StepFun · apache_2_0

Step-3.5-Flash

Step-3.5-Flash by StepFun appears in 1 source with Reasoning at 49.2. Best read for Code quality, Low cost, Open weights.

CreatorStepFun

Release date2026-02-02

Knowledge cutoffNot published

Context66K tokens

Input price$0.1/M tokens

Output price$0.4/M tokens

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank76ranking · source_rank

Reasoning49.2reasoning · index_reasoning

Math46.64math · index_math

Coding27.91coding · index_code

Research22.35research · index_search

Tool calling18.3tool_calling · index_tool_calling

AIME 202597.3 %math · aime_2025_score

SWE-bench Verified74.4 %coding · swe_bench_verified_score

Code Arena723.26 %coding · coding_arena_score

BrowseComp69 %research · browsecomp_score

Context65,536 tokenscontext · context

Speed264.75 c/sperformance · throughput

Latency15,415.15 msperformance · latency

Input price0.1 $/Mpricing · input_price

Output price0.4 $/Mpricing · output_price

Parameters196,000,000,000 paramsmodel · params

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Step-3.5-Flash verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.