StepFun
Step 3.7 Flash
Quality Score30.2
Value Score31.1
Reliability31.4
Cache Discount80%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 262,144 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.200
- Output
- $1.15
- Cached Input
- $0.040
- Cached Output
- not available
- Cost per task
- $0.091
Capability
- Intelligence
- 30.9
- Coding
- 39.6
- Agentic
- 21.7
- Omniscience
- -37.3
- Correct
- 25.8%
- Blended price
- $0.183
Answer outcomes
Correct 25.8%Incorrect 63.1%Abstained 11.2%
Artificial Analysis benchmarks
- GDPval-AA v2
- 26%
- τ³-Banking
- 12%
- Terminal-Bench v2.1
- 39%
- SciCode
- 40%
- Humanity’s Last Exam
- 21%
- GPQA Diamond
- 81%
- CritPt
- 2%
- AA-Omniscience
- 31%
- AA-LCR
- 70%
Similar models
- Step3 VL 10BStepFunQuality Score 9.7Value Score not available
- Mistral Medium 3.5MistralQuality Score 30.2Value Score 24.6
- Ring-2.6-1TInclusionAIQuality Score 30.5Value Score 28.2
- Qwen3.5 122B A10B (Reasoning)AlibabaQuality Score 30.4Value Score 27.7
- Qwen3.6 35B A3B (Reasoning)AlibabaQuality Score 31.1Value Score 27.1
- K-EXAONE 2.0 0803LG AI ResearchQuality Score 31.9Value Score not available