# MiniCPM5-2B vs Qwen3.8-27B

> Side-by-side benchmark comparison for MiniCPM5-2B and Qwen3.8-27B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/minicpm5-2b-vs-qwen3-8-27b
- Last updated: September 10, 2026

- Shared sourced benchmarks: 7
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Qwen3.8-27B if you want the stronger benchmark profile. MiniCPM5-2B only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Qwen3.8-27B leads overall 64.52 to 44.
- The biggest single benchmark swing is Terminal-Bench 2.1 in Agentic, with scores of 8.6% and 73.0%.
- Qwen3.8-27B also has the larger context window at 262K.

## Model Snapshot

| Property | MiniCPM5-2B | Qwen3.8-27B |
|----------|----------|----------|
| Creator | OpenBMB | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 131K | 262K |
| Overall Score | null | 64.52 |
| Benchmarks Covered | 19 | 33 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Qwen3.8-27B public-lane score: 63.4 (Supported · #13/152)

| Benchmark | MiniCPM5-2B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| BFCL v4 | 66.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 8.6% | 73.0% | Qwen3.8-27B |
| CoWorkBench | Coming soon | 70.7% | Coming soon |
| JobBench | Coming soon | 33.4% | Coming soon |
| Agents' Last Exam | Coming soon | 42.9% | Coming soon |
| OSWorld-Verified | Coming soon | 84.3% | Coming soon |
| WebArena-Verified | Coming soon | 64.8% | Coming soon |
| AndroidWorld | Coming soon | 81.9% | Coming soon |
| Terminal-Bench 2.1 (Vals) | Coming soon | 58.4% | Coming soon |

### Coding

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Qwen3.8-27B public-lane score: 53.9 (Supported · #43/151)

| Benchmark | MiniCPM5-2B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench v6 | 69.1% | 90.3% | Qwen3.8-27B |
| SciCode | 26.3% | Coming soon | Coming soon |
| SWE-bench Verified | 46.4% | Coming soon | Coming soon |
| SWE-bench Pro | 14.4% | 61.7% | Qwen3.8-27B |
| Terminal-Bench 2.1 | 8.6% | 73.0% | Qwen3.8-27B |
| NL2Repo | Coming soon | 42.3% | Coming soon |
| DeepSWE | Coming soon | 42.2% | Coming soon |
| VulcanBench v3 | Coming soon | 82.6% | Coming soon |
| LiveCodeBench (Vals) | Coming soon | 84.0% | Coming soon |
| SWE-bench (Vals) | Coming soon | 86.0% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Qwen3.8-27B public-lane score: 80 (#11/48)

| Benchmark | MiniCPM5-2B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| MathVision | Coming soon | 90.0% | Coming soon |
| MathVision w/ Python | Coming soon | 94.6% | Coming soon |
| BabyVision | Coming soon | 65.7% | Coming soon |
| BabyVision w/ Python | Coming soon | 85.6% | Coming soon |
| Vision2Web | Coming soon | 62.9% | Coming soon |
| CharXiv w/o tools | Coming soon | 83.7% | Coming soon |
| CharXiv | Coming soon | 90.2% | Coming soon |
| OmniDocBench 1.5 | Coming soon | 91.1% | Coming soon |
| RealWorldQA | Coming soon | 85.9% | Coming soon |
| ERQA | Coming soon | 65.5% | Coming soon |

### Reasoning

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Qwen3.8-27B public-lane score: 77.4 (#7/20)

| Benchmark | MiniCPM5-2B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 43.7% | Coming soon | Coming soon |

### Knowledge

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Qwen3.8-27B public-lane score: 54.1 (Supported · #58/183)

| Benchmark | MiniCPM5-2B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 70.8% | Coming soon | Coming soon |
| MMLU-Redux | 84.7% | Coming soon | Coming soon |
| HLE | 8.9% | 30.8% | Qwen3.8-27B |
| GPQA-D | 70.2% | 89.2% | Qwen3.8-27B |
| SuperGPQA | 40.8% | Coming soon | Coming soon |
| GPQA | Coming soon | 89.2% | Coming soon |
| HLE w/o tools | Coming soon | 30.8% | Coming soon |
| GPQA Diamond (Vals) | Coming soon | 88.9% | Coming soon |
| MMLU-Pro (Vals) | Coming soon | 84.3% | Coming soon |

### Instruction Following

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Qwen3.8-27B public-lane score: 84.7 (#45/123)

| Benchmark | MiniCPM5-2B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 66.3% | 79.5% | Qwen3.8-27B |
| IFEval | 86.7% | Coming soon | Coming soon |

### Mathematics

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Qwen3.8-27B public-lane score: Coming soon

| Benchmark | MiniCPM5-2B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 86.5% | Coming soon | Coming soon |
| AIME26 | 86.5% | Coming soon | Coming soon |
| HMMT Feb 2026 | 63.8% | Coming soon | Coming soon |
| MATH-500 | 94.6% | Coming soon | Coming soon |

## FAQ

### Which is better overall, MiniCPM5-2B or Qwen3.8-27B?

Qwen3.8-27B is ahead overall on BenchLM right now.

### How many benchmarks does MiniCPM5-2B cover on BenchLM?

MiniCPM5-2B currently has 19 sourced benchmark scores on BenchLM.

### How many benchmarks does Qwen3.8-27B cover on BenchLM?

Qwen3.8-27B currently has 33 sourced benchmark scores on BenchLM.

## Related Comparisons

- [MiniCPM5-2B vs MiniCPM5-1B](/compare/minicpm5-1b-vs-minicpm5-2b)
- [Qwen3.8-27B vs MiniCPM5-1B](/compare/minicpm5-1b-vs-qwen3-8-27b)
- [MiniCPM5-2B vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-minicpm5-2b)
- [Qwen3.8-27B vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-qwen3-8-27b)

## Explore More

- [MiniCPM5-2B profile](/models/minicpm5-2b)
- [Qwen3.8-27B profile](/models/qwen3-8-27b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)