes.
Higher measured value1,450.383
95% confidence interval: ±9.664The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,421.161
95% confidence interval: ±21.257The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 11,879 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,925 anonymous pairwise votes.
Higher measured value1,465.677
95% confidence interval: ±6.69The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,432.256
95% confidence interval: ±14.007The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 34,290 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 6,131 anonymous pairwise votes.
Higher measured value1,437.302
95% confidence interval: ±4.678The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,406.139
95% confidence interval: ±8.159The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 1,194 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 235 anonymous pairwise votes.
Higher measured value1,462.837
95% confidence interval: ±17.906The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,415.979
95% confidence interval: ±38.135The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 6,986 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,242 anonymous pairwise votes.
Higher measured value1,451.017
95% confidence interval: ±7.971The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,410.34
95% confidence interval: ±17.157The 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 ControlSoftware and IT servicesTest details
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 25,035 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 4,587 anonymous pairwise votes.
Higher measured value1,485.239
95% confidence interval: ±5.216The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,468.806
95% confidence interval: ±9.304The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 1,936 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 393 anonymous pairwise votes.
Higher measured value1,433.967
95% confidence interval: ±14.932The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,392.394
95% confidence interval: ±31.573The 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 ControlWriting, literature and languageTest details
Test setup not documented as identicalNo direct winnerVersion: 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 Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 15,639 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,919 anonymous pairwise votes.
Higher measured value1,423.622
95% confidence interval: ±6.069The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,403.766
95% confidence interval: ±11.409The 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.
Mistral Medium 3.5
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
mistralai/mistral-medium-3-5
Reasoning setting
high
Pinned endpoint
Mistral | mistralai/mistral-medium-3.5-20260430
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 Mistral Medium 3.5 with other leading models using the same data and benchmark logic.