Venice Atlas
← Back to model catalog

VENICE ATLAS · MODEL DOSSIER · GEMINI 3.7 FLASH

Model overview

Gemini 3.7 Flash

Gemini 3.7 Flash is Google's most capable Flash model, built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.

gemini-3-7-flash · venice.ai
Text · Venice catalog$0.94 per 1M tokensPrice on Venice AI
ModalityTextOn Venice AI
Primary price$0.94 per 1M tokensper 1M tokens
Context window1MMax tokens
Benchmarks18Benchmark results

Benchmark results

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

Agents#2831.52 ratingVision#2432.14 ratingGeneral intelligence#2547.50 ratingKnowledge#615.81 ratingLong Context#330.47 ratingMultimodal#1633.12 ratingReasoning#3045.28 ratingScience#21-3.23 rating
Agents2 results
Agents' Last Examagents-last-exam · agents
26.3%
ReportedOct 2026
AutomationBenchautomationbench · agents
30.4%
ReportedOct 2026
Biology2 results
BioMysteryBenchbiomysterybench · biology
43.5%
ReportedOct 2026
LABBench2labbench2 · biology
82.1%
ReportedOct 2026
Coding2 results
DeepSWE 1.1deepswe-1.1 · code
65.3%
ReportedOct 2026
WebDev Arenawebdev-arena · code
79.4%
ReportedOct 2026
General intelligence3 results
Artificial Analysisartificial-analysis · general
56.0%
ReportedOct 2026
GDP.pdfgdp-pdf · general
34.0%
ReportedOct 2026
GDPval-AAgdpval-aa · general
50.8%
ReportedOct 2026
Knowledge2 results
Harvey LAB-AAharvey-lab-aa · knowledge
90.7%
ReportedOct 2026
HLE-Verifiedhle-verified · knowledge
53.6%
ReportedOct 2026
Long Context1 result
MRCR v2 (8-needle)mrcr-v2-(8-needle) · long_context
97.0%
ReportedOct 2026
Multimodal1 result
OSWorld 2.0osworld-2.0 · multimodal
47.9%
ReportedOct 2026
Reasoning4 results
CharXiv-Rcharxiv-r · reasoning
88.7%
ReportedOct 2026
FrontierCode 1.1frontiercode-1.1 · reasoning
43.6%
ReportedOct 2026
Terminal-Bench 2.1terminal-bench-2.1 · reasoning
85.8%
ReportedOct 2026
Terminal-Bench 3.0terminal-bench-3.0 · reasoning
14.9%
ReportedOct 2026
Vision1 result
LVBenchlvbench · vision
85.4%
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 ↗gemini-4-argonGemini 4 Argon$2.50 input per 1M tokens ↗google-gemma-3-27b-itGoogle Gemma 3 27B Instruct$0.12 input per 1M tokens ↗