Skip to main content
BenchLM
Advertise

Model comparison

Nemotron 3 Ultra vs Step 3.7 Flash

Data verified

Head-to-head evidence from 21 shared benchmark results across 6 categories. Overall scores shown here use BenchLM's provisional ranking lane.

63/100
Margin
5.0pts
← winning
58/100
1 category wins1 category wins

Verified leaderboard positions: Nemotron 3 Ultra #21; Step 3.7 Flash unranked

Evidence parity. Nemotron 3 Ultra and Step 3.7 Flash share 21 comparable benchmark results. 2 of 8 categories are comparable. 19 results are unique to Nemotron 3 Ultra; 9 to Step 3.7 Flash.

Updated July 14, 2026
Shared results
21
Nemotron 3 Ultra only
19
Step 3.7 Flash only
9
Comparable categories
2 / 8

Pick Nemotron 3 Ultra if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if agentic is the priority.

Confidence note. This is a partial-evidence comparison with 21 shared benchmark results across 6 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Nemotron 3 Ultra is clearly ahead on the provisional aggregate, 63 to 58. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Nemotron 3 Ultra's sharpest advantage is in coding, where it averages 75.5 against 56.3. The single biggest benchmark swing on the page is BrowseComp, 44.4% to 75.8%. Step 3.7 Flash does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

Step 3.7 Flash is also the more expensive model on tokens at $0.20 input / $1.15 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Nemotron 3 Ultra. That is roughly Infinityx on output cost alone. Nemotron 3 Ultra gives you the larger context window at 1M, compared with 256K for Step 3.7 Flash.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Nemotron 3 Ultra and Step 3.7 Flash
CategoryNemotron 3 UltraΔStep 3.7 Flash
CodingNemotron 3 Ultra75.5Margin← 19.2Step 3.7 Flash56.3
AgenticNemotron 3 Ultra51.3Margin→ 15.1Step 3.7 Flash66.4
ReasoningNemotron 3 Ultra61.9MarginNo overlapStep 3.7 FlashNot measured
KnowledgeNemotron 3 Ultra54.2MarginNo overlapStep 3.7 FlashNot measured
MultilingualNemotron 3 Ultra83.0MarginNo overlapStep 3.7 FlashNot measured
Inst. FollowingNemotron 3 Ultra81.7MarginNo overlapStep 3.7 FlashNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Nemotron 3 UltraB · Step 3.7 Flash

  1. BrowseComp

    Agentic
    Source ↗
    A 44.4%B 75.8%
    Winner: Step 3.7 FlashΔ 31.4
    BrowseComp: Nemotron 3 Ultra scored 44.4%; Step 3.7 Flash scored 75.8%. Step 3.7 Flash wins this benchmark.

  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 56.4%B 59.5%
    Winner: Step 3.7 FlashΔ 3.1
    Terminal-Bench 2.0: Nemotron 3 Ultra scored 56.4%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricNemotron 3 UltraStep 3.7 FlashComparison
Input / output priceUSD per 1M tokensNemotron 3 Ultra$0 input / $0 outputStep 3.7 Flash$0.2 input / $1.15 outputNemotron 3 Ultra has the lower combined listed price.
Generation speedtokens per secondNemotron 3 UltraNot availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenNemotron 3 UltraNot availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensNemotron 3 Ultra1MStep 3.7 Flash256KNemotron 3 Ultra lists the larger context window.

Benchmark Deep Dive

AgenticStep 3.7 Flash wins
BenchmarkNemotron 3 UltraStep 3.7 FlashResult
Terminal-Bench 2.0Source 56.4%59.5%Step 3.7 Flash leads
PinchBenchSource 90.0%—Not comparable
BrowseCompSource 44.4%75.8%Step 3.7 Flash leads
TAU3-BenchSource 70.9%—Not comparable
GDPval-AASource 33.2%25.9%Nemotron 3 Ultra leads
HLE w/ toolsSource 37.4%47.2%Step 3.7 Flash leads
AA Agentic IndexSource 27.4%21.5%Nemotron 3 Ultra leads
Tau2-TelecomSource 83.3%98.5%Step 3.7 Flash leads
GDPval-AASource 11641017Nemotron 3 Ultra leads
AA BriefcaseSource 870—Not comparable
AA EnterpriseOps-GymSource 28.9%—Not comparable
AA Harvey LABSource 3.3%—Not comparable
AA Tau3 BankingSource 13.8%—Not comparable
DeepSearchQASource —92.8%Not comparable
ToolathlonSource —49.5%Not comparable
Claw-EvalSource —67.1%Not comparable
Gert LabsSource —51.57%Not comparable
APEX-Agents-AASource —14.8%Not comparable
CodingNemotron 3 Ultra wins
BenchmarkNemotron 3 UltraStep 3.7 FlashResult
SWE-bench VerifiedSource 71.9%—Not comparable
SWE MultilingualSource 67.7%—Not comparable
LiveCodeBenchSource 89%—Not comparable
SciCodeSource 44.6%—Not comparable
Terminal-Bench 2.0Source 56.4%59.5%Step 3.7 Flash leads
AA Coding IndexSource 49.3%39.6%Nemotron 3 Ultra leads
Terminal-Bench HardSource 36.4%35.6%Nemotron 3 Ultra leads
AA-SciCodeSource 39.9%40.0%Step 3.7 Flash leads
SWE-bench ProSource —56.3%Not comparable
Reasoning
BenchmarkNemotron 3 UltraStep 3.7 FlashResult
AA-LCRSource 67.0%63.7%Nemotron 3 Ultra leads
CritPtSource 3.1%2.3%Nemotron 3 Ultra leads
LongBench v2Source 61.9%—Not comparable
Knowledge
BenchmarkNemotron 3 UltraStep 3.7 FlashResult
GPQASource 87%—Not comparable
GPQA-DSource 87.0%—Not comparable
HLESource 26.7%—Not comparable
HLE w/o toolsSource 26.7%—Not comparable
MMLU-ProSource 86.8%—Not comparable
AA-Omniscience AccuracySource 21.6%25.4%Step 3.7 Flash leads
Artificial Analysis Intelligence IndexSource 37.8%30.3%Nemotron 3 Ultra leads
AA-GPQA DiamondSource 86.7%80.9%Nemotron 3 Ultra leads
AA-HLESource 26.6%19.9%Nemotron 3 Ultra leads
AA-Omniscience IndexSource -0.8%-37.5%Nemotron 3 Ultra leads
AA-Omniscience Hallucination RateSource 28.5%84.4%Nemotron 3 Ultra leads
AA Openness IndexSource 83.3%—Not comparable
Multilingual
BenchmarkNemotron 3 UltraStep 3.7 FlashResult
MMLU-ProXSource 83%—Not comparable
Multimodal
BenchmarkNemotron 3 UltraStep 3.7 FlashResult
Design Arena WebsiteSource 11321218Step 3.7 Flash leads
SimpleVQASource —79.2%Not comparable
V*Source —95.3%Not comparable
AA-MMMU-ProSource —75.3%Not comparable
Inst. Following
BenchmarkNemotron 3 UltraStep 3.7 FlashResult
IFBenchSource 81.7%—Not comparable
AA-IFBenchSource 81.4%67.3%Nemotron 3 Ultra leads
Frequently Asked Questions (3)

Which is better, Nemotron 3 Ultra or Step 3.7 Flash?

Nemotron 3 Ultra is ahead on BenchLM's provisional leaderboard, 63 to 58. The biggest single separator in this matchup is BrowseComp, where the scores are 44.4% and 75.8%.

Which is better for coding, Nemotron 3 Ultra or Step 3.7 Flash?

Nemotron 3 Ultra has the edge for coding in this comparison, averaging 75.5 versus 56.3. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Nemotron 3 Ultra or Step 3.7 Flash?

Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 51.3. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

NVIDIA Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 14, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.