Head-to-head comparison

Claude Opus 4.8 vs. Gemini 3.7 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: 212
distinct benchmark metrics: 26
latest retrieval: 2026-10-16

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 Claude Opus 4.8 and Gemini 3.7 Flash
Attribute	Claude Opus 4.8	Gemini 3.7 Flash
Provider	Anthropic	Google
Released	May 2026	Aug 13, 2026
Availability	Legacy	Active
Model type	Proprietary	Proprietary
Parameters	Not published	Not published
Architecture	Not published	Not published
Context window	1,000,000 tokens	1,048,576 tokens
Knowledge cutoff	January 2026	March 2026
Technical sources	Model, Knowledge cutoff	Model, 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 Claude Opus 4.8 and Gemini 3.7 Flash
Price type	Claude Opus 4.8	Gemini 3.7 Flash
API input	$5	$0.75
API output	$25	$3.75
Cache read	$0.5	$0.075
Cache write (5 min.)	$6.25	Not listed
Cache write (1 hr.)	$10	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

Claude Opus 4.8Gemini 3.7 Flash

API inputUSD per 1M tokens, base tier

Claude Opus 4.8$5

Gemini 3.7 Flash$0.75

API outputUSD per 1M tokens, base tier

Claude Opus 4.8$25

Gemini 3.7 Flash$3.75

Cache readUSD per 1M tokens, base tier

Claude Opus 4.8$0.5

Gemini 3.7 Flash$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.

No provider tariff for Claude Opus 4.8 is available in the stored OpenRouter snapshot. The official direct price is still shown.

Provider pricing for Claude Opus 4.8 and Gemini 3.7 Flash
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Opus 4.8	Anthropic	Direct from developerStandard API	Lowest listed price: $5	Lowest listed price: $25	Source09/22/2026
Gemini 3.7 Flash	Google	Direct from developerStandard API	$0.75	$3.75	Source09/22/2026
	Google	Via OpenRoutergoogle-vertex/global	$0.75	$3.75	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/global/priority	$1.35	$6.75	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/us	$0.825	$4.125	Source10/26/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio	$0.75	$3.75	Source10/26/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/flex	Lowest listed price: $0.375	Lowest listed price: $1.875	Source10/26/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/priority	$1.35	$6.75	Source10/26/2026

Benchmark index

Benchmark index compared

The index combines independent benchmarks on a scale from 0 to 100. A lead only counts when a model comes first in at least 95% of 200 recalculations with randomly redrawn test families. Otherwise both count as level.

Open the AI leaderboard

Claude Opus 4.8

Overall index

57.0

Gemini 3.7 Flash

Overall index

67.3

Gemini 3.7 Flash leads in 3 of 10 shared areas. 7 areas are tied.

Area	Claude Opus 4.8	Gemini 3.7 Flash
Codingtied	55.3	48.9
Reasoning	46.2	78.1
Knowledgetied	65.6	76.1
Agentstied	56.7	69.9
General	45.3	60.6
Financetied	65.0	65.7
Legaltied	57.4	67.6
Healthtied	67.8	65.6
Multimodal	55.0	79.9
Educationtied	71.1	66.2

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.

Not enough directly matched categories for a reliable radar

Only 2 of at least 5 categories have comparable, direct model measurements. The benchmark tables below show the available evidence without filling missing axes.

Claude Opus 4.8Gemini 3.7 Flash

Code MigrationOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.847.25 %

Gemini 3.7 Flash34.8 %

EMBOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.869.373 %

Gemini 3.7 Flash71.326 %

Finance Agent (v2)Overall. Higher is better. Test setup not documented as identical

Claude Opus 4.853.918 %

Gemini 3.7 Flash59.042 %

GPQA DiamondOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.892.424 %

Gemini 3.7 Flash93.94 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. Test setup not documented as identical

Claude Opus 4.89.583 %

Gemini 3.7 Flash8.75 %

Legal Research BenchOverall · All-pass. Higher is better. Test setup not documented as identical

Claude Opus 4.843.75 %

Gemini 3.7 Flash34.615 %

LegalBenchOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.883.568 %

Gemini 3.7 Flash87.256 %

LiveCodeBench v6Overall. Higher is better. Test setup not documented as identical

Claude Opus 4.887.819 %

Gemini 3.7 Flash88.652 %

LMArena Code Arena WebDevOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.81,536.177

Gemini 3.7 Flash1,589.906

LMArena Vision, Style ControlOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.81,278.955

Gemini 3.7 Flash1,296.875

MedCodeOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.853.217 %

Gemini 3.7 Flash53.39 %

MedScribeOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.885.755 %

Gemini 3.7 Flash83.942 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Opus 4.8 and Gemini 3.7 Flash
Benchmark and task	Claude Opus 4.8	Gemini 3.7 Flash	Source
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value47.25 %	34.8 %	Vals AI Source details Data as of: 10/12/2026
EMBOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	69.373 %	Higher measured value71.326 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	53.918 %	Higher measured value59.042 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	92.424 %	Higher measured value93.94 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value9.583 %	8.75 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchOverall · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value43.75 %	34.615 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	83.568 %	Higher measured value87.256 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	87.819 %	Higher measured value88.652 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevOverall Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Code Arena WebDev Gemini 3.7 Flash: Snapshot: gemini-3.7-flash-high, Reasoning: high, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 17,454 published pairwise votes.Gemini 3.7 Flash: Arena rating from 11,731 published pairwise votes.	1,536.177 95% confidence interval: ±5.702The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Higher measured value1,589.906 95% confidence interval: ±6.967The 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 Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Vision, style control Gemini 3.7 Flash: Snapshot: gemini-3.7-flash-high, Reasoning: high, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 18,852 published pairwise votes.Gemini 3.7 Flash: Arena rating from 4,524 published pairwise votes.	1,278.955 95% confidence interval: ±6.534The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Higher measured value1,296.875 95% confidence interval: ±9.827The 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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens	53.217 %	Higher measured value53.39 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens	Higher measured value85.755 %	83.942 %	Vals AI Source details Data as of: 10/13/2026
MMLU-ProOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	89.585 %	Higher measured value90.121 %	Vals AI Source details Data as of: 09/01/2026
MMMU-ProOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	86.59 %	Higher measured value88.96 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value69.912 %	66.654 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value1 %	0 %	Vals AI Source details Data as of: 10/12/2026
SAGEOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens	Higher measured value54.788 %	49.232 %	Vals AI Source details Data as of: 10/08/2026
SkillsBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Harness: OpenHands, Temperature: 1, Output limit: 65,536 tokens	59.227 %	Higher measured value65.891 %	Vals AI Source details Data as of: 09/27/2026
SWE-bench VerifiedOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value88.6 %	80.8 %	Vals AI Source details Data as of: 09/01/2026
Tax Agent BenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value29.999 %	22.798 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value75.634 %	74.734 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	71.91 %	Higher measured value77.528 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Overall Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value23.232 %	12.121 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceOverall Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 65,536 tokens	4.286 %	Higher measured value7.143 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexOverall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: weighted index scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value55.1 %	51.273 %	Vals AI Source details Data as of: 10/13/2026
Vibe Code Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Harness: OpenHands, Temperature: 1, Output limit: 65,536 tokens	Higher measured value82.725 %	70.395 %	Vals AI Source details Data as of: 10/12/2026
Code MigrationCLI Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value40.143 %	23.543 %	Vals AI Source details Data as of: 10/12/2026
EMBComps Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	72.797 %	Higher measured value74.609 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Adjustments Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	48.387 %	Higher measured value54.718 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondFew-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	91.919 %	Higher measured value95.455 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	87.319 %	Higher measured value89.493 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchAdministrative / Regulatory · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value43.939 %	42.424 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchConclusion Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	88.937 %	Higher measured value91.146 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Easy Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	No direct winner99.068 %	No direct winner99.068 %	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 betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Code Arena WebDev Gemini 3.7 Flash: Snapshot: gemini-3.7-flash-high, Reasoning: high, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 18,540 published pairwise votes.Gemini 3.7 Flash: Arena rating from 11,731 published pairwise votes.	1,555.99 95% confidence interval: ±5.768The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Winner1,589.906 95% confidence interval: ±6.967The 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 betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Vision, style control Gemini 3.7 Flash: Snapshot: gemini-3.7-flash-high, Reasoning: high, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 18,341 published pairwise votes.Gemini 3.7 Flash: Arena rating from 4,524 published pairwise votes.	1,285.632 95% confidence interval: ±6.5The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	No clear lead1,296.875 95% confidence interval: ±9.827The 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 Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	No direct winner94.7 %	No direct winner94.7 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxNumerical Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value79.73 %	75.676 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: almost-resolved rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value15.5 %	9.5 %	Vals AI Source details Data as of: 10/12/2026
SAGEAutomata Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens	Higher measured value41.666 %	35.318 %	Vals AI Source details Data as of: 10/08/2026
SkillsBenchNo Skills Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Harness: OpenHands, Temperature: 1, Output limit: 65,536 tokens	43.674 %	Higher measured value44.887 %	Vals AI Source details Data as of: 09/27/2026
SWE-bench Verified<15 min fix Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value92.784 %	87.113 %	Vals AI Source details Data as of: 09/01/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value13.133 %	6.667 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Correctness Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value64.513 %	63.614 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.1Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value100 %	91.667 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Hardware Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value26.667 %	13.333 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceEarth Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 65,536 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexCode Migration Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value46.942 %	28.997 %	Vals AI Source details Data as of: 10/13/2026
Code MigrationCOBOL Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	No direct winner68.571 %	No direct winner68.571 %	Vals AI Source details Data as of: 10/12/2026
EMBDataroom Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	85.948 %	Higher measured value86.481 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)All-Pass Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	43.517 %	Higher measured value47.45 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondZero-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value92.929 %	92.424 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value87.365 %	85.147 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchInterpretation Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	82.703 %	Higher measured value84.608 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Hard Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	74.571 %	Higher measured value76.286 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevWebdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Code Arena WebDev Gemini 3.7 Flash: Snapshot: gemini-3.7-flash-high, Reasoning: high, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 17,454 published pairwise votes.Gemini 3.7 Flash: Arena rating from 11,731 published pairwise votes.	1,536.177 95% confidence interval: ±5.702The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Higher measured value1,589.906 95% confidence interval: ±6.967The 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 Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Vision, style control Gemini 3.7 Flash: Snapshot: gemini-3.7-flash-high, Reasoning: high, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 1,131 published pairwise votes.Gemini 3.7 Flash: Arena rating from 246 published pairwise votes.	1,334.517 95% confidence interval: ±19.635The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Higher measured value1,367.09 95% confidence interval: ±37.432The 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-ProBusiness Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	92.649 %	Higher measured value92.776 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxSemantic Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value60.095 %	57.631 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchFully Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value1 %	0 %	Vals AI Source details Data as of: 10/12/2026
SAGELinear Algebra Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens	Higher measured value78.253 %	69.52 %	Vals AI Source details Data as of: 10/08/2026
SkillsBenchWith Skills Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Harness: OpenHands, Temperature: 1, Output limit: 65,536 tokens	59.227 %	Higher measured value65.891 %	Vals AI Source details Data as of: 09/27/2026
SWE-bench Verified>4 hours Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Gemini 3.7 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value66.667 %	33.333 %	Vals AI Source details Data as of: 09/01/2026
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: 43b8c5c46830

Claude Opus 4.8

Unavailable in this round

Gemini 3.7 Flash

Unavailable in this round

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Opus 4.8

Reasoning (requested): high

Current attempt

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: anthropic/claude-opus-4.8
API model reported in response: anthropic/claude-opus-4.8
Reasoning setting: high
Pinned endpoint: Anthropic | anthropic/claude-4.8-opus-20260528
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating
Response time: 18 s

Visually reviewed. This individual test does not establish overall model quality.

Gemini 3.7 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-3.7-flash
API model reported in response: google/gemini-3.7-flash
Reasoning setting: high
Pinned endpoint: Google AI Studio | google/gemini-3.7-flash-20260813
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 28.8 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

Compare Claude Opus 4.8 and Gemini 3.7 Flash with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Claude Opus 4.8 vs. Gemini 3.7 Flash

Change model selection

General specifications

API pricing compared

Benchmark index compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Claude Opus 4.8

Gemini 3.7 Flash

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons