DataLearner logo

DeepSeek-V4-Flash-Vision-ExpvsGemini 3.7 Flash

Across 4 shared benchmarks, Gemini 3.7 Flash leads overall: DeepSeek-V4-Flash-Vision-Exp wins 1, Gemini 3.7 Flash wins 3, with 0 ties and an average score difference of -2.90.

DeepSeek-AI
DeepSeek-V4-Flash-Vision-Exp

DeepSeek-AI · 2026-08-21 · Multimodal model

Google Deep Mind
Gemini 3.7 Flash

Google Deep Mind · 2026-08-13 · Multimodal model

DeepSeek-V4-Flash-Vision-Exp1 win(25%)(75%)3 winsGemini 3.7 Flash

Benchmark scores

Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.

AI Agent - Tool Usage

Gemini 3.7 Flash 2/2
BenchmarkDeepSeek-V4-Flash-Vision-ExpGemini 3.7 FlashDiff
AutomationBench25.707 / 8Max (With Tools)30.404 / 8Thinking (With Tools)-4.70
Terminal-Bench 2.183.9011 / 44Max (With Tools)85.809 / 44Thinking (With Tools)-1.90

Agent Level Benchmark

DeepSeek-V4-Flash-Vision-Exp 1/1
BenchmarkDeepSeek-V4-Flash-Vision-ExpGemini 3.7 FlashDiff
Agents' Last Exam27.306 / 11Max (With Tools)26.308 / 11Thinking Medium (With Tools)+1

Coding and Software Engineer

Gemini 3.7 Flash 1/1
BenchmarkDeepSeek-V4-Flash-Vision-ExpGemini 3.7 FlashDiff
DeepSWE59.3012 / 27Max (With Tools)65.3010 / 27Thinking High (With Tools)-6

Specs

FieldDeepSeek-V4-Flash-Vision-ExpGemini 3.7 Flash
PublisherDeepSeek-AIGoogle Deep Mind
Release date2026-08-212026-08-13
Model typeMultimodal modelMultimodal model
ArchitectureDenseDense
ParametersNot availableNot available
Context length1M1M
Max output384K64K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemDeepSeek-V4-Flash-Vision-ExpGemini 3.7 Flash
Text input$0.22 / 1M tokens$0.75 / 1M tokens
Text output$0.66 / 1M tokens$3.75 / 1M tokens
Cache read$0.007 / 1M tokens$0.075 / 1M tokens

Summary

  • DeepSeek-V4-Flash-Vision-Expleads in:Agent Level Benchmark (1/1)
  • Gemini 3.7 Flashleads in:AI Agent - Tool Usage (2/2), Coding and Software Engineer (1/1)

On average across the 4 shared benchmarks, Gemini 3.7 Flash scores 2.90 higher.

Largest single-benchmark gap: DeepSWE — DeepSeek-V4-Flash-Vision-Exp 59.30 vs Gemini 3.7 Flash 65.30 (-6).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.