SmophyAI

Published daily · Next update 02:00 UTC

DeepSeek · DeepSeek family

DeepSeek: DeepSeek V3.2

DeepSeek: DeepSeek V3.2 ranks #50 of 85 models by Artificial Analysis quality score (32.6) at $0.30/1M tokens blended - and ranks #29 of 291 by average real OpenRouter usage share over the trailing 35-day window (0.66%). Available from 14 providers at up to 100.0% uptime.

  1. Quality (Intelligence Index) - 32.6
  2. Coding index - 44.2
  3. Agentic index - 18.3
  4. Price (blended $/1M) - 0.30
  5. Context window - 163,840
  6. Usage rank - #29 of 291
  7. Providers - 14
  8. Open/closed - open
Provider reliability →Compare DeepSeek versions →

Usage share over time

1.08%0.81%0.54%0.27%0.00%Share of usageJul 5Jul 22Aug 8

What DeepSeek: DeepSeek V3.2 is actually used for

Share of each real task category's classified traffic this model handles, from OpenRouter's task classification.

TaskShare of task traffic
Roleplay & Fiction3.9%

Frequently asked questions

What is DeepSeek: DeepSeek V3.2's quality score?

DeepSeek: DeepSeek V3.2 scores 32.6 on Artificial Analysis's Intelligence Index, ranking #50 of 85 models with a published score.

How much does DeepSeek: DeepSeek V3.2 cost?

DeepSeek: DeepSeek V3.2 costs $0.30 per 1M tokens (blended 75% prompt / 25% completion pricing).

Is DeepSeek: DeepSeek V3.2 widely used?

DeepSeek: DeepSeek V3.2 ranks #29 of 291 models by average real OpenRouter usage share, averaging 0.66% of classified token volume over the trailing 35-day window.

Is DeepSeek: DeepSeek V3.2 open-weight or closed?

DeepSeek: DeepSeek V3.2 is an open-weight model.

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

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

Methodology: smophy.ai/benchmark/methodology

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