Vision-language

Step-1V

By StepFun, in the Step Vision family.

Released
—
Status
Retired
Retired
8 Jul 2026
Context
32.8K
Max output
—
Input per 1M tokens
—
Output per 1M tokens
—
Open weights
No
License
proprietary
Parameters
—
Knowledge cutoff
—
Reasoning
No
Modalities
text, image → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Human preference12.6Not ranked1 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Vision Arena (arena.ai)Arena score (Elo scale)1064Independent—28 Sep 2026Arena
Vision Arena (arena.ai)Votes1534Independent—28 Sep 2026Arena

Other Step Vision versions

Sources