SmophyAI

Published daily · Next update 02:00 UTC

Real data comparison

DeepSeek: DeepSeek V4.1 Flash (batch) vs Tencent: Hy3 preview

On quality, DeepSeek: DeepSeek V4.1 Flash (batch) leads (39.5 vs 25.3). On price, DeepSeek: DeepSeek V4.1 Flash (batch) is cheaper ($0.20 vs $0.29 per 1M). In real production usage, DeepSeek: DeepSeek V4.1 Flash (batch) is used more (rank #4 vs #13 of 353).

  • DeepSeek: DeepSeek V4.1 Flash (batch)
  • Tencent: Hy3 preview
Quality (Intelligence Index)39.5 / 25.3
Price ($/1M blended)$0.20 / $0.29
Average usage share10.69% / 2.60%
Context window1,048,576 / 262,144
Quality per dollar197.5 pts/$ / 88.8 pts/$

Usage share over time

18.62%13.97%9.31%4.66%0.00%Share of usageJul 5Sep 14Sep 22
  • DeepSeek: DeepSeek V4.1 Flash (batch)
  • Tencent: Hy3 preview

Frequently asked questions

DeepSeek: DeepSeek V4.1 Flash (batch) vs Tencent: Hy3 preview: which is better quality?

DeepSeek: DeepSeek V4.1 Flash (batch) scores higher on Artificial Analysis's Intelligence Index (39.5 vs 25.3).

DeepSeek: DeepSeek V4.1 Flash (batch) vs Tencent: Hy3 preview: which is cheaper?

DeepSeek: DeepSeek V4.1 Flash (batch) is cheaper at $0.20/1M vs $0.29/1M.

DeepSeek: DeepSeek V4.1 Flash (batch) vs Tencent: Hy3 preview: which is used more?

DeepSeek: DeepSeek V4.1 Flash (batch) has higher real OpenRouter usage share (rank #4 vs #13 of 353).

Source: OpenRouter (openrouter.ai/rankings), as of September 23, 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.