- MultiChallenge 55.6
- RoleBench (non-reasoning) 71.2
- RoleMRC 79.1
- EQ-Bench v3 (non-reasoning) 38.1
- Brevity Benchmark 82.8
- BFCL-v3 67.3
- When2Call Multi-Turn 60.5
- ToolSandbox 74.1
- Tau2-Bench 52.3
- IHEval 82.4
- AgentIF 22.9
- StructEval-T 80
- IFBench 64
- InverseIFEval 45.3
- RULER (64K, non-reasoning) 85.8
- LongMemEval 69.9
- LongBench v2 (48K) 48.7
- SysBench 67.2
- GaRAGe 40.7
- RAGTruth 77.9
- RelyToolBench 69.3
Nemotron 3.5 Bolt E4B
Nemotron 3.5 Bolt E4B.
31
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
NVIDIA Oct 2026 Nemotron 3.5 Bolt E4B
Open weights Small
No Epoch Capabilities Index score yet
- IFBench 64% #51 /70
- MMMU-Pro 42% #68 /72
- LongBench v2 48.7% #22 /27
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AgentIF (2026-10 setting) | 64.7% | #7 of 24 | Official leaderboard | |
| EQ-Bench 3 | 1,199 | #43 of 78 | Official leaderboard | |
| MultiChallenge | 55.6% | #22 of 36 | Model card | |
| RULER | 85.8% | #26 of 38 | Model card | |
| IFBench | 64% | #51 of 70 | Model card | |
| Creative Writing v3 | 57.0 | #92 of 120 | Official leaderboard | |
| LongBench v2 | 48.7% | #22 of 27 | Model card | |
| MMLU-ProX | 66.2% | #15 of 17 | Model card | |
| SysBench | 67.2% | #6 of 6 | Model card | |
| Inverse IFEval | 45.3% | #3 of 3 | Model card | |
| AgentIF | 22.9% | #1 of 1 | Model card | |
| Brevity Benchmark | 82.8% | #1 of 1 | Model card | |
| GaRAGe | 40.7% | #1 of 1 | Model card | |
| LongMemEval | 69.9% | #1 of 1 | Model card | |
| RAGTruth | 77.9% | #1 of 1 | Model card | |
| RoleBench | 71.2 | #1 of 1 | Model card | |
| RoleMRC | 79.1% | #1 of 1 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| StructEval | 80% | #1 of 1 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) | 67.3% | #29 of 47 | Model card | |
| ToolSandbox | 74.1% | #4 of 5 | Model card | |
| tau2-bench | 52.3% | #65 of 69 | Model card | |
| RelyToolBench | 69.3% | #1 of 1 | Model card | |
| When2Call | 60.5% | #1 of 1 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MedXpertQA-MM | 26.9% | #12 of 12 | Model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OmniDocBench v1.5 | 0.42 | #5 of 13 | Model card | |
| VoiceBench | 80.3% | #8 of 10 | Model card | |
| MATH-Vision (MathVision) | 46.3% | #37 of 42 | Model card | |
| CoVoST2 | 36.1 | #10 of 11 | Model card | |
| MMMU-Pro | 42% | #68 of 72 | Model card | |
| Audio MC | 25.2% | #5 of 5 | Model card |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| IHEval | 82.4% | #1 of 2 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 11 of them aren't in the launch post.
Nemotron 3.5 Bolt E4B 4GB: An Open and Efficient Small Language Model for Fast Conversational Agents 23 Oct 2026
Capabilities
- MultiChallenge 55.6
- RoleBench 71.2
- RoleMRC 79.1
- EQ-Bench 3 38.1
- Brevity Benchmark 82.8
- Berkeley Function Calling Leaderboard (BFCL) 67.3
- When2Call 60.5
- ToolSandbox 74.1
- tau2-bench 52.3
- IHEval 82.4
- AgentIF 22.9
- StructEval 80
- IFBench 64
- Inverse IFEval 45.3
- RULER 85.8
- LongMemEval 69.9
- LongBench v2 48.7
- SysBench 67.2
- RelyToolBench 69.3
- WMT24++ 74.4
- MMLU-ProX 66.2
- Audio MC 25.2
- VoiceBench 80.3
- CoVoST2 36.1
- FLEURS 10.2
- Open ASR Leaderboard 9.28
- OmniDocBench v1.5 0.42
- MMMU-Pro 42
- MATH-Vision (MathVision) 46.3
Health
- MedXpertQA-MM 26.9