SmophyAI

Published daily · Next update 02:00 UTC

Real data comparison

Xiaomi: MiMo-V2.5 vs StepFun: Step 3.7 Flash

On quality, Xiaomi: MiMo-V2.5 leads (38 vs 30.9). On price, Xiaomi: MiMo-V2.5 is cheaper ($0.18 vs $0.44 per 1M). In real production usage, Xiaomi: MiMo-V2.5 is used more (rank #2 vs #11 of 291). Across 6 real task categories where both models have classified traffic, Xiaomi: MiMo-V2.5 handles more of the traffic in 6 of them.

  • Xiaomi: MiMo-V2.5
  • StepFun: Step 3.7 Flash
Quality (Intelligence Index)38 / 30.9
Price ($/1M blended)$0.18 / $0.44
Average usage share12.72% / 2.36%
Best provider uptime98.9% / 99.4%
Coding index56.8 / 39.6
Agentic index24.4 / 21.7
Context window1,050,000 / 262,144
Quality per dollar217.1 pts/$ / 70.6 pts/$

Head-to-head by real task

Xiaomi: MiMo-V2.5 leads 6 of 6 shared task categories by real classified traffic share; StepFun: Step 3.7 Flash leads 0. Not a benchmark score - this is what developers actually route to each model for, per OpenRouter's task classification.

TaskXiaomi: MiMo-V2.5StepFun: Step 3.7 Flash
Frontend & UI14.7%2.6%
DevOps & Config12.0%2.8%
File I/O10.7%2.9%
DevOps11.3%4.4%
SQL & Database8.3%2.6%
Shell Execution5.2%3.1%

Usage share over time

21.85%16.39%10.93%5.46%0.00%Share of usageJul 5Jul 22Aug 8
  • Xiaomi: MiMo-V2.5
  • StepFun: Step 3.7 Flash

Frequently asked questions

Xiaomi: MiMo-V2.5 vs StepFun: Step 3.7 Flash: which is better quality?

Xiaomi: MiMo-V2.5 scores higher on Artificial Analysis's Intelligence Index (38 vs 30.9).

Xiaomi: MiMo-V2.5 vs StepFun: Step 3.7 Flash: which is cheaper?

Xiaomi: MiMo-V2.5 is cheaper at $0.18/1M vs $0.44/1M.

Xiaomi: MiMo-V2.5 vs StepFun: Step 3.7 Flash: which is used more?

Xiaomi: MiMo-V2.5 has higher real OpenRouter usage share (rank #2 vs #11 of 291).

Xiaomi: MiMo-V2.5 vs StepFun: Step 3.7 Flash: which wins more real-world task categories?

Xiaomi: MiMo-V2.5 handles more traffic in 6 of 6 shared task categories where both models have classified OpenRouter usage.

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.