# Kanana-2 3B Instruct vs Nemotron 3.5 Super VL 120B A12B NVFP4

> Side-by-side benchmark comparison for Kanana-2 3B Instruct and Nemotron 3.5 Super VL 120B A12B NVFP4 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kanana-2-3b-instruct-vs-nemotron-3-5-super-vl-120b-a12b-nvfp4
- Last updated: October 15, 2026

- Shared sourced benchmarks: 1
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Kanana-2 3B Instruct and Nemotron 3.5 Super VL 120B A12B NVFP4 share only 1 sourced benchmark row.

## Summary

- Only 1 shared sourced benchmark row is available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Nemotron 3.5 Super VL 120B A12B NVFP4 has the lower published output-token price.
- Nemotron 3.5 Super VL 120B A12B NVFP4 has the larger published context window at 1M.

## Model Snapshot

| Property | Kanana-2 3B Instruct | Nemotron 3.5 Super VL 120B A12B NVFP4 |
|----------|----------|----------|
| Creator | Kakao | NVIDIA |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 32K | 1M |
| Independent public score (not head-to-head) | null | null |
| Benchmarks Covered | 3 | 18 |
| Pricing (input/output) | $0.00 / $0.00 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Kanana-2 3B Instruct public-lane score: Coming soon
- Nemotron 3.5 Super VL 120B A12B NVFP4 public-lane score: Coming soon

| Benchmark | Kanana-2 3B Instruct | Nemotron 3.5 Super VL 120B A12B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | Coming soon | 60.8% | Coming soon |
| τ²-bench Airline | Coming soon | 75.8% | Coming soon |
| τ³-bench results | Coming soon | 17.8% | Coming soon |
| BrowseComp | Coming soon | 77.5% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Kanana-2 3B Instruct public-lane score: Coming soon
- Nemotron 3.5 Super VL 120B A12B NVFP4 public-lane score: Coming soon

| Benchmark | Kanana-2 3B Instruct | Nemotron 3.5 Super VL 120B A12B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench v6 | Coming soon | 87.4% | Coming soon |
| SWE-bench Verified | Coming soon | 71.1% | Coming soon |
| SWE Multilingual | Coming soon | 67% | Coming soon |
| SWE-bench Pro | Coming soon | 51.3% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Kanana-2 3B Instruct public-lane score: Coming soon
- Nemotron 3.5 Super VL 120B A12B NVFP4 public-lane score: 72.4 (Unranked · 1 rankable row)

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Kanana-2 3B Instruct public-lane score: Coming soon
- Nemotron 3.5 Super VL 120B A12B NVFP4 public-lane score: 59.5 (Unranked · 5 rankable rows)

| Benchmark | Kanana-2 3B Instruct | Nemotron 3.5 Super VL 120B A12B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| BabyVision | Coming soon | 29.5% | Coming soon |
| MMLongBench-Doc | Coming soon | 62.8% | Coming soon |
| V* | Coming soon | 86.0% | Coming soon |
| MathVision | Coming soon | 77.8% | Coming soon |
| CharXiv | Coming soon | 79.9% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Kanana-2 3B Instruct public-lane score: Coming soon
- Nemotron 3.5 Super VL 120B A12B NVFP4 public-lane score: Coming soon

| Benchmark | Kanana-2 3B Instruct | Nemotron 3.5 Super VL 120B A12B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | Coming soon | 89.9% | Coming soon |
| HLE w/o tools | Coming soon | 31.4% | Coming soon |
| HLE | Coming soon | 29% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Kanana-2 3B Instruct public-lane score: Coming soon
- Nemotron 3.5 Super VL 120B A12B NVFP4 public-lane score: 68.1 (#71/146)

| Benchmark | Kanana-2 3B Instruct | Nemotron 3.5 Super VL 120B A12B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 33.3% | 71.5% | Nemotron 3.5 Super VL 120B A12B NVFP4 |
| IFEval | 81.0% | Coming soon | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Kanana-2 3B Instruct public-lane score: Coming soon
- Nemotron 3.5 Super VL 120B A12B NVFP4 public-lane score: Coming soon

| Benchmark | Kanana-2 3B Instruct | Nemotron 3.5 Super VL 120B A12B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| MATH-500 | 61.2% | Coming soon | Coming soon |
| Apex Shortlist | Coming soon | 89.4% | Coming soon |

## FAQ

### Is there enough evidence to pick between Kanana-2 3B Instruct and Nemotron 3.5 Super VL 120B A12B NVFP4?

Not yet. The models share only 1 sourced benchmark row, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Kanana-2 3B Instruct vs Kanana-2 1.3B Instruct](/compare/kanana-2-1-3b-instruct-vs-kanana-2-3b-instruct)
- [Nemotron 3.5 Super VL 120B A12B NVFP4 vs Kanana-2 1.3B Instruct](/compare/kanana-2-1-3b-instruct-vs-nemotron-3-5-super-vl-120b-a12b-nvfp4)
- [Kanana-2 3B Instruct vs Nemotron 3.5 Super VL 120B A12B](/compare/kanana-2-3b-instruct-vs-nemotron-3-5-super-vl-120b-a12b)
- [Nemotron 3.5 Super VL 120B A12B NVFP4 vs Nemotron 3.5 Super VL 120B A12B](/compare/nemotron-3-5-super-vl-120b-a12b-vs-nemotron-3-5-super-vl-120b-a12b-nvfp4)

## Explore More

- [Kanana-2 3B Instruct profile](/models/kanana-2-3b-instruct)
- [Nemotron 3.5 Super VL 120B A12B NVFP4 profile](/models/nemotron-3-5-super-vl-120b-a12b-nvfp4)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)