Agentic
Like-for-like- Inkling-Small
- 36.9
- Supported · #128/152
- Nemotron 3 Ultra
- 27.0
- Supported · #143/152
- Basis
- BenchAlign lane · 5 vs 6 public rows
- Reading
- Inkling-Small leads · intervals overlap
Inkling-Small vs Nemotron 3 Ultra
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Inkling-Small has the higher public score, 59.25 versus 40.51, and the 90% score intervals do not overlap.
16 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Coding work
Code generation, repair, and software-engineering tasks
Inkling-Small
Inkling-Small leads on the public coding lane, 43.8 to 26.6, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Inkling-Small
Inkling-Small leads on the public agentic lane, 36.9 to 27, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Show secondary and unsupported calls
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
9 Inkling-Small only
16 Shared
8 Nemotron 3 Ultra only
- Shared results
- 16
- Inkling-Small only
- 9
- Nemotron 3 Ultra only
- 8
- Like-for-like categories
- 3 / 8
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Coding
Like-for-like- Inkling-Small
- 43.8
- Supported · #97/151
- Nemotron 3 Ultra
- 26.6
- Supported · #145/151
- Basis
- BenchAlign lane · 6 vs 7 public rows
- Reading
- Inkling-Small leads · intervals overlap
Instruction following
Like-for-like- Inkling-Small
- 89.6
- #25/123
- Nemotron 3 Ultra
- 88.8
- #28/123
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Inkling-Small leads
Knowledge
Directional only- Inkling-Small
- 56.5
- Supported · #46/183
- Nemotron 3 Ultra
- 44.7
- Estimated · #111/183
- Basis
- BenchAlign lane · 6 vs 7 public rows
- Reading
- Directional only
Reasoning
Not comparable- Inkling-Small
- 42.7
- Unranked · 3 rankable rows
- Nemotron 3 Ultra
- 48.7
- Unranked · 1 rankable row
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- Inkling-Small
- 76.9
- Unranked · 2 rankable rows
- Nemotron 3 Ultra
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Inkling-Small
- Not ranked
- Nemotron 3 Ultra
- 47.4
- #7/12
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Inkling-Small
- 48.8
- #39/48
- Nemotron 3 Ultra
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
| Category | Inkling-Small | Nemotron 3 Ultra | Basis | Reading |
|---|---|---|---|---|
| Agentic | 36.9Supported · #128/152 | 27.0Supported · #143/152 | Like-for-likeBenchAlign lane · 5 vs 6 public rows | Inkling-Small leads · intervals overlap |
| Coding | 43.8Supported · #97/151 | 26.6Supported · #145/151 | Like-for-likeBenchAlign lane · 6 vs 7 public rows | Inkling-Small leads · intervals overlap |
| Instruction following | 89.6#25/123 | 88.8#28/123 | Like-for-likeProvisional lane · 1 vs 1 weighted rows | Inkling-Small leads |
| Knowledge | 56.5Supported · #46/183 | 44.7Estimated · #111/183 | Directional onlyBenchAlign lane · 6 vs 7 public rows | Directional only |
| Reasoning | 42.7Unranked · 3 rankable rows | 48.7Unranked · 1 rankable row | Not comparableProvisional lane · 1 vs 1 weighted rows | Not comparable |
| Math | 76.9Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | 47.4#7/12 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multimodal | 48.8#39/48 | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
BrowseComp
Agentic
Inkling-Small: 77.4%Nemotron 3 Ultra: 44.4%Normalized gap 33.0Inkling-Small source Nemotron 3 Ultra sourceHLE
Knowledge
Inkling-Small: 47.8%Nemotron 3 Ultra: 26.7%Normalized gap 21.1Inkling-Small source Nemotron 3 Ultra sourceTerminal-Bench 2.0
Agentic
Inkling-Small: 64.7%Nemotron 3 Ultra: 56.4%Normalized gap 8.3Inkling-Small source Nemotron 3 Ultra sourceSWE-bench Verified
Coding
Inkling-Small: 80.2%Nemotron 3 Ultra: 71.9%Normalized gap 8.3Inkling-Small source Nemotron 3 Ultra sourceHLE w/o tools
Knowledge
Inkling-Small: 31.6%Nemotron 3 Ultra: 26.7%Normalized gap 4.9Inkling-Small source Nemotron 3 Ultra source
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Inkling-Small
- $0.0013
- Fits in one request
- Nemotron 3 Ultra
- Self-hosted; infrastructure cost varies
- Fits in one request
Nemotron 3 Ultra has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Inkling-Small
- $0.03332
- Fits in one request
- Nemotron 3 Ultra
- Self-hosted; infrastructure cost varies
- Fits in one request
Nemotron 3 Ultra has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Inkling-Small
- $0.0492
- Fits in one request
- Nemotron 3 Ultra
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Nemotron 3 Ultra has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationInkling-SmallNemotron 3 Ultra
Context window
Maximum documented context; output-token limits may be lower.
Inkling-Small
1M
Nemotron 3 Ultra
1M
API model ID
Inkling-Small
Not sourced
Nemotron 3 Ultra
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Inkling-Small
$0.116 per 1M cached input tokens
Nemotron 3 Ultra
No comparable hosted API rate
Documented inputs
Inkling-Small
Not sourced
Nemotron 3 Ultra
Not sourced
Documented outputs
Inkling-Small
Not sourced
Nemotron 3 Ultra
Not sourced
Provider availability
Inkling-Small
Not sourced
Nemotron 3 Ultra
Not sourced
Reasoning profile
Inkling-Small
Hybrid
Nemotron 3 Ultra
Reasoning
Weight access
Inkling-Small
Open Weight
Nemotron 3 Ultra
Open Weight
License
Inkling-Small
Open Weight
Nemotron 3 Ultra
Open Weight
Release date
Inkling-Small
2026-07-30
Nemotron 3 Ultra
2026-06-04
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Inkling-Small has the higher public score, 59.25 versus 40.51, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence33 rows
Agentic
Terminal-Bench 2.0
Inkling-Small64.7%SourceNemotron 3 Ultra56.4%SourceInkling-Small leads this result
BrowseComp
Inkling-Small77.4%SourceNemotron 3 Ultra44.4%SourceInkling-Small leads this result
MCP Atlas
Inkling-Small79.6%SourceNemotron 3 Ultra—Not directly comparable
Toolathlon-Verified
Inkling-Small54.4%SourceNemotron 3 Ultra—Not directly comparable
Terminal-Bench 2.1 (Vals)
Inkling-Small55.1%SourceNemotron 3 Ultra50.9%SourceInkling-Small leads this result
PinchBench
Inkling-Small—Nemotron 3 Ultra90.0%SourceNot directly comparable
τ³-bench results
Inkling-Small—Nemotron 3 Ultra70.9%SourceNot directly comparable
HLE w/ tools
Inkling-Small—Nemotron 3 Ultra37.4%SourceNot directly comparable
Coding
SWE-bench Verified
Inkling-Small80.2%SourceNemotron 3 Ultra71.9%SourceInkling-Small leads this result
SWE-bench Pro
Inkling-Small55.9%SourceNemotron 3 Ultra—Not directly comparable
Terminal-Bench 2.0
Inkling-Small64.7%SourceNemotron 3 Ultra56.4%SourceInkling-Small leads this result
SciCode
Inkling-Small48.7%SourceNemotron 3 Ultra44.6%SourceInkling-Small leads this result
LiveCodeBench (Vals)
Inkling-Small85.9%SourceNemotron 3 Ultra86.0%SourceNemotron 3 Ultra leads this result
SWE-bench (Vals)
Inkling-Small82.2%SourceNemotron 3 Ultra69.0%SourceInkling-Small leads this result
SWE Multilingual
Inkling-Small—Nemotron 3 Ultra67.7%SourceNot directly comparable
LiveCodeBench v6
Inkling-Small—Nemotron 3 Ultra89.0%SourceNot directly comparable
Reasoning
Knowledge
GPQA
Inkling-Small89.5%SourceNemotron 3 Ultra87%SourceInkling-Small leads this result
GPQA-D
Inkling-Small89.5%SourceNemotron 3 Ultra87.0%SourceInkling-Small leads this result
HLE
Inkling-Small47.8%SourceNemotron 3 Ultra26.7%SourceInkling-Small leads this result
HLE w/o tools
Inkling-Small31.6%SourceNemotron 3 Ultra26.7%SourceInkling-Small leads this result
GPQA Diamond (Vals)
Inkling-Small83.6%SourceNemotron 3 Ultra86.1%SourceNemotron 3 Ultra leads this result
MMLU-Pro (Vals)
Inkling-Small85.6%SourceNemotron 3 Ultra85.8%SourceNemotron 3 Ultra leads this result
MMLU-Pro
Inkling-Small—Nemotron 3 Ultra86.8%SourceNot directly comparable
Math
Multilingual
MMLU-ProX
Inkling-Small—Nemotron 3 Ultra83%SourceNot directly comparable
Multimodal
Instruction following
Frequently asked questions
Which is better, Inkling-Small or Nemotron 3 Ultra?
Inkling-Small has the higher public score, 59.25 versus 40.51, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Inkling-Small or Nemotron 3 Ultra?
Inkling-Small leads the public coding lane, 43.8 to 26.6, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Inkling-Small or Nemotron 3 Ultra?
Inkling-Small leads the public agentic tasks lane, 36.9 to 27, with Supported evidence for both models, although the 90% intervals overlap.
Which costs less, Inkling-Small or Nemotron 3 Ultra?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Inkling-Small or Nemotron 3 Ultra?
Both models list the same context window, 1M.
Related comparisons
Last updated September 10, 2026
Watch Inkling-Small vs Nemotron 3 Ultra
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.