Quality
#62/670
Overall quality score
🇨🇳StepFunOpen sourceStepFun: Step 3.5 Flash.
See how StepFun: Step 3.5 Flash compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.
Speed
#41/6756 t/s
Output tokens per second
Input price
#18/67$0.10/1M
Per 1M tokens
Output price
#16/67$0.30/1M
Per 1M tokens
Context
#44/67262.1K
Content read at once
Comparison summary
StepFun: Step 3.5 Flash ranks #62 of 67 for overall quality and #41 for response speed in the current catalogue.
Its listed input price is $0.10/1M, output price is $0.30/1M, and it can work with up to 262.1K of context at once.
Its strongest areas in the current data are everyday help, coding, complex tasks.
Practical specifications
- Company
- StepFun
- Reasoning
- Yes
- Open weights
- Yes
- Input
- Text
- Output
- Text
- Context window
- 262.1K
StepFun: Step 3.5 Flash technical benchmarks.
Named evaluation records for technical comparison. Results retain their original benchmark names and sources.
| Benchmark | Area | Step 3.5 Flash | Source |
|---|---|---|---|
| GPQA | GPQA Diamond | 83.1 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 19.1 | OpenRouter model benchmarks |
| IFBench | IFBench | 64.6 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 94.4 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 43 | OpenRouter model benchmarks |
| CritPt | CritPt | 2.5 | OpenRouter model benchmarks |
| SciCode | SciCode | 40.4 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 27.3 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 23.9 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 14.8 | OpenRouter model benchmarks |
| MMLU-Pro | Knowledge and reasoning | 84.4 | OpenEvals/leaderboard-data |
| SWE-bench Verified | Coding | 74.4 | OpenEvals/leaderboard-data |
| Terminal-Bench | Agentic coding | 51 | OpenEvals/leaderboard-data |
| AIME 2026 | Math | 96.67 | OpenEvals/leaderboard-data |
Quality benchmarks
See where StepFun: Step 3.5 Flash stands.
The darker bar marks StepFun: Step 3.5 Flash; the lighter bars provide context from other leading models.
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better