Skip to main content

Head-to-head comparison

Gemini 3.8 Flash vs. Gemini 3.6 Flash

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

shared result series
230
distinct benchmarks
37
latest retrieval
2026-10-15

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 Gemini 3.8 Flash and Gemini 3.6 Flash
AttributeGemini 3.8 FlashGemini 3.6 Flash
ProviderGoogleGoogle
ReleasedSep 2, 2026Jul 21, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,048,576 tokens1,048,576 tokens
Knowledge cutoffMarch 2026March 2026
Technical sourcesModel, Knowledge cutoffModel, Knowledge cutoff

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 Gemini 3.8 Flash and Gemini 3.6 Flash
Price typeGemini 3.8 FlashGemini 3.6 Flash
API input$0.75$0.75
API output$3.75$3.75
Cache read$0.075$0.075
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified09/22/2026 Source09/22/2026 Source
Gemini 3.8 FlashGemini 3.6 Flash
API inputUSD per 1M tokens, base tier
Gemini 3.8 FlashTie$0.75
Gemini 3.6 FlashTie$0.75
API outputUSD per 1M tokens, base tier
Gemini 3.8 FlashTie$3.75
Gemini 3.6 FlashTie$3.75
Cache readUSD per 1M tokens, base tier
Gemini 3.8 FlashTie$0.075
Gemini 3.6 FlashTie$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 Gemini 3.8 Flash and Gemini 3.6 Flash
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Gemini 3.8 FlashGoogleDirect from developerStandard API$0.75$3.75Source09/22/2026
GoogleVia OpenRoutergoogle-vertex/us$0.825$4.125Source10/17/2026
Google AI StudioVia OpenRoutergoogle-ai-studio$0.75$3.75Source10/17/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/flexLowest listed price: $0.375Lowest listed price: $1.875Source10/17/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/priority$1.35$6.75Source10/17/2026
Gemini 3.6 FlashGoogleDirect from developerStandard API$0.75$3.75Source09/22/2026
GoogleVia OpenRoutergoogle-vertex/global$0.75$3.75Source10/17/2026
GoogleVia OpenRoutergoogle-vertex/global/flexLowest listed price: $0.375Lowest listed price: $1.875Source10/17/2026
GoogleVia OpenRoutergoogle-vertex/global/priority$1.35$6.75Source10/17/2026
GoogleVia OpenRoutergoogle-vertex/us$0.825$4.125Source10/17/2026
Google AI StudioVia OpenRoutergoogle-ai-studio$0.75$3.75Source10/17/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/flexLowest listed price: $0.375Lowest listed price: $1.875Source10/17/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/priority$1.35$6.75Source10/17/2026

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.

255075100CodingReasoningMathematicsKnowledgeFinanceLegalAgentic tasksMultimodal
Gemini 3.8 Flash
Gemini 3.6 Flash
Coding: 100 / 75.8 (9 benchmark families)
Reasoning: 100 / 92.8 (5 benchmark families)
Mathematics: 100 / 98.7 (1 benchmark family)
Knowledge: 100 / 90.7 (3 benchmark families)
Finance: 99.2 / 90.5 (6 benchmark families)
Legal: 100 / 89.5 (4 benchmark families)
Agentic tasks: 100 / 87.5 (4 benchmark families)
Multimodal: 100 / 98.8 (2 benchmark families)

228 matched rows from 35 benchmark families were considered. The radar shows 8 of 14 comparable categories.

Gemini 3.8 FlashGemini 3.6 Flash
AA-BriefcaseOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner1,203.02 elo
Gemini 3.6 Flash953.92 elo
AA-LCROverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner81.3%
Gemini 3.6 Flash80.0%
AA-OmniscienceOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner29.55 points
Gemini 3.6 Flash22.133 points
Artificial Analysis Intelligence IndexOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner40.926 points
Gemini 3.6 Flash33.979 points
AutomationBench-AAOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner59.9%
Gemini 3.6 Flash53.0%
BioMysteryBenchOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner62.222 %
Gemini 3.6 Flash58.519 %
Code MigrationOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner36.546 %
Gemini 3.6 Flash30.928 %
CyberBench v1.1Overall. Higher is better. No documented setup difference
Gemini 3.8 Flash43.75 %
Gemini 3.6 FlashWinner45.357 %
EMBOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner72.196 %
Gemini 3.6 Flash65.411 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner61.435 %
Gemini 3.6 Flash56.296 %
GDP.pdfOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner21.0%
Gemini 3.6 Flash17.4%
GDPval-AAOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner1,436.3 elo
Gemini 3.6 Flash1,284.34 elo

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Gemini 3.8 Flash and Gemini 3.6 Flash
Benchmark and taskGemini 3.8 FlashGemini 3.6 FlashSource
AA-BriefcaseOverall
Test details
No documented difference in the test setupVersion: v1.1Metric: AA-Briefcase EloScoring: Higher is betterGemini 3.8 Flash: Snapshot: Gemini 3.8 Flash (High), Reasoning: High
Gemini 3.6 Flash: Snapshot: Gemini 3.6 Flash (High), Reasoning: HighGemini 3.8 Flash: Exact AA configuration: Gemini 3.8 Flash (High) (release gemini-3-8-flash, row gemini-3-8-flash, UUID 8a999846-4c1d-4ce7-a8b7-1310a7166fd7, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.Gemini 3.6 Flash: Exact AA configuration: Gemini 3.6 Flash (High) (release gemini-3-6-flash, row gemini-3-6-flash, UUID 78332c88-fe60-42c8-af9d-3617e44cf1f5, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.
Winner1,203.02 elo
953.92 elo
Artificial Analysis
Source details
Data as of: 10/15/2026
AA-LCROverall
Test details
No documented difference in the test setupVersion: v1.1Metric: Pass rateScoring: Higher is betterGemini 3.8 Flash: Snapshot: Gemini 3.8 Flash (High), Reasoning: High
Gemini 3.6 Flash: Snapshot: Gemini 3.6 Flash (High), Reasoning: HighGemini 3.8 Flash: Exact AA configuration: Gemini 3.8 Flash (High) (release gemini-3-8-flash, row gemini-3-8-flash, UUID 8a999846-4c1d-4ce7-a8b7-1310a7166fd7, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.Gemini 3.6 Flash: Exact AA configuration: Gemini 3.6 Flash (High) (release gemini-3-6-flash, row gemini-3-6-flash, UUID 78332c88-fe60-42c8-af9d-3617e44cf1f5, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.
Winner81.3%
80.0%
Artificial Analysis
Source details
Data as of: 10/15/2026
AA-OmniscienceOverall
Test details
No documented difference in the test setupVersion: unspecifiedMetric: AA-Omniscience IndexScoring: Higher is betterGemini 3.8 Flash: Snapshot: Gemini 3.8 Flash (High), Reasoning: High
Gemini 3.6 Flash: Snapshot: Gemini 3.6 Flash (High), Reasoning: HighGemini 3.8 Flash: Exact AA configuration: Gemini 3.8 Flash (High) (release gemini-3-8-flash, row gemini-3-8-flash, UUID 8a999846-4c1d-4ce7-a8b7-1310a7166fd7, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.Gemini 3.6 Flash: Exact AA configuration: Gemini 3.6 Flash (High) (release gemini-3-6-flash, row gemini-3-6-flash, UUID 78332c88-fe60-42c8-af9d-3617e44cf1f5, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.
Winner29.55 points
The index can be negative and ranges from -100 to 100 according to Artificial Analysis.
22.133 points
The index can be negative and ranges from -100 to 100 according to Artificial Analysis.		Artificial Analysis
Source details
Data as of: 10/15/2026
Artificial Analysis Intelligence IndexOverall
Test details
No documented difference in the test setupVersion: v4.3.2Metric: Artificial Analysis Intelligence IndexScoring: Higher is betterGemini 3.8 Flash: Snapshot: Gemini 3.8 Flash (High), Reasoning: High
Gemini 3.6 Flash: Snapshot: Gemini 3.6 Flash (High), Reasoning: HighGemini 3.8 Flash: Exact AA configuration: Gemini 3.8 Flash (High) (release gemini-3-8-flash, row gemini-3-8-flash, UUID 8a999846-4c1d-4ce7-a8b7-1310a7166fd7, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.Gemini 3.6 Flash: Exact AA configuration: Gemini 3.6 Flash (High) (release gemini-3-6-flash, row gemini-3-6-flash, UUID 78332c88-fe60-42c8-af9d-3617e44cf1f5, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.
Winner40.926 points
33.979 points
Artificial Analysis
Source details
Data as of: 10/15/2026
AutomationBench-AAOverall
Test details
No documented difference in the test setupVersion: unspecifiedMetric: Objectives completed without guardrail violationsScoring: Higher is betterGemini 3.8 Flash: Snapshot: Gemini 3.8 Flash (High), Reasoning: High
Gemini 3.6 Flash: Snapshot: Gemini 3.6 Flash (High), Reasoning: HighGemini 3.8 Flash: Exact AA configuration: Gemini 3.8 Flash (High) (release gemini-3-8-flash, row gemini-3-8-flash, UUID 8a999846-4c1d-4ce7-a8b7-1310a7166fd7, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.Gemini 3.6 Flash: Exact AA configuration: Gemini 3.6 Flash (High) (release gemini-3-6-flash, row gemini-3-6-flash, UUID 78332c88-fe60-42c8-af9d-3617e44cf1f5, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.
Winner59.9%
53.0%
Artificial Analysis
Source details
Data as of: 10/15/2026
BioMysteryBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Harness: Terminus 2, Temperature: 1, Output limit: 65,536 tokens
Winner62.222 %
58.519 %
Vals AI
Source details
Data as of: 10/12/2026
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner36.546 %
30.928 %
Vals AI
Source details
Data as of: 10/12/2026
CyberBench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
43.75 %
Winner45.357 %
Vals AI
Source details
Data as of: 10/12/2026
EMBOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner72.196 %
65.411 %
Vals AI
Source details
Data as of: 10/12/2026
Finance Agent (v2)Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner61.435 %
56.296 %
Vals AI
Source details
Data as of: 10/12/2026
GDP.pdfOverall
Test details
No documented difference in the test setupVersion: unspecifiedMetric: All-pass rateScoring: Higher is betterGemini 3.8 Flash: Snapshot: Gemini 3.8 Flash (High), Reasoning: High
Gemini 3.6 Flash: Snapshot: Gemini 3.6 Flash (High), Reasoning: HighGemini 3.8 Flash: Exact AA configuration: Gemini 3.8 Flash (High) (release gemini-3-8-flash, row gemini-3-8-flash, UUID 8a999846-4c1d-4ce7-a8b7-1310a7166fd7, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.Gemini 3.6 Flash: Exact AA configuration: Gemini 3.6 Flash (High) (release gemini-3-6-flash, row gemini-3-6-flash, UUID 78332c88-fe60-42c8-af9d-3617e44cf1f5, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.
Winner21.0%
17.4%
Artificial Analysis
Source details
Data as of: 10/15/2026
GDPval-AAOverall
Test details
No documented difference in the test setupVersion: v2.1Metric: GDPval-AA EloScoring: Higher is betterGemini 3.8 Flash: Snapshot: Gemini 3.8 Flash (High), Reasoning: High
Gemini 3.6 Flash: Snapshot: Gemini 3.6 Flash (High), Reasoning: HighGemini 3.8 Flash: Exact AA configuration: Gemini 3.8 Flash (High) (release gemini-3-8-flash, row gemini-3-8-flash, UUID 8a999846-4c1d-4ce7-a8b7-1310a7166fd7, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.Gemini 3.6 Flash: Exact AA configuration: Gemini 3.6 Flash (High) (release gemini-3-6-flash, row gemini-3-6-flash, UUID 78332c88-fe60-42c8-af9d-3617e44cf1f5, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.
Winner1,436.3 elo
1,284.34 elo
Artificial Analysis
Source details
Data as of: 10/15/2026
GPQA DiamondOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner94.444 %
93.434 %
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 betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner10 %
3.333 %
Vals AI
Source details
Data as of: 10/12/2026
Humanity's Last ExamOverall
Test details
No documented difference in the test setupVersion: unspecifiedMetric: Text-only pass@1 accuracyScoring: Higher is betterGemini 3.8 Flash: Snapshot: Gemini 3.8 Flash (High), Reasoning: High
Gemini 3.6 Flash: Snapshot: Gemini 3.6 Flash (High), Reasoning: HighGemini 3.8 Flash: Exact AA configuration: Gemini 3.8 Flash (High) (release gemini-3-8-flash, row gemini-3-8-flash, UUID 8a999846-4c1d-4ce7-a8b7-1310a7166fd7, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.Gemini 3.6 Flash: Exact AA configuration: Gemini 3.6 Flash (High) (release gemini-3-6-flash, row gemini-3-6-flash, UUID 78332c88-fe60-42c8-af9d-3617e44cf1f5, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.
Winner47.8%
Artificial Analysis describes this comparable run as 2,158 text-only questions, not the full 2,500-question dataset.
40.8%
Artificial Analysis describes this comparable run as 2,158 text-only questions, not the full 2,500-question dataset.		Artificial Analysis
Source details
Data as of: 10/15/2026
IOIOverall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner56.944 %
35.056 %
Vals AI
Source details
Data as of: 10/14/2026
Legal Research BenchOverall · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner38.942 %
25 %
Vals AI
Source details
Data as of: 10/12/2026
LegalBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner86.993 %
86.705 %
Vals AI
Source details
Data as of: 10/13/2026
LiveCodeBench v6Overall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner89.484 %
88.08 %
Vals AI
Source details
Data as of: 09/01/2026
LMArena Code Arena WebDevOverall
Test details
No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGemini 3.8 Flash: Snapshot: gemini-3.8-flash-high, Reasoning: high, Harness: Arena Code Arena WebDev
Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena Code Arena WebDevGemini 3.8 Flash: Arena rating from 10,077 published pairwise votes.Gemini 3.6 Flash: Arena rating from 8,768 published pairwise votes.
Winner1,584.77
95% confidence interval: ±7.59The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
1,538.044
95% confidence interval: ±7.497The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.		LMArena
Source details
Data as of: 10/13/2026
LMArena Text, Style ControlOverall
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.8 Flash: Snapshot: gemini-3.8-flash-high, Reasoning: high, Harness: Arena Text, style control
Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena Text, style controlGemini 3.8 Flash: Arena rating from 35,670 published pairwise votes.Gemini 3.6 Flash: Arena rating from 36,107 published pairwise votes.
Winner1,496.319
95% confidence interval: ±4.654The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
1,482.911
95% confidence interval: ±4.426The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.		LMArena
Source details
Data as of: 10/13/2026
LMArena Vision, Style ControlOverall
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.8 Flash: Snapshot: gemini-3.8-flash-high, Reasoning: high, Harness: Arena Vision, style control
Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena Vision, style controlGemini 3.8 Flash: Arena rating from 3,792 published pairwise votes.Gemini 3.6 Flash: Arena rating from 8,127 published pairwise votes.
No clear lead1,289.129
95% confidence interval: ±10.62The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
1,280.714
95% confidence interval: ±8.17The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.		LMArena
Source details
Data as of: 10/09/2026
MedCodeOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.8 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Gemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens
48.135 %
Higher measured value53.153 %
Vals AI
Source details
Data as of: 10/13/2026
MedScribeOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.8 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Gemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens
Higher measured value84.496 %
79.661 %
Vals AI
Source details
Data as of: 10/13/2026
MMLU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner90.221 %
89.276 %
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 betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner89.075 %
88.382 %
Vals AI
Source details
Data as of: 09/01/2026
MortgageTaxOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
65.342 %
Winner67.608 %
Vals AI
Source details
Data as of: 09/01/2026
ProgramBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: fully resolved rateScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner1 %
0 %
Vals AI
Source details
Data as of: 10/12/2026
Public Benefits Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner65.291 %
56.563 %
Vals AI
Source details
Data as of: 10/12/2026
SAGEOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens
35.064 %
Winner48.686 %
Vals AI
Source details
Data as of: 10/08/2026
SWE-bench VerifiedOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner80 %
79.6 %
Vals AI
Source details
Data as of: 09/01/2026
Tax Agent BenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner32.124 %
18.038 %
Vals AI
Source details
Data as of: 10/12/2026
TaxEval v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
74.448 %
Winner74.857 %
Vals AI
Source details
Data as of: 09/01/2026
Terminal-BenchOverall
Test details
No documented difference in the test setupVersion: 4.0Metric: Task successScoring: Higher is betterGemini 3.8 Flash: Snapshot: Gemini 3.8 Flash (High), Reasoning: High
Gemini 3.6 Flash: Snapshot: Gemini 3.6 Flash (High), Reasoning: HighGemini 3.8 Flash: Exact AA configuration: Gemini 3.8 Flash (High) (release gemini-3-8-flash, row gemini-3-8-flash, UUID 8a999846-4c1d-4ce7-a8b7-1310a7166fd7, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.Gemini 3.6 Flash: Exact AA configuration: Gemini 3.6 Flash (High) (release gemini-3-6-flash, row gemini-3-6-flash, UUID 78332c88-fe60-42c8-af9d-3617e44cf1f5, reasoning=true, source reasoning-token configuration budget=0, suffix=High). This configured value is not measured token consumption.
Winner19.7%
7.1%
Artificial Analysis
Source details
Data as of: 10/15/2026
Terminal-Bench 2.1Overall
Test details
No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner81.273 %
73.783 %
Vals AI
Source details
Data as of: 09/28/2026
Terminal-Bench ScienceOverall
Test details
No documented difference in the test setupVersion: 0.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 65,536 tokens
Winner8.571 %
4.286 %
Vals AI
Source details
Data as of: 10/14/2026
Vibe Code Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Harness: OpenHands, Temperature: 1, Output limit: 65,536 tokens
Winner78.651 %
64.005 %
Vals AI
Source details
Data as of: 10/12/2026
BioMysteryBenchHard
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Harness: Terminus 2, Temperature: 1, Output limit: 65,536 tokens
Tie21.569 %
Tie21.569 %
Vals AI
Source details
Data as of: 10/12/2026
Code MigrationCLI
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner25.871 %
19.332 %
Vals AI
Source details
Data as of: 10/12/2026
CyberBench v1.1Patch
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner87.5 %
85.714 %
Vals AI
Source details
Data as of: 10/12/2026
EMBComps
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner76.435 %
70.019 %
Vals AI
Source details
Data as of: 10/12/2026
Finance Agent (v2)Adjustments
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner54.828 %
53.608 %
Vals AI
Source details
Data as of: 10/12/2026
GPQA DiamondFew-Shot CoT
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner94.949 %
92.424 %
Vals AI
Source details
Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed
Test details
No documented difference in the test setupVersion: 1Metric: criteria pass rateScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner87.681 %
79.71 %
Vals AI
Source details
Data as of: 10/12/2026
IOIIOI 2024
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner55.667 %
40.667 %
Vals AI
Source details
Data as of: 10/14/2026
Legal Research BenchAdministrative / Regulatory · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner46.97 %
31.818 %
Vals AI
Source details
Data as of: 10/12/2026
LegalBenchConclusion Tasks
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
90.691 %
Winner91.081 %
Vals AI
Source details
Data as of: 10/13/2026
LiveCodeBench v6Easy
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Tie99.068 %
Tie99.068 %
Vals AI
Source details
Data as of: 09/01/2026
LMArena Code Arena WebDevImage to webdev
Test details
No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGemini 3.8 Flash: Snapshot: gemini-3.8-flash-high, Reasoning: high, Harness: Arena Code Arena WebDev
Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena Code Arena WebDevGemini 3.8 Flash: Arena rating from 2,015 published pairwise votes.Gemini 3.6 Flash: Arena rating from 1,799 published pairwise votes.
Winner1,593.067
95% confidence interval: ±13.862The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
1,544.911
95% confidence interval: ±14.31The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.		LMArena
Source details
Data as of: 10/09/2026
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 betterGemini 3.8 Flash: Snapshot: gemini-3.8-flash-high, Reasoning: high, Harness: Arena Text, style control
Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena Text, style controlGemini 3.8 Flash: Arena rating from 6,520 published pairwise votes.Gemini 3.6 Flash: Arena rating from 6,836 published pairwise votes.
No clear lead1,479.887
95% confidence interval: ±8.136The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
1,472.186
95% confidence interval: ±7.855The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.		LMArena
Source details
Data as of: 10/13/2026
LMArena Vision, Style ControlChinese
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.8 Flash: Snapshot: gemini-3.8-flash-high, Reasoning: high, Harness: Arena Vision, style control
Gemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena Vision, style controlGemini 3.8 Flash: Arena rating from 182 published pairwise votes.Gemini 3.6 Flash: Arena rating from 479 published pairwise votes.
No clear lead1,379.729
95% confidence interval: ±43.521The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
1,329.153
95% confidence interval: ±27.579The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.		LMArena
Source details
Data as of: 10/09/2026
MMLU-ProBiology
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner94.979 %
94.7 %
Vals AI
Source details
Data as of: 09/01/2026
MortgageTaxNumerical Extraction
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
70.588 %
Winner76.789 %
Vals AI
Source details
Data as of: 09/01/2026
ProgramBenchAlmost Resolved
Test details
No documented difference in the test setupVersion: 1Metric: almost-resolved rateScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner14 %
2.5 %
Vals AI
Source details
Data as of: 10/12/2026
SAGEAutomata
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens
33.334 %
Winner34.92 %
Vals AI
Source details
Data as of: 10/08/2026
SWE-bench Verified<15 min fix
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner89.691 %
87.113 %
Vals AI
Source details
Data as of: 09/01/2026
Tax Agent BenchControversy & Precedence Analysis
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner6.667 %
3.333 %
Vals AI
Source details
Data as of: 10/12/2026
TaxEval v2Correctness
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
62.469 %
Winner63.532 %
Vals AI
Source details
Data as of: 09/01/2026
Terminal-Bench 2.1Easy
Test details
No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Tie100 %
Tie100 %
Vals AI
Source details
Data as of: 09/28/2026
Terminal-Bench ScienceEarth Sciences
Test details
No documented difference in the test setupVersion: 0.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 65,536 tokens
0 %
Winner12.5 %
Vals AI
Source details
Data as of: 10/14/2026
BioMysteryBenchHuman-solvable
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Harness: Terminus 2, Temperature: 1, Output limit: 65,536 tokens
Winner71.689 %
67.123 %
Vals AI
Source details
Data as of: 10/12/2026
Code MigrationCOBOL
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner68.571 %
65.714 %
Vals AI
Source details
Data as of: 10/12/2026
CyberBench v1.1PoC
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
0 %
Winner5 %
Vals AI
Source details
Data as of: 10/12/2026
EMBDataroom
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Winner86.218 %
72.965 %
Vals AI
Source details
Data as of: 10/12/2026

Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

SVG short test

One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.

Shared test round: 4ae5d8eeb9a9

Gemini 3.8 Flash

Unavailable in this round

Gemini 3.6 Flash

Unavailable in this round

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Gemini 3.8 Flash

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

Reasoning (requested): high

Current attempt
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
google/gemini-3.8-flash
API model reported in response
google/gemini-3.8-flash
Reasoning setting
high
Pinned endpoint
Google AI Studio | google/gemini-3.8-flash-20260902
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Failed
Response time
40.2 s

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Earlier attempts (3)
  • Oct 2, 2026API request failedReasoning setting: high
  • Oct 1, 2026API request failedReasoning setting: high
  • Sep 7, 2026API request failedReasoning setting: high

Gemini 3.6 Flash

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

Reasoning (requested): high

Current attempt
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
google/gemini-3.6-flash
API model reported in response
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
Failed
Response time
39.6 s

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Earlier attempts (3)
  • Oct 2, 2026API request failedReasoning setting: high
  • Oct 1, 2026API request failedReasoning setting: high
  • Sep 7, 2026API request failedReasoning setting: high
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 Gemini 3.8 Flash and Gemini 3.6 Flash with other leading models using the same data and benchmark logic.

View the complete LLM comparison