SI Index Data as of Oct 9, 2026

Nemotron 3 Ultra 550B A55B: Price, Context, Benchmarks, and Release Details

nvidia provisional listing open weights · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:09 UTC
61.2
SI Score (method si-v3-retained-evidence-2)
#59 of 140 ranked
100% confidence 100 percent, Full confidence — 3 of 3 expected sources in
Coverage 100% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 53.0
Math (weight 15 percent) 85.5
Preference (weight 15 percent) —
Reasoning (weight 30 percent) 65.7

Pillar weights: reasoning 30% · math 15% · coding 40% · preference 15%. Benchmark results use fixed 0–100 scales before averaging; incomplete evidence is shrunk toward 50.

Facts

Input price / 1M
not yet reported
Output price / 1M
not yet reported
Context window
1Mmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
128Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Jun 4, 2026models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Open weights
Yesmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
textmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Popularity rank
#7 by usageOpenRouter rankingsPublished source fact; tokens processed; page default period; excludes catalog and endpoint statistics Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗

Benchmark results

24 results
Benchmark Raw result Normalized (0–100) Pillar
gpqa diamond 85.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		85.4 reasoning
gpqa diamond 87%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] no toolsPublished Jun 4, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		87.0 reasoning
hle 26.7%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] no toolsPublished Jun 4, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		26.7 reasoning
hle tools 37.4%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] with toolsPublished Jun 4, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		37.4 reasoning
livebench coding code completion 2026_06_25 69.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		69.6 coding
livebench coding code generation 2026_06_25 71.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		71.8 coding
livebench coding javascript 2026_06_25 54.5%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		54.5 coding
livebench coding python 2026_06_25 45%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		45.0 coding
livebench coding typescript 2026_06_25 16.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		16.7 coding
livebench math amps hard 2026_06_25 96%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		96.0 math
livebench math integrals with game 2026_06_25 80%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		80.0 math
livebench math math comp 2026_06_25 96.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		96.1 math
livebench math olympiad 2026_06_25 82.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		82.6 math
livebench math simplify 2026_06_25 72.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		72.3 math
livebench reasoning connections 2026_06_25 86.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		86.7 reasoning
livebench reasoning consecutive events 2026_06_25 18.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		18.8 reasoning
livebench reasoning logic with navigation 2026_06_25 68%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		68.0 reasoning
livebench reasoning spatial 2026_06_25 98%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		98.0 reasoning
livebench reasoning theory of mind 2026_06_25 61.5%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		61.5 reasoning
livebench reasoning zebra puzzle 2026_06_25 71.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		71.3 reasoning
mmlu pro 86.8%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Jun 4, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		86.8 reasoning
otis mock aime 2024 2025 86.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.7 math
swe bench verified 70.7%Official model cards via models.devLab-reported; metric resolved; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Jun 4, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		70.7 coding
terminal bench v2 1 56.4%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] 2.1Published Jun 4, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		56.4 coding

Normalization uses fixed absolute 0–100 scales for each unit, independently of other models that have a result on each benchmark. Coverage and evidence breadth still affect the composite; compare the evaluation conditions before reading a small score gap as decisive. “lab-reported” marks the provider's own published figure.

Sources: in and pending

in Reported (3)

  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • Official model cards via models.dev · arrived Oct 8, 2026
  • LiveBench · arrived Oct 8, 2026

pending Awaiting (0)

Every expected source has reported for this model.

The confidence % rises as pending sources publish. Some sources never cover some models — that is why 100% confidence arrives at 80% of expected weight, not at full coverage.