Real data comparison
DeepSeek: DeepSeek V4 Flash 0423 vs StepFun: Step 3.7 Flash
On quality, DeepSeek: DeepSeek V4 Flash 0423 leads (51.8 vs 30.9). On price, DeepSeek: DeepSeek V4 Flash 0423 is cheaper ($0.11 vs $0.44 per 1M). In real production usage, DeepSeek: DeepSeek V4 Flash 0423 is used more (rank #1 vs #11 of 291). Across 6 real task categories where both models have classified traffic, DeepSeek: DeepSeek V4 Flash 0423 handles more of the traffic in 6 of them.
- DeepSeek: DeepSeek V4 Flash 0423
- StepFun: Step 3.7 Flash
Head-to-head by real task
DeepSeek: DeepSeek V4 Flash 0423 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.
| Task | DeepSeek: DeepSeek V4 Flash 0423 | StepFun: Step 3.7 Flash |
|---|---|---|
| DevOps & Config | 23.0% | 2.8% |
| DevOps | 23.0% | 4.4% |
| File I/O | 20.1% | 2.9% |
| SQL & Database | 19.8% | 2.6% |
| Frontend & UI | 17.2% | 2.6% |
| Shell Execution | 14.5% | 3.1% |
Usage share over time
- DeepSeek: DeepSeek V4 Flash 0423
- StepFun: Step 3.7 Flash
Frequently asked questions
DeepSeek: DeepSeek V4 Flash 0423 vs StepFun: Step 3.7 Flash: which is better quality?
DeepSeek: DeepSeek V4 Flash 0423 scores higher on Artificial Analysis's Intelligence Index (51.8 vs 30.9).
DeepSeek: DeepSeek V4 Flash 0423 vs StepFun: Step 3.7 Flash: which is cheaper?
DeepSeek: DeepSeek V4 Flash 0423 is cheaper at $0.11/1M vs $0.44/1M.
DeepSeek: DeepSeek V4 Flash 0423 vs StepFun: Step 3.7 Flash: which is used more?
DeepSeek: DeepSeek V4 Flash 0423 has higher real OpenRouter usage share (rank #1 vs #11 of 291).
DeepSeek: DeepSeek V4 Flash 0423 vs StepFun: Step 3.7 Flash: which wins more real-world task categories?
DeepSeek: DeepSeek V4 Flash 0423 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.
