Data as of October 16, 2026 · How the score is built
Nemotron 3.5 Bolt 74B-A9B BF16
Decision readingNemotron 3.5 Bolt 74B-A9B BF16 is tracked, but not publicly ranked yet. The profile exposes 8 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Oct 15, 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
Unranked
field median 49.6Not eligible for a public rank
Price
API rate not published
input median $0.75No comparable first-party hosted token rate
Speed
Not measured
field median 92 tok/sTime to first token not measured
Context
256Ktokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
8 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 8 displayable benchmark rows
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank Not rankedWeight 22%6 benchmarksVerified | 53.1 | 6 benchmarks | Verified | |||
| CodingWeight 20%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank Not rankedWeight 12%2 benchmarksVerified | 47.8 | 2 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
8 of 681 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic6/6 verified
- CodingNot measured
- ReasoningNot measured
- MultimodalNot measured
- Knowledge2/2 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- MathNot measured
Benchmark ledger
Agentic opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Agentic6 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Score53.9% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap38.9 behind | Weight8% ref. weight | Provider exact |
| BrowseComp | Score70% | Versus best verified row Best verified: Atria Dawn Preview · 92.5% | Gap22.5 behind | Weight8% ref. weight | Provider exact |
| MCP Atlas | Score55.6% | Versus best verified row Best verified: Muse Spark Open · 89.2% | Gap33.6 behind | Weight4% ref. weight | Provider exact |
| τ³-bench resultsτ³-Bench Tool-Agent-User Evaluation | Score17.0% | Versus best verified row Best verified: Mercury 2.5 · 96.0% | Gap79 behind | Weight2% ref. weight | Provider exact |
| PinchBench | Score90.3% | Versus best verified row Best verified: Pokee-Isaac 28B · 95.7% | Gap5.3 behind | WeightDisplay only | Provider exact |
| WebArenaWebArena Web Agent Benchmark | Score50.3% | Versus best verified row Best verified: Nemotron 3.5 Bolt 74B-A9B · 50.9% | Gap0.6 behind | WeightDisplay only | Provider exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLE w/o toolsHumanity's Last Exam without tools | Score28.7% | Versus best verified row Best verified: Claude Opus 5.5 · 64.4% | Gap35.7 behind | Weight7% ref. weight | Provider exact |
| GPQA-DGPQA Diamond | Score88.8% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap7.2 behind | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 8 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- Weights model ID
- nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16NVIDIA BF16 model card
- Context window
- 256KNVIDIA BF16 model card
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, image, videoNVIDIA BF16 model card
- Output modalities
- textNVIDIA BF16 model card
- Parameters
- Not sourced yet
- Availability
- Hugging Face · self-hosted inferenceNVIDIA BF16 model card
- Cloud regions
- Not tracked yet
- Lifecycle
- activeNVIDIA BF16 model card
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordNVIDIA Hugging Face model card
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Nemotron 3.5 Bolt 74B-A9B BF16, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Nemotron 3.5 Bolt 74B-A9B BF16 is a open weight model with a 256K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Open BF16 weights for self-hosted inference and customization; about 148 GB of weights before quantization. The 24GB checkpoint is the release NVIDIA documents for RTX Spark and DGX Spark.
NVIDIA released the unquantized BF16 checkpoint on October 15, 2026 under OpenMDW 1.1 alongside the 24GB release: the same 74B-total, 9B-active hybrid Mamba-2, attention and MoE network compressed from Nemotron 3.5 Super VL, published for further customization rather than for 24GB local inference. It takes text, image and video input and keeps a 256K-token context. Benchmark values are NVIDIA-reported runs of this BF16 checkpoint; the 24GB column stays on the released model's row. The GDPval v2 figure is reported as an index on a different scale from the stored rating lane, SciCode is subtask accuracy rather than main-problem resolve rate, the Omniscience non-hallucination rate is the complement of the stored hallucination-rate lane, and IFBench appears only in the technical report as the instruction-loose metric; those stay unmapped. This reference checkpoint is tracked beside the 24GB release and does not receive a second family rank.
Nemotron 3.5 Bolt 74B-A9B BF16 sits in the Nemotron 3.5 Bolt 74B-A9B family with Nemotron 3.5 Bolt 74B-A9B. 8 of 681 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 16, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Nemotron 3.5 Bolt 74B-A9B BF16 perform overall in AI benchmarks?
Nemotron 3.5 Bolt 74B-A9B BF16 has 8 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is Nemotron 3.5 Bolt 74B-A9B BF16 good for knowledge and understanding?
Nemotron 3.5 Bolt 74B-A9B BF16 has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Nemotron 3.5 Bolt 74B-A9B BF16 good for agentic tool use and computer tasks?
Nemotron 3.5 Bolt 74B-A9B BF16 has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Nemotron 3.5 Bolt 74B-A9B BF16 open source?
Nemotron 3.5 Bolt 74B-A9B BF16 is an open-weight model from NVIDIA. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to Nemotron 3.5 Bolt 74B-A9B BF16?
Nemotron 3.5 Bolt 74B-A9B BF16 belongs to the Nemotron 3.5 Bolt 74B-A9B family. Related tracked variants include Nemotron 3.5 Bolt 74B-A9B. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Nemotron 3.5 Bolt 74B-A9B BF16 have full benchmark coverage on BenchLM?
No. Nemotron 3.5 Bolt 74B-A9B BF16 currently has 10 source-displayable rows across 681 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Nemotron 3.5 Bolt 74B-A9B BF16?
Nemotron 3.5 Bolt 74B-A9B BF16 has a documented context window of 256K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.