# Mellum2-12B-A2.5B-Thinking vs Raw Phi-4 mini direct logits

> Side-by-side benchmark comparison for Mellum2-12B-A2.5B-Thinking and Raw Phi-4 mini direct logits across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/mellum2-12b-a2-5b-thinking-vs-raw-phi-4-mini
- Last updated: October 1, 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 Mellum2-12B-A2.5B-Thinking and Raw Phi-4 mini direct logits.

## Summary

- Mellum2-12B-A2.5B-Thinking and Raw Phi-4 mini direct logits 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 | Mellum2-12B-A2.5B-Thinking | Raw Phi-4 mini direct logits |
|----------|----------|----------|
| Creator | JetBrains | Microsoft |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 128K | null |
| Independent public score (not head-to-head) | null | null |
| Benchmarks Covered | 6 | 2 |
| Pricing (input/output) | N/A | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Mellum2-12B-A2.5B-Thinking public-lane score: Coming soon
- Raw Phi-4 mini direct logits public-lane score: Coming soon

| Benchmark | Mellum2-12B-A2.5B-Thinking | Raw Phi-4 mini direct logits | Winner |
|-----------|-----------|-----------|--------|
| BFCL v4 | 45.6% | Coming soon | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Mellum2-12B-A2.5B-Thinking public-lane score: Coming soon
- Raw Phi-4 mini direct logits public-lane score: Coming soon

| Benchmark | Mellum2-12B-A2.5B-Thinking | Raw Phi-4 mini direct logits | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench v6 | 69.9% | Coming soon | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Mellum2-12B-A2.5B-Thinking public-lane score: Coming soon
- Raw Phi-4 mini direct logits public-lane score: Coming soon

| Benchmark | Mellum2-12B-A2.5B-Thinking | Raw Phi-4 mini direct logits | Winner |
|-----------|-----------|-----------|--------|
| JevBench 1.4 | Coming soon | 37.96 | Coming soon |
| JevBench 1.5 | Coming soon | 15.22 | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Mellum2-12B-A2.5B-Thinking public-lane score: Coming soon
- Raw Phi-4 mini direct logits public-lane score: Coming soon

| Benchmark | Mellum2-12B-A2.5B-Thinking | Raw Phi-4 mini direct logits | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Redux | 86.2% | Coming soon | Coming soon |
| GPQA | 57.6% | Coming soon | Coming soon |
| GPQA-D | 57.6% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Mellum2-12B-A2.5B-Thinking public-lane score: Coming soon
- Raw Phi-4 mini direct logits public-lane score: Coming soon

| Benchmark | Mellum2-12B-A2.5B-Thinking | Raw Phi-4 mini direct logits | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 76.5% | Coming soon | Coming soon |

## FAQ

### Can I compare Mellum2-12B-A2.5B-Thinking and Raw Phi-4 mini direct logits 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

- [Mellum2-12B-A2.5B-Thinking vs Mellum2-12B-A2.5B-Instruct](/compare/mellum2-12b-a2-5b-instruct-vs-mellum2-12b-a2-5b-thinking)
- [Raw Phi-4 mini direct logits vs Mellum2-12B-A2.5B-Instruct](/compare/mellum2-12b-a2-5b-instruct-vs-raw-phi-4-mini)
- [Mellum2-12B-A2.5B-Thinking vs GPT-6 Astra](/compare/gpt-6-astra-vs-mellum2-12b-a2-5b-thinking)
- [Raw Phi-4 mini direct logits vs GPT-6 Astra](/compare/gpt-6-astra-vs-raw-phi-4-mini)

## Explore More

- [Mellum2-12B-A2.5B-Thinking profile](/models/mellum2-12b-a2-5b-thinking)
- [Raw Phi-4 mini direct logits profile](/models/raw-phi-4-mini)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)