BenchLeader

Step 3.5 Flash

Step 3.5 Flash is a StepFun open-weights reasoning model, released 2 Apr 2026. Its best configuration ranks #269 of 775 on the BenchLeader Index at 53.8 ±3.8, in the upper half. The ± is the point: 279 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (66) and lowest in knowledge (42). At $0.150 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 145 tokens per second puts it in the fastest quarter, with a first answer in 18.8 s. Last measured 15 Oct 2026.

Blended price
$0.150/M
$0.100 in · $0.300 out
Output speed
145 tok/s
measured by Artificial Analysis
First answer
19 s
first token 1.18 s
Context
256k
Full answer
23 s
median, reasoning included
Cost per run
–
Released
2 Apr 2026
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index54
  2. Reasoning49
  3. Coding58
  4. Agents & tools62
  5. Maths54
  6. Knowledge42
  7. Instruction following66
  8. Human preference57
  9. Long context56
  10. Composite49

Versions

StepFun has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Step 3.7 Flash29 May 202651.5#341
Step 3.5 Flashthis page2 Apr 202653.8#269

How its index has moved

9 Sept 2026 to 19 Oct 2026
505559

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Coding

Benchmarknot statedSourceTrend
Arena Coding1449#147Arena (LMArena)

Agents & tools

Benchmarknot statedSourceTrend
Terminal-Bench Hard32.6%#97Artificial Analysis
τ²-Bench Telecom (AA)not in index87.4%#77Artificial Analysis

Maths

Benchmarknot statedSourceTrend
AIME 202696.7%#6MathArena
HMMT February 202686.4%#20MathArena
USAMO 2026not in index44.6%#7MathArena
MathArena Apexpossible contamination13.5%#18MathArena
Arena Maths1407#139Arena (LMArena)

Knowledge

Instruction following

Benchmarknot statedSourceTrend
IFBench66.5%#94Artificial Analysis
Arena Instruction Followingnot in index1384#158Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1393#159Arena (LMArena)
Arena Creative Writingnot in index1345#172Arena (LMArena)
Arena Multi-turnnot in index1396#158Arena (LMArena)
Arena Longer Queriesnot in index1403#158Arena (LMArena)

Long context

Benchmarknot statedSourceTrend
AA-LCR63.0%#265Artificial Analysis

Composite

Benchmarknot statedSourceTrend
AA Intelligence Index v4.3.217.0#261Artificial Analysis

Where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
SiliconFlow72 tok/s1.18 s$0.100$0.300262kfp8

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.020 per 1M. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0001$0.000120.9 s
Summarize a 30-page report12,000 / 600$0.0014$0.000723.0 s
Code edit6,000 / 1,500$0.0011$0.000729.2 s
Agentic coding session60,000 / 4,000$0.0072$0.003646.4 s
Structured extraction2,000 / 200$0.0003$0.000120.2 s

More from StepFun

New this month

See also

Data as of 21 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Step 3.5 Flash: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/step-3-5-flash, data as of 21 Oct 2026.