Model result, rank 23 of 27

Step 3.7 Flash

OpenRouter · stepfun/step-3.7-flash · extra-high reasoning · Full + SWE + Hard measured. Public result card with the model’s overall score, lane measurements, runtime and cost telemetry, and the ranking formula.

Compare all models Download public JSON

Figure 1 Lane profile against the cohort Each bar is one measured lane on the shared 0 to 100 scale. The thin mark is the cohort median; the bright mark is the best score any ranked model reached on that lane.

Full / Agenticlane rank #3 of 27

87.09

SWE MVPlane rank #10 of 27

80.39

Hard Intelligencelane rank #27 of 27

33.99

Step 3.7 Flash
Cohort median
Cohort best

Overall score67.16

Rank #23

Full / Agentic87.09

Full rank #3

SWE MVP80.39

SWE rank #10

Hard Intelligence33.99

Hard rank #27

Measured cost$0.494

100.0% reliability

Overall

All-around publication view

Score67.16

Formulamean(Full, SWE, Hard Intelligence)

BasisOpenRouter · stepfun/step-3.7-flash · extra-high reasoning · Full + SWE + Hard measured

The overall score averages the measured major lanes while keeping each source measurement visible.

Lane 01

Full / Agentic benchmark

Final87.09

Capability92.11

Agentic86.92

Pass rate88.6%

Prompts43

This lane captures instruction following, structured behavior, tool discipline, and general agentic reliability.

Lane 02

Software engineering MVP

SWE score80.39

Focused final70.04

Capability80.39

Daily driver67.40

Prompts24

This lane is closer to implementation usefulness: source handling, architecture cleanliness, and deliverable quality.

Lane 03

Hard Intelligence diagnostic

Hard score33.99

Active inquiry17.50

Online adaptation80.00

Self-repair29.46

Authority integrity9.00

Hard Intelligence measures active inquiry, online adaptation, evidence-driven self-repair, and authority/salience integrity.

Telemetry

Runtime economics

Total cost$0.494

Cost / scored item$0.0066

Seconds / timed item27.77s

Runtime coverage100.0%

Recorded tokens / item11.5k

Token coverage100.0%

Cost, time, and token basis are normalized telemetry. They explain tradeoffs; they do not overwrite the capability score yet.

Interpretation

Why the result lands here.

The result is best read as a balanced benchmark entry: one overall score plus the lane measurements that produced it. Hard Intelligence score is 33.99 and contributes to the overall score alongside Full/Agentic and SWE. Hard Intelligence is published alongside Full/Agentic and SWE for the current ranking.