Back

StepFun

Step 3.5 Flash 2603

ReasoningClosed weightsModels.dev
Intelligence
17.0
Rank 279 of 744 measured models
Output speed
142 t/s
Rank 102 of 403 measured models
Price/1M
$0.15
Rank 128 of 659 measured models
Context window
256K
Rank 518 of 1199 measured models

Step 3.5 Flash 2603 scores 17.0 on the Artificial Analysis Intelligence Index, ranking 279th of 744 measured models. The closest models on this index are Ling-2.6-1T (17.0), Doubao Seed Code (16.9), and GPT-5 mini (16.8). At $0.15 per million tokens (3:1 input/output blended price), it is cheaper than Ling-2.6-1T ($0.85) and GPT-5 mini ($0.688). With an output speed of 142 t/s, it is about as fast as GPT-5 mini (148 t/s).

Artificial Analysis Indices
Intelligence17.0
Rank 279 of 744 measured models
Standard Benchmarks
GPQA Diamond82.6%
Rank 180 of 619 measured models
HLE24.5%
Rank 189 of 664 measured models
IFBench66.5%
Rank 95 of 450 measured models
AA-LCR63.0%
Rank 272 of 575 measured models
TerminalBench Hard32.6%
Rank 100 of 432 measured models
τ²-Bench87.4%
Rank 82 of 440 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy