Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
NVIDIA · Open Weight · bench-align-v5
Nemotron 3.5 Bolt E4B is a general-purpose language model.
Nemotron 3.5 Bolt E4B by NVIDIA carries a context window of 64K tokens — observed 2026-11-21.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
Every published price component, including cache reads and writes.
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: ObservedUnavailable
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | Unavailable | Unavailable | Unavailable | |
| Throughput | Unavailable | Unavailable | Unavailable |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| LongBench v2 LongBench v2 | 48.67 | #24 | Long-context tasks | Hard long-context | LongBench v2 |
| RULER (64K) RULER at a 64K-token context | 85.76 | #2 | Synthetic long-context tasks | Long-context retrieval and reasoning | RULER: What's the Real Context Size of Your Long-Context Language Models? |
| LongMemEval LongMemEval | 69.92 | #2 | Questions over multi-session chat histories | Recall across conversations | LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-IFBench Artificial Analysis IFBench | 61.1 | #65 | Verifiable instruction constraints | Instruction precision | Artificial Analysis IFBench Benchmark Leaderboard |
| MultiChallenge (provider reports) MultiChallenge: provider-reported runs | 55.60 | #2 | — | — | MultiChallenge |
| Brevity Benchmark Brevity Benchmark (NVIDIA) | 82.84 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| τ²-bench results τ²-Bench Tool-Agent-User Evaluation | 52.32 | #97 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment |
| BFCL v3 Berkeley Function Calling Leaderboard v3 | 67.3 | #7 | Function-calling tasks | Advanced tool use | The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models |
| When2Call Multi-Turn When2Call Multi-Turn (NVIDIA) | 60.50 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GaRAGe GaRAGe | 40.73 | #2 | Questions with retrieved passages | Facts from supplied sources | GaRAGe |
| RAGTruth (provider reports) RAGTruth: provider-reported F1 | 77.88 | #1 | Retrieval-augmented question answering, summarization and data-to-text | Avoiding unsupported claims | RAGTruth |
| #1 |
| Conversational prompts (not yet published) |
| Concise, speech-ready answers |
| NVIDIA Nemotron 3.5 Bolt E4B 4GB |
| EQ-Bench 3 EQ-Bench 3 | 38.15 | #2 | Multi-turn roleplay scenarios | Emotional and social intelligence | EQ-Bench 3 |
| RoleBench RoleBench (RoleLLM) | 71.21 | #1 | Character role-play prompts | Character speaking style | RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models |
| RoleMRC RoleMRC | 79.12 | #2 | Role-play and in-role instruction prompts | Role identity adherence | RoleMRC |
| IHEval IHEval: instruction hierarchy evaluation | 82.40 | #2 | Aligned and conflicting instruction sets | Instruction priority | IHEval: Evaluating Language Models on Following the Instruction Hierarchy |
| AgentIF AgentIF: instruction following in agentic scenarios | 22.95 | #2 | Agentic system prompts and instructions | Complex agentic instructions | AgentIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios |
| InverseIFEval InverseIFEval | 45.26 | #2 | Counterintuitive instructions | Overriding trained conventions | InverseIFEval |
| StructEval-T StructEval text-format subset | 79.99 | #2 | Structured-output generation and conversion | Valid structured output | StructEval |
| SysBench SysBench: system message following | 67.22 | #2 | System-message constraints over conversations | Keeping long prompt rules | SysBench: Can Large Language Models Follow System Messages? |
| #2 |
| Multi-turn tool-use decisions (not yet published) |
| When to call, clarify or abstain |
| NVIDIA Nemotron 3.5 Bolt E4B 4GB |
| ToolSandbox ToolSandbox | 74.13 | #2 | Stateful tool-use conversations | Tool use with changing state | ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities |
| RelyToolBench RelyToolBench | 69.29 | #1 | Tool-use requests | Tool grounding and hallucination | RelyToolBench |