Venice Atlas
← Back to model catalog

VENICE ATLAS · MODEL DOSSIER · GEMINI 4 ARGON

Model overview

Gemini 4 Argon

Gemini 4 Argon is Google's frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable thinking.

gemini-4-argon · venice.ai
Text · Venice catalog$2.50 per 1M tokensPrice on Venice AI
ModalityTextOn Venice AI
Primary price$2.50 per 1M tokensper 1M tokens
Context window1MMax tokens
Benchmarks19Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Agents#441.06 ratingCoding#642.36 ratingVision#737.12 ratingGeneral intelligence#454.98 ratingKnowledge#121.52 ratingLong Context#230.56 ratingMultimodal#637.19 ratingReasoning#553.03 ratingScience#149.75 ratingSpatial Reasoning#629.01 ratingSystems#119.52 ratingTool Calling#431.81 rating
Agents3 results
Agents' Last Examagents-last-exam · agents
39.5%
ReportedOct 2026
AutomationBenchautomationbench · agents
51.3%
ReportedOct 2026
PostTrainBenchposttrainbench · agents
45.3%
ReportedOct 2026
Biology1 result
LABBench2labbench2 · biology
88.8%
ReportedOct 2026
Coding4 results
CWE-Benchcwe-bench · code
68.0%
ReportedOct 2026
DeepSWE 1.1deepswe-1.1 · code
77.9%
ReportedOct 2026
FrontierSWE V2frontierswe-v2 · code
55.0%
ReportedOct 2026
Vibe Code Benchvibe-code-bench · code
91.9%
ReportedOct 2026
Finance1 result
Vals Finance Agent v2vals-finance-agent-v2 · finance
65.4%
ReportedOct 2026
Knowledge1 result
Vals Indexvals-index · knowledge
68.9%
ReportedOct 2026
Legal1 result
Harvey's Legal Agent Benchmarkharveys-legal-agent-benchmark · legal
19.6%
ReportedOct 2026
Math1 result
RiemannBenchriemannbench · math
76.0%
ReportedOct 2026
Multimodal1 result
OSWorld 2.0osworld-2.0 · multimodal
69.2%
ReportedOct 2026
Reasoning4 results
Graphwalks BFS <128kgraphwalks-bfs-<128k · reasoning
99.7%
ReportedOct 2026
Graphwalks BFS >128kgraphwalks-bfs->128k · reasoning
84.2%
ReportedOct 2026
Terminal-Bench 4.0terminal-bench-4.0 · reasoning
57.4%
ReportedOct 2026
Terminal-Bench-Science 0.1terminal-bench-science-0.1 · reasoning
57.6%
ReportedOct 2026
Vision2 results
Chartography (no tools)chartography-no-tools · vision
71.6%
ReportedOct 2026
LVBenchlvbench · vision
91.7%
ReportedOct 2026

Learn what each benchmark measures ↗

Related models

More from google

gemini-3-8-flashGemini 3.8 Flash$0.94 input per 1M tokens ↗google-gemma-3-27b-itGoogle Gemma 3 27B Instruct$0.12 input per 1M tokens ↗gemini-3-1-pro-previewGemini 3.1 Pro Preview$2.50 input per 1M tokens ↗