# Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) vs kev 4B (research preview)

> Side-by-side benchmark comparison for Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) and kev 4B (research preview) across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/jevbench-decision-4b-v12-vs-jevbench-kev-4b
- Last updated: September 30, 2026

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

## Quick Verdict

Evidence is too thin for a benchmark verdict: Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) and kev 4B (research preview) 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.

## Model Snapshot

| Property | Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) | kev 4B (research preview) |
|----------|----------|----------|
| Creator | unknown | Jared Palmer |
| Type | Unknown | Open Weight |
| Reasoning | Non-Reasoning | Non-Reasoning |
| Context | null | null |
| Independent public score (not head-to-head) | null | null |
| Benchmarks Covered | 1 | 2 |
| Pricing (input/output) | Pricing unavailable / Pricing unavailable | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Reasoning

- Winner: Insufficient shared evidence
- Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) public-lane score: Coming soon
- kev 4B (research preview) public-lane score: Coming soon

| Benchmark | Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) | kev 4B (research preview) | Winner |
|-----------|-----------|-----------|--------|
| JevBench 1.5 | 70.83 | 38.07 | Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) |
| JevBench 1.4 | Coming soon | 36.14 | Coming soon |

## FAQ

### Is there enough evidence to pick between Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) and kev 4B (research preview)?

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

- [Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) vs GPT-6 Astra](/compare/gpt-6-astra-vs-jevbench-decision-4b-v12)
- [kev 4B (research preview) vs GPT-6 Astra](/compare/gpt-6-astra-vs-jevbench-kev-4b)
- [Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-jevbench-decision-4b-v12)
- [kev 4B (research preview) vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-jevbench-kev-4b)

## Explore More

- [Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) profile](/models/jevbench-decision-4b-v12)
- [kev 4B (research preview) profile](/models/jevbench-kev-4b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)