# Mellum2.1-12B-A2.5B-Thinking Benchmark Scores & Performance

> Mellum2.1-12B-A2.5B-Thinking by JetBrains has 7 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/mellum2-1-12b-a2-5b-thinking

Last updated: October 8, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | JetBrains |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Overall Score | Not computed (unranked) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Mellum2.1 12B-A2.5B
- Variant: thinking
- Benchmarks covered: 7 of 623
- Related earlier model: [Mellum2-12B-A2.5B-Thinking](/models/mellum2-12b-a2-5b-thinking)
- Coverage note: Published evidence is shown below; no public overall score is assigned.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 17.4% | [JetBrains: Mellum2.1 Thinking model card](https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 82.0% | [JetBrains: Mellum2.1 Thinking model card](https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking) |
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 47% | [JetBrains: Mellum2.1 Thinking model card](https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking) |
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 28% | [JetBrains: Mellum2.1 Thinking model card](https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MMLU-Redux](/benchmarks/mmluredux) | 87.8% | [JetBrains: Mellum2.1 Thinking model card](https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking) |
| [GPQA-D](/benchmarks/gpqa-diamond) | 64.6% | [JetBrains: Mellum2.1 Thinking model card](https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFEval](/benchmarks/ifeval) | 90.6% | [JetBrains: Mellum2.1 Thinking model card](https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking) |

## Other JetBrains Models

- [Mellum2-12B-A2.5B-Thinking](/models/mellum2-12b-a2-5b-thinking) - Score: not computed
- [Mellum2-12B-A2.5B-Instruct](/models/mellum2-12b-a2-5b-instruct) - Score: not computed