readable AI benchmarks (simplified)

readable AI benchmarks

StepFun

Step 5 Preview

reasoning · closed weights · release date not listed

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