ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4vsStep 3.7 Flash

Step 3.7 Flash leads 3 of 3 shared benchmarks. NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 has the larger context window (1M tokens).

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

Shared benchmarks
0 – 3
Step 3.7 Flash leads
Cheaper per token
list price, input + output
Larger context
NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
1M tokens
Provider uptime (30d)
100% · —
NVIDIA · StepFun
NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
NVIDIA · released 2026-06-04
text
Context
1M
Max out
Input /1M
Output /1M
Cached /1M
Scores
6 · 4 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

BenchmarkNVIDIA Nemotron 3 Ultra 550B-A55B NVFP4Step 3.7 FlashΔEdge
Reported by both · 3
SWE-bench Verified69.7% 76.5% -6.8 ptStep 3.7 Flash
BrowseComp41.4% 75.8% -34.4 ptStep 3.7 Flash
Terminal-Bench 2.153.9% 59.6% -5.7 ptStep 3.7 Flash
Only NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 reports · 3
GPQA Diamond87.9% not reported
Humanity's Last Exam (no tools)26.1% not reported
LMArena Elo1444.7 not reported
Only Step 3.7 Flash reports · 16
AIME 2026not reported95% matharena
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%
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 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 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

SpecNVIDIA Nemotron 3 Ultra 550B-A55B NVFP4Step 3.7 FlashEdge
Context window1M tokens256K tokensNVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
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
Released2026-06-042026-05-29
Cited benchmark scores619
Reliability

Provider status

All providers
More matchups

NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 vs …

More matchups

Step 3.7 Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 and Step 3.7 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.