Skip to main content

Model comparison

Inkling vs Nemotron 3 Ultra

Data verified

Head-to-head evidence from 9 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Thinking Machines Lab
69/100
Margin
8.0pts
← winning
61/100
2 category wins2 category wins

Verified leaderboard positions: Inkling #17; Nemotron 3 Ultra #24

Evidence parity. Inkling and Nemotron 3 Ultra share 9 comparable benchmark results. 4 of 8 categories are comparable. 7 results are unique to Inkling; 31 to Nemotron 3 Ultra.

Updated July 15, 2026
Shared results
9
Inkling only
7
Nemotron 3 Ultra only
31
Comparable categories
4 / 8

Pick Inkling if you want the stronger benchmark profile. Nemotron 3 Ultra only becomes the better choice if knowledge is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 9 shared benchmark results across 4 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Inkling is clearly ahead on the provisional aggregate, 69 to 61. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Inkling's sharpest advantage is in agentic, where it averages 69.4 against 51.3. The single biggest benchmark swing on the page is BrowseComp, 77.1% to 44.4%. Nemotron 3 Ultra does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Inkling is also the more expensive model on tokens at $1.87 input / $4.68 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 is the reasoning model in the pair, while Inkling is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

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 Inkling and Nemotron 3 Ultra
CategoryInklingΔNemotron 3 Ultra
AgenticInkling69.4Margin 18.1Nemotron 3 Ultra51.3
CodingInkling68.6Margin 10.3Nemotron 3 Ultra58.3
KnowledgeInkling51.7Margin 2.5Nemotron 3 Ultra54.2
Inst. FollowingInkling79.8Margin 1.9Nemotron 3 Ultra81.7
ReasoningInklingNot measuredMarginNo overlapNemotron 3 Ultra61.9
MathInkling97.1MarginNo overlapNemotron 3 UltraNot measured
MultilingualInklingNot measuredMarginNo overlapNemotron 3 Ultra83.0
MultimodalInkling76.5MarginNo overlapNemotron 3 UltraNot measured

Decisive benchmark drivers

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

More
A · InklingB · Nemotron 3 Ultra
  1. BrowseComp

    Agentic
    Source ↗
    A 77.1%B 44.4%
    Winner: InklingΔ 32.7
    BrowseComp: Inkling scored 77.1%; Nemotron 3 Ultra scored 44.4%. Inkling wins this benchmark.
  2. HLE

    Knowledge
    Source ↗
    A 46%B 26.7%
    Winner: InklingΔ 19.3
    HLE: Inkling scored 46%; Nemotron 3 Ultra scored 26.7%. Inkling wins this benchmark.
  3. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 63.8%B 56.4%
    Winner: InklingΔ 7.4
    Terminal-Bench 2.0: Inkling scored 63.8%; Nemotron 3 Ultra scored 56.4%. Inkling wins this benchmark.
  4. SWE-bench Verified

    Coding
    Source ↗
    A 77.6%B 71.9%
    Winner: InklingΔ 5.7
    SWE-bench Verified: Inkling scored 77.6%; Nemotron 3 Ultra scored 71.9%. Inkling wins this benchmark.
  5. IFBench

    Inst. Following
    Source ↗
    A 79.8%B 81.7%
    Winner: Nemotron 3 UltraΔ 1.9
    IFBench: Inkling scored 79.8%; Nemotron 3 Ultra scored 81.7%. Nemotron 3 Ultra wins this benchmark.

Operational comparison

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

MetricInklingNemotron 3 UltraComparison
Input / output priceUSD per 1M tokensInkling$1.87 input / $4.68 outputNemotron 3 Ultra$0 input / $0 outputNemotron 3 Ultra has the lower combined listed price.
Generation speedtokens per secondInklingNot availableNemotron 3 UltraNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenInklingNot availableNemotron 3 UltraNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensInkling1MNemotron 3 Ultra1MListed context windows are equal.

Benchmark Deep Dive

AgenticInkling wins
BenchmarkInklingNemotron 3 UltraResult
Terminal-Bench 2.0Source 63.8%56.4%Inkling leads
BrowseCompSource 77.1%44.4%Inkling leads
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1258Not comparable
PinchBenchSource 90.0%Not comparable
τ³-bench resultsSource 70.9%Not comparable
GDPval-AASource 33.2%Not comparable
HLE w/ toolsSource 37.4%Not comparable
AA Agentic IndexSource 27.4%Not comparable
τ²-bench resultsSource 83.3%Not comparable
GDPval-AASource 1164Not comparable
AA BriefcaseSource 870Not comparable
AA EnterpriseOps-GymSource 28.9%Not comparable
AA Harvey LABSource 3.3%Not comparable
AA Tau3 BankingSource 13.8%Not comparable
CodingInkling wins
BenchmarkInklingNemotron 3 UltraResult
SWE-bench VerifiedSource 77.6%71.9%Inkling leads
SWE-bench ProSource 54.3%Not comparable
Terminal-Bench 2.0Source 63.8%56.4%Inkling leads
SWE MultilingualSource 67.7%Not comparable
LiveCodeBench v6Source 89.0%Not comparable
SciCodeSource 44.6%Not comparable
AA Coding IndexSource 49.3%Not comparable
Terminal-Bench HardSource 36.4%Not comparable
AA-SciCodeSource 39.9%Not comparable
Reasoning
BenchmarkInklingNemotron 3 UltraResult
AA-LCRSource 67.0%Not comparable
CritPtSource 3.1%Not comparable
LongBench v2Source 61.9%Not comparable
KnowledgeNemotron 3 Ultra wins
BenchmarkInklingNemotron 3 UltraResult
GPQASource 87.9%87%Inkling leads
GPQA-DSource 87.9%87.0%Inkling leads
HLESource 46%26.7%Inkling leads
HLE w/o toolsSource 30%26.7%Inkling leads
MMLU-ProSource 86.8%Not comparable
AA-Omniscience AccuracySource 21.6%Not comparable
Artificial Analysis Intelligence IndexSource 37.8%Not comparable
AA-GPQA DiamondSource 86.7%Not comparable
AA-HLESource 26.6%Not comparable
AA-Omniscience IndexSource -0.8%Not comparable
AA-Omniscience Hallucination RateSource 28.5%Not comparable
AA Openness IndexSource 83.3%Not comparable
Math
BenchmarkInklingNemotron 3 UltraResult
AIME26Source 97.1%Not comparable
Multilingual
BenchmarkInklingNemotron 3 UltraResult
MMLU-ProXSource 83%Not comparable
Multimodal
BenchmarkInklingNemotron 3 UltraResult
MMMU-ProSource 73.5%Not comparable
CharXivSource 82%Not comparable
CharXiv w/o toolsSource 78.1%Not comparable
Design Arena WebsiteSource 1132Not comparable
Inst. FollowingNemotron 3 Ultra wins
BenchmarkInklingNemotron 3 UltraResult
IFBenchSource 79.8%81.7%Nemotron 3 Ultra leads
AA-IFBenchSource 81.4%Not comparable
Frequently Asked Questions (5)

Which is better, Inkling or Nemotron 3 Ultra?

Inkling is ahead on BenchLM's provisional leaderboard, 69 to 61. The biggest single separator in this matchup is BrowseComp, where the scores are 77.1% and 44.4%.

Which is better for knowledge tasks, Inkling or Nemotron 3 Ultra?

Nemotron 3 Ultra has the edge for knowledge tasks in this comparison, averaging 54.2 versus 51.7. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, Inkling or Nemotron 3 Ultra?

Inkling has the edge for coding in this comparison, averaging 68.6 versus 58.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Inkling or Nemotron 3 Ultra?

Inkling has the edge for agentic tasks in this comparison, averaging 69.4 versus 51.3. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for instruction following, Inkling or Nemotron 3 Ultra?

Nemotron 3 Ultra has the edge for instruction following in this comparison, averaging 81.7 versus 79.8. Inside this category, IFBench is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 15, 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.