readable AI benchmarks (simplified)
StepFun
Step 5 Preview
Step 5 Preview has a Quality Score of 54.8, ranking 31st among 262 scored models. Per 1M tokens, pricing is $1.00 input, $2.70 output, and $0.050 cached input. It has a 1M token context window. Its Reliability Score is 58.2, ranking 33rd among 262 scored models, above average (total average: 35.2). Its Value Score is 42.1, high compared with the total Value average of 28.9.
Quality Score54.8coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score42.1
Reliability58.2
Cache Discount95%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $1.00
- Output
- $2.70
- Cached Input
- $0.050
- Cache write
- not available
- Cost per task
- $0.713
Capability
- Intelligence
- 43.6
- Coding
- not available
- Agentic
- not available
- Omniscience
- 16.4
- Correct
- 41.5%
- Blended price
- $0.505
Answer outcomes
Attempt rate: 66.7%
Correct 41.5%Incorrect 25.2%Abstained 33.3%
Artificial Analysis benchmarks
- GDPval-AA v2
- 54%
- SciCode
- 59%
- Humanity’s Last Exam
- 46%
- CritPt
- 21%
- AA-Omniscience
- 58%
- AA-LCR
- 88%
Similar models
- Step 3.7 FlashStepFunQuality Score 22.5Value Score 22.1
- Step3 VL 10BStepFunQuality Score 9.0Value Score not available
- GPT-5.6 Terra (max)OpenAIQuality Score 52.9Value Score 35.8
- Kimi K3 (max)KimiQuality Score 57.7Value Score 36.4
- GLM-5.3 (max)Z AIQuality Score 52.3Value Score 38.3
- Muse Spark 1.3 (xhigh)MetaQuality Score 57.4Value Score 41.3