ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Dola Seed 2.1 TurbovsStep 3.7 Flash

Dola Seed 2.1 Turbo leads 1 of 1 shared benchmark. Both offer a 256K-token context window.

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

Shared benchmarks
1 – 0
Dola Seed 2.1 Turbo leads
Cheaper per token
list price, input + output
Larger context
Tie
both 256K tokens
Provider uptime (30d)
— · —
ByteDance Seed · StepFun
Dola Seed 2.1 Turbo
ByteDance Seed · released 2026-07-13
textvisionvideo
Context
256K
Max out
Input /1M
$0.5
Output /1M
$2.5
Cached /1M
$0.1
Scores
26 · 2 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

BenchmarkDola Seed 2.1 TurboStep 3.7 FlashΔEdge
Reported by both · 1
Terminal-Bench 2.167.6% 59.6% +8 ptDola Seed 2.1 Turbo
Only Dola Seed 2.1 Turbo reports · 25
Agent Startup Bench54% not reported
BabyVision62.9% not reported
BeyondAIME88% not reported
CharXiv-RQ82.5% not reported
CharXiv-RQ (with tools)83.6% not reported
ERQA71.3% not reported
KINA46.6% not reported
MathVision90.1% not reported
MathVision (with tools)92.7% not reported
Minerva Video Reasoning65.9% not reported
MMLongBench 128K76.9% not reported
MMMU-Pro80.1% not reported
MMMU-Pro (with tools)82.2% not reported
NL2Repo-Bench43.7% not reported
OVOBench79.2% not reported
SuperGPQA67.4% not reported
SWE-Atlas30.6% not reported
TOMATO56.8% not reported
VideoMME89% not reported
VideoSimpleQA71.4% not reported
Workspace Bench54.7% not reported
WorldVQA48.6% not reported
xDailyBench56.4% not reported
ZEROBench11% not reported
ZEROBench (with tools)20% not reported
Only Step 3.7 Flash reports · 18
SWE-bench Verifiednot reported76.5%
AIME 2026not reported95% matharena
AA-LCRnot reported63.9%
BrowseCompnot reported75.8%
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%
ResearchRubricsnot reported71.7%
SimpleVQA (with tools)not reported79.2%
SWE-bench Multilingualnot reported72.4%
SWE-bench Pronot reported56.3%
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 Dola Seed 2.1 Turbo 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

SpecDola Seed 2.1 TurboStep 3.7 FlashEdge
Context window256K tokens256K tokensTie
Max output
Input price / 1M$0.5
Output price / 1M$2.5
Cached input / 1M$0.1
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$3
Modalitiestext · vision · videotext · visionDola Seed 2.1 Turbo
Released2026-07-132026-05-29
Cited benchmark scores2619
Reliability

Provider status

All providers
More matchups

Dola Seed 2.1 Turbo vs …

More matchups

Step 3.7 Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Dola Seed 2.1 Turbo and Step 3.7 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.