Home/Models/Step 5 Preview
S

Step 5 Preview

Closed API StepFun 2026-09 1M context

LiveBench design 76.9 — a capable document generator among Chinese multimodal models

Intelligence v5
— v4.3.2 —
Leaderboard rank
—
Input / output
$0.50/$2.00
Blended 3:1
$0.88
Output speed
95 tok/s
Value
—
Capability profile Normalised to the field maximum
Specifications
Vendor
StepFun
Released
2026-09
Weights
Closed, API only
Context
1,000,000 tokens
Max output
Undisclosed
Parameters
Undisclosed
Input price
$0.50 / 1M
Output price
$2.00 / 1M
Cache hit
n/a
Output speed
95 tok/s
Intelligence
not indexed

Benchmark scores

How it is measured →

Bars are scaled to the field maximum for that benchmark.

BenchmarksScoreVs. best in fieldGap
AA Intelligence Index v5——not indexed
AA Intelligence Index v4.3.2——not indexed
GPQA Diamond——not indexed
Terminal-Bench 4.0——not indexed
LiveBench Design Document generation (DOCX/PPT/PDF) 76.988% −10.0 pts
Vals Index——not indexed

Assessment

StepFun's flagship. A LiveBench design score of 76.9 puts it just below Kimi K3's 77.2 and above GLM-5.3 Flash — the middle of the first tier.

At the same price

The four models closest on blended price, side by side.

Modelv5Blendedtok/sScore gap
GLM-5.3 Open weightsZ.ai 32.0 $1.00 77 —
MiMo-V2.6 Pro Open weightsXiaomi 30.0 $0.61 81 —
DeepSeek V4.1 Flash Open weightsDeepSeek 32.5 $0.53 148 —
MiniMax M3.1 FlashMiniMax 29.0 $0.26 118 —

Compare side by side

Line it up against other models on price, speed and every benchmark.

The comparison tool lines up to 4 models side by side with switchable normalisation — built for purchasing decisions.

Open the comparison tool → Back to leaderboard

Related benchmarks