# kev 0.6B (research preview) vs Nemotron 3.5 Lightning 30B A3B NVFP4

> Side-by-side benchmark comparison for kev 0.6B (research preview) and Nemotron 3.5 Lightning 30B A3B NVFP4 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/jevbench-kev-0-6b-vs-nemotron-3-5-lightning-30b-a3b-nvfp4
- Last updated: September 30, 2026

- Shared sourced benchmarks: 0
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

No benchmark verdict yet: there is no shared sourced benchmark row for kev 0.6B (research preview) and Nemotron 3.5 Lightning 30B A3B NVFP4.

## Summary

- kev 0.6B (research preview) and Nemotron 3.5 Lightning 30B A3B NVFP4 do not currently share a sourced benchmark row. The mirror therefore compares metadata, pricing, context windows, and each model's separately reported coverage without naming a benchmark winner.

## Model Snapshot

| Property | kev 0.6B (research preview) | Nemotron 3.5 Lightning 30B A3B NVFP4 |
|----------|----------|----------|
| Creator | Jared Palmer | NVIDIA |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | null | 1M |
| Independent public score (not head-to-head) | null | 20.13 |
| Benchmarks Covered | 2 | 13 |
| Pricing (input/output) | Pricing unavailable / Pricing unavailable | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- kev 0.6B (research preview) public-lane score: Coming soon
- Nemotron 3.5 Lightning 30B A3B NVFP4 public-lane score: 8 (Estimated · #113/119)

| Benchmark | kev 0.6B (research preview) | Nemotron 3.5 Lightning 30B A3B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | Coming soon | 23.5% | Coming soon |
| PinchBench | Coming soon | 83.4% | Coming soon |
| BrowseComp | Coming soon | 36.8% | Coming soon |
| τ³-bench results | Coming soon | 9.5% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- kev 0.6B (research preview) public-lane score: Coming soon
- Nemotron 3.5 Lightning 30B A3B NVFP4 public-lane score: 12.2 (Estimated · #140/144)

| Benchmark | kev 0.6B (research preview) | Nemotron 3.5 Lightning 30B A3B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | Coming soon | 52.8% | Coming soon |
| SWE Multilingual | Coming soon | 36.5% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 23.5% | Coming soon |
| SciCode | Coming soon | 31.4% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- kev 0.6B (research preview) public-lane score: Coming soon
- Nemotron 3.5 Lightning 30B A3B NVFP4 public-lane score: 56 (Unranked · 1 rankable row)

| Benchmark | kev 0.6B (research preview) | Nemotron 3.5 Lightning 30B A3B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| JevBench 1.4 | 24.75 | Coming soon | Coming soon |
| JevBench 1.5 | 1.26 | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- kev 0.6B (research preview) public-lane score: Coming soon
- Nemotron 3.5 Lightning 30B A3B NVFP4 public-lane score: 22.4 (Estimated · #163/170)

| Benchmark | kev 0.6B (research preview) | Nemotron 3.5 Lightning 30B A3B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | Coming soon | 75.6% | Coming soon |
| GPQA-D | Coming soon | 75.6% | Coming soon |
| HLE w/o tools | Coming soon | 10.5% | Coming soon |
| MMLU-Pro | Coming soon | 81.6% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- kev 0.6B (research preview) public-lane score: Coming soon
- Nemotron 3.5 Lightning 30B A3B NVFP4 public-lane score: 68.5 (#67/124)

| Benchmark | kev 0.6B (research preview) | Nemotron 3.5 Lightning 30B A3B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 72.9% | Coming soon |

## FAQ

### Can I compare kev 0.6B (research preview) and Nemotron 3.5 Lightning 30B A3B NVFP4 on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but sourced benchmark coverage is still incomplete for a fair score-level comparison.

### Why does this page show "coming soon" values?

BenchLM only calls winners when public benchmark coverage is available on both sides of the comparison.

## Related Comparisons

- [kev 0.6B (research preview) vs GPT-6 Astra](/compare/gpt-6-astra-vs-jevbench-kev-0-6b)
- [Nemotron 3.5 Lightning 30B A3B NVFP4 vs GPT-6 Astra](/compare/gpt-6-astra-vs-nemotron-3-5-lightning-30b-a3b-nvfp4)
- [kev 0.6B (research preview) vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-jevbench-kev-0-6b)
- [Nemotron 3.5 Lightning 30B A3B NVFP4 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-nemotron-3-5-lightning-30b-a3b-nvfp4)

## Explore More

- [kev 0.6B (research preview) profile](/models/jevbench-kev-0-6b)
- [Nemotron 3.5 Lightning 30B A3B NVFP4 profile](/models/nemotron-3-5-lightning-30b-a3b-nvfp4)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)