Head-to-head comparison

Gemini 4 Argon vs. Qwen 3.8 Max 0902

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

shared result series: 171
distinct benchmark metrics: 22
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 Gemini 4 Argon and Qwen 3.8 Max 0902
Attribute	Gemini 4 Argon	Qwen 3.8 Max 0902
Provider	Google DeepMind	Alibaba
Released	Oct 13, 2026	Sep 2, 2026
Availability	Active	API-only
Model type	Proprietary	Proprietary
Parameters	Not published	2.4T
Architecture	Not published	Mixture of Experts
Context window	1,048,576 tokens shared across input, thinking, and output	1,000,000 tokens
Knowledge cutoff	Not published	Not published
Technical sources	Model	Model

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Gemini 4 Argon and Qwen 3.8 Max 0902
Price type	Gemini 4 Argon	Qwen 3.8 Max 0902
API input	$2	$1.65
API output	$10	$4.951
Cache read	$0.1	$0.137
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	10/25/2026 Source	09/22/2026 Source
Gemini 4 Argon, Standard pricing through November 30, 2026 Per 1 million tokens: $2.00 input, $10.00 output including thinking, and $0.10 cached input. Source
Gemini 4 Argon, Standard pricing from December 1, 2026 Per 1 million tokens: $4.00 input, $20.00 output including thinking, and $0.20 cached input. Source
Gemini 4 Argon, Caching Implicit caching only; explicit caching is not supported. Source

Gemini 4 ArgonQwen 3.8 Max 0902

API inputUSD per 1M tokens, base tier

Gemini 4 Argon$2

Qwen 3.8 Max 0902$1.65

API outputUSD per 1M tokens, base tier

Gemini 4 Argon$10

Qwen 3.8 Max 0902$4.951

Cache readUSD per 1M tokens, base tier

Gemini 4 Argon$0.1

Qwen 3.8 Max 0902$0.137

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 Gemini 4 Argon is available in the stored OpenRouter snapshot. The official direct price is still shown.

Provider pricing for Gemini 4 Argon and Qwen 3.8 Max 0902
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Gemini 4 Argon	Google DeepMind	Direct from developerStandard API	Lowest listed price: $2	Lowest listed price: $10	Source10/25/2026
Qwen 3.8 Max 0902	Alibaba	Direct from developerStandard API	Lowest listed price: $1.65	Lowest listed price: $4.951	Source09/22/2026
	Alibaba	Via OpenRouteralibaba	$2	$6	Source10/26/2026
	Alibaba	Via OpenRouteralibaba/us-east-1	$2	$6	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

Gemini 4 Argon

Overall index

92.6

Qwen 3.8 Max 0902

Overall index

51.2

Gemini 4 Argon leads in 11 of 11 shared areas.

Area	Gemini 4 Argon	Qwen 3.8 Max 0902
Coding	92.4	53.2
Reasoning	91.6	55.6
Mathematics	89.3	46.3
Knowledge	93.6	45.4
General	90.2	51.9
Finance	94.6	48.9
Legal	94.9	59.3
Health	92.8	39.1
Cybersecurity	92.8	47.8
Productivity	90.6	62.2
Education	93.6	61.1

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

Gemini 4 ArgonQwen 3.8 Max 0902

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

Gemini 4 Argon68.173 %

Qwen 3.8 Max 090223.958 %

CyberBench v1.1Overall. Higher is better. Test setup not documented as identical

Gemini 4 Argon77.857 %

Qwen 3.8 Max 090228.572 %

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

Gemini 4 Argon75.244 %

Qwen 3.8 Max 090260.066 %

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

Gemini 4 Argon65.401 %

Qwen 3.8 Max 090250.593 %

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

Gemini 4 Argon19.583 %

Qwen 3.8 Max 090210.417 %

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

Gemini 4 Argon100 %

Qwen 3.8 Max 090268.889 %

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

Gemini 4 Argon54.808 %

Qwen 3.8 Max 090247.596 %

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

Gemini 4 Argon88.299 %

Qwen 3.8 Max 090283.609 %

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

Gemini 4 Argon58.801 %

Qwen 3.8 Max 090240.668 %

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

Gemini 4 Argon87.427 %

Qwen 3.8 Max 090284.947 %

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

Gemini 4 Argon45.495 %

Qwen 3.8 Max 090223.874 %

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

Gemini 4 Argon2.5 %

Qwen 3.8 Max 09020 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Gemini 4 Argon and Qwen 3.8 Max 0902
Benchmark and task	Gemini 4 Argon	Qwen 3.8 Max 0902	Source
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value68.173 %	23.958 %	Vals AI Source details Data as of: 10/12/2026
CyberBench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value77.857 %	28.572 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value75.244 %	60.066 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value65.401 %	50.593 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value19.583 %	10.417 %	Vals AI Source details Data as of: 10/12/2026
IOIOverall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value100 %	68.889 %	Vals AI Source details Data as of: 10/14/2026
Legal Research BenchOverall · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value54.808 %	47.596 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value88.299 %	83.609 %	Vals AI Source details Data as of: 10/13/2026
MedCodeOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 1, Output limit: 30,000 tokens	Higher measured value58.801 %	40.668 %	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 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 1, Output limit: 30,000 tokens	Higher measured value87.427 %	84.947 %	Vals AI Source details Data as of: 10/13/2026
MysteryMechanismOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value45.495 %	23.874 %	Vals AI Source details Data as of: 10/12/2026
ProgramBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value2.5 %	0 %	Vals AI Source details Data as of: 10/12/2026
ProofBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value99 %	58 %	Vals AI Source details Data as of: 10/12/2026
Public Benefits Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value69.756 %	67.118 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 1, Output limit: 30,000 tokens	Higher measured value53.645 %	51.254 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench MultimodalOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value56.042 %	39.167 %	Vals AI Source details Data as of: 10/13/2026
Tax Agent BenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value44.56 %	32.095 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0Overall Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value57.576 %	34.343 %	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 betterGemini 4 Argon: Reasoning: high, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Harness: Mini-SWE-agent, Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value44.286 %	12.857 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value68.896 %	48.27 %	Vals AI Source details Data as of: 10/13/2026
Vibe Code Bench 1-100Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.0Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Harness: OpenHands, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Harness: OpenHands, Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value21.2 %	12.833 %	Vals AI Source details Data as of: 10/14/2026
Vibe Code Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Harness: OpenHands, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Harness: OpenHands, Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value91.906 %	64.696 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value67.564 %	11.944 %	Vals AI Source details Data as of: 10/12/2026
CyberBench v1.1Patch Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value85.714 %	57.143 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value82.979 %	54.32 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value60.527 %	48.426 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value94.203 %	90.942 %	Vals AI Source details Data as of: 10/12/2026
IOIIOI 2024 Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value100 %	78.167 %	Vals AI Source details Data as of: 10/14/2026
Legal Research BenchAdministrative / Regulatory · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value68.182 %	59.091 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value90.847 %	88.23 %	Vals AI Source details Data as of: 10/13/2026
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: almost-resolved rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value41 %	10.5 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 1, Output limit: 30,000 tokens	Higher measured value45.635 %	39.682 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench Multimodalbpmn-js Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value71.698 %	62.264 %	Vals AI Source details Data as of: 10/13/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	No direct winner20 %	No direct winner20 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0Hardware Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value46.667 %	0 %	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 betterGemini 4 Argon: Reasoning: high, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Harness: Mini-SWE-agent, Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value62.5 %	12.5 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value69.503 %	23.163 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value70 %	60 %	Vals AI Source details Data as of: 10/12/2026
CyberBench v1.1PoC Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value70 %	0 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value85.109 %	83.536 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value55.789 %	38.229 %	Vals AI Source details Data as of: 10/12/2026
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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	No direct winner20 %	No direct winner20 %	Vals AI Source details Data as of: 10/12/2026
IOIIOI 2025 Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value100 %	68.333 %	Vals AI Source details Data as of: 10/14/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value92.945 %	90.519 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value84.097 %	84.061 %	Vals AI Source details Data as of: 10/13/2026
ProgramBenchFully Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value2.5 %	0 %	Vals AI Source details Data as of: 10/12/2026
SAGECalculus Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 1, Output limit: 30,000 tokens	Higher measured value84.877 %	71.914 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench MultimodalCarbon Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value43.609 %	24.812 %	Vals AI Source details Data as of: 10/13/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value63.603 %	62.591 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0Media Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value83.333 %	50 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceEngineering Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Harness: Mini-SWE-agent, Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value11.111 %	0 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexEMB Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value75.244 %	60.066 %	Vals AI Source details Data as of: 10/13/2026
Code MigrationCode Quality Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	3.574 / 5	Higher measured value4.255 / 5	Vals AI Source details Data as of: 10/12/2026
EMBDCF Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value65.719 %	49.134 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Comparables Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value50.956 %	44.251 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value94.265 %	89.964 %	Vals AI Source details Data as of: 10/12/2026
IOIIOI 2026 Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value100 %	60.167 %	Vals AI Source details Data as of: 10/14/2026
Legal Research BenchBusiness & Commercial · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	No direct winner46.512 %	No direct winner46.512 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchIssue Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value92.941 %	90.635 %	Vals AI Source details Data as of: 10/13/2026
ProgramBenchRaw Pass Rate Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: raw test pass rateScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value83.715 %	39.971 %	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 betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 1, Output limit: 30,000 tokens	Higher measured value74.031 %	69.636 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench MultimodalESLint Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	No direct winner72.727 %	No direct winner72.727 %	Vals AI Source details Data as of: 10/13/2026
Tax Agent BenchCurrent & Temporal Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value66.667 %	49.889 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0ML Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterGemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens Qwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens	Higher measured value69.697 %	48.485 %	Vals AI Source details Data as of: 10/13/2026
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

Gemini 4 Argon

Unavailable in this round

Qwen 3.8 Max 0902

Unavailable in this round

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Gemini 4 Argon

Not tested yet

Qwen 3.8 Max 0902

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: qwen/qwen3.8-max-0902
API model reported in response: qwen/qwen3.8-max-0902
Reasoning setting: high
Pinned endpoint: Alibaba | qwen/qwen3.8-max-20260902
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 189.9 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 Gemini 4 Argon and Qwen 3.8 Max 0902 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Gemini 4 Argon vs. Qwen 3.8 Max 0902

Change model selection

General specifications

API pricing compared

Benchmark index compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Gemini 4 Argon

Qwen 3.8 Max 0902

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons