SmophyAI

Published daily · Next update 02:00 UTC

Real data comparison

DeepSeek: DeepSeek V4 Pro 0423 vs Google: Gemini 3.8 Flash (batch)

On quality, Google: Gemini 3.8 Flash (batch) leads (41.2 vs 36.3). On price, DeepSeek: DeepSeek V4 Pro 0423 is cheaper ($0.87 vs $1.50 per 1M). In real production usage, DeepSeek: DeepSeek V4 Pro 0423 is used more (rank #10 vs #22 of 325).

  • DeepSeek: DeepSeek V4 Pro 0423
  • Google: Gemini 3.8 Flash (batch)
Quality (Intelligence Index)36.3 / 41.2
Price ($/1M blended)$0.87 / $1.50
Average usage share4.04% / 1.54%
Best provider uptime100.0% / 100.0%
Coding index68.8 / 76.3
Agentic index42.3 / 41.1
Context window1,048,576 / 1,048,576
Quality per dollar41.8 pts/$ / 27.5 pts/$

Usage share over time

7.35%5.51%3.68%1.84%0.00%Share of usageJul 5Aug 6Sep 8
  • DeepSeek: DeepSeek V4 Pro 0423
  • Google: Gemini 3.8 Flash (batch)

Frequently asked questions

DeepSeek: DeepSeek V4 Pro 0423 vs Google: Gemini 3.8 Flash (batch): which is better quality?

Google: Gemini 3.8 Flash (batch) scores higher on Artificial Analysis's Intelligence Index (41.2 vs 36.3).

DeepSeek: DeepSeek V4 Pro 0423 vs Google: Gemini 3.8 Flash (batch): which is cheaper?

DeepSeek: DeepSeek V4 Pro 0423 is cheaper at $0.87/1M vs $1.50/1M.

DeepSeek: DeepSeek V4 Pro 0423 vs Google: Gemini 3.8 Flash (batch): which is used more?

DeepSeek: DeepSeek V4 Pro 0423 has higher real OpenRouter usage share (rank #10 vs #22 of 325).

Source: OpenRouter (openrouter.ai/rankings), as of September 9, 2026.

Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).

Methodology: www.smophy.ai/benchmark/methodology

Token counts originate from each provider's own tokenizer and are not directly comparable across providers.