Stepfun · model passport

Step 3

step-3

Open weights
Apache 2.0 licence
Released 2026-10-09(first seen on LMArena)

Overall · LMArena: 1,349#202 of 396
Best percentile: 52.8Hard prompts
Cohort standing: 48.2median 60.7

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 23.5 percentile points between its best and worst axis — 52.8 pct on Hard prompts versus 29.3 pct on Vision Arena.

Hard prompts52.8 pct1,379Verify →
Coding52.4 pct1,409Verify →
Instruction following51.5 pct1,344Verify →
Overall49.2 pct1,349Verify →
Vision Arena29.3 pct1,145Verify →
WebDev ArenaNot benchmarked
Factuality ArenaNot benchmarked
Search ArenaNot benchmarked
Document ArenaNot benchmarked
Agent ArenaNot benchmarked
GPQA DiamondNot benchmarked
AIME (math)Not benchmarked
FrontierMathNot benchmarked
SimpleQA VerifiedNot benchmarked
ARC-AGI-2Not benchmarked
Humanity's Last ExamNot benchmarked
SimpleBenchNot benchmarked
LiveBenchNot benchmarked
BFCL v4 (function calling)Not benchmarked
SWE-bench Verified (live board)Not benchmarked
Terminal-Bench 4.0Not benchmarked
MMLU-Pro (Artificial Analysis)Not benchmarked
LiveCodeBench (Artificial Analysis)Not benchmarked
IFBench (Artificial Analysis)Not benchmarked
HHEM Hallucination (Vectara)Not benchmarked
SWE-bench VerifiedNot benchmarked
Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

step-3 stands at 48.2 (raw mean 47.1) — measured on 5 of 27 axes.
standingtemplateVerify →
step-3 stands at 48.2 versus a cohort median of 60.7 across 171 models released within 180 days — below the peer median.
cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →