ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Step 3.5 FlashvsStep 3.7 Flash

Step 3.7 Flash leads 3 of 4 shared benchmarks. Both offer a 256K-token context window.

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
1 – 3
Step 3.7 Flash leads
Cheaper per token
list price, input + output
Larger context
Tie
both 256K tokens
Provider uptime (30d)
StepFun
Step 3.5 Flash
StepFun · released 2026-02-12
text
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
18 · 5 core
Step 3.7 Flash
StepFun · released 2026-05-29
textvision
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
19 · 6 core
Quality

Benchmark matrix

BenchmarkStep 3.5 FlashStep 3.7 FlashΔEdge
Reported by both · 4
SWE-bench Verified74.4% 76.5% -2.1 ptStep 3.7 Flash
AIME 202696.7% matharena95% matharena+1.7 ptStep 3.5 Flash
BrowseComp51.6% 75.8% -24.2 ptStep 3.7 Flash
ResearchRubrics65.3% 71.7% -6.4 ptStep 3.7 Flash
Only Step 3.5 Flash reports · 13
AIME 202597.3% not reported
LMArena Elo1403.7 not reported
BrowseComp (with context manager)69% not reported
BrowseComp-ZH66.9% not reported
BrowseComp-ZH (with context manager)73.7% not reported
GAIA (no file)84.5% not reported
HMMT 2025 (Feb/Nov average)96.2% not reported
IMOAnswerBench85.4% not reported
LiveCodeBench v686.4% not reported
Tau2-Bench88.2% not reported
Terminal-Bench 2.051% not reported
xbench-DeepSearch 2025.0583.7% not reported
xbench-DeepSearch 2025.1056.3% not reported
Only Step 3.7 Flash reports · 15
AA-LCRnot reported63.9%
ClawEval v1.1not reported67.1%
DeepSearchQA Accuracynot reported81.7%
DeepSearchQA F1not reported92.8%
GDPval-Stirrupnot reported1415.8
GDPval-Stirrup Intelligence Indexnot reported45.8
HLE (with tools, text-only)not reported49.7%
HLE (with tools)not reported47.2%
SimpleVQA (with tools)not reported79.2%
SWE-bench Multilingualnot reported72.4%
SWE-bench Pronot reported56.3%
Terminal-Bench 2.1not reported59.6%
Toolathlonnot reported49.5%
V* (with Python)not reported95.3%
WorldVQA (with visual search)not reported58.1%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Step 3.5 Flash minus Step 3.7 Flash in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecStep 3.5 FlashStep 3.7 FlashEdge
Context window256K tokens256K tokensTie
Max output
Input price / 1M
Output price / 1M
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
Modalitiestexttext · visionStep 3.7 Flash
Released2026-02-122026-05-29
Cited benchmark scores1819
Reliability

StepFun status

All providers
More matchups

Step 3.5 Flash vs …

More matchups

Step 3.7 Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Step 3.5 Flash and Step 3.7 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.