# MiniCPM5-2B vs Muse Spark

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

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

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Muse Spark 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

- Muse Spark leads overall 67.69 to 44.
- The biggest single benchmark swing is HLE in Knowledge, with scores of 8.9% and 50.4%.
- Muse Spark also has the larger context window at 262K.

## Model Snapshot

| Property | MiniCPM5-2B | Muse Spark |
|----------|----------|----------|
| Creator | OpenBMB | Meta |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 131K | 262K |
| Overall Score | null | 67.69 |
| Benchmarks Covered | 19 | 24 |
| Pricing (input/output) | $0.00 / $0.00 | N/A |

## Category Breakdown

### Agentic

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Muse Spark public-lane score: 56.1 (Supported · #34/152)

| Benchmark | MiniCPM5-2B | Muse Spark | Winner |
|-----------|-----------|-----------|--------|
| BFCL v4 | 66.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 8.6% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 59% | Coming soon |
| τ²-bench results | Coming soon | 91.5% | Coming soon |
| DeepSearchQA | Coming soon | 74.8% | Coming soon |
| CyberGym | Coming soon | 43.5% | Coming soon |
| Claw-Eval | Coming soon | 63.8% | Coming soon |

### Coding

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Muse Spark public-lane score: 59 (Supported · #25/151)

| Benchmark | MiniCPM5-2B | Muse Spark | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench v6 | 69.1% | Coming soon | Coming soon |
| SciCode | 26.3% | Coming soon | Coming soon |
| SWE-bench Verified | 46.4% | 77.4% | Muse Spark |
| SWE-bench Pro | 14.4% | 52.4% | Muse Spark |
| Terminal-Bench 2.1 | 8.6% | Coming soon | Coming soon |
| LiveCodeBench Pro | Coming soon | 80.0% | Coming soon |
| Vibe Code Bench | Coming soon | 19.67% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Muse Spark public-lane score: 77.5 (#14/48)

| Benchmark | MiniCPM5-2B | Muse Spark | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | Coming soon | 86.4% | Coming soon |
| MMMU-Pro | Coming soon | 80.4% | Coming soon |
| ERQA | Coming soon | 64.7% | Coming soon |
| SimpleVQA | Coming soon | 71.3% | Coming soon |
| ScreenSpot Pro | Coming soon | 84.1% | Coming soon |
| ZeroBench | Coming soon | 33.0% | Coming soon |
| MedXpertQA (MM) | Coming soon | 78.4% | Coming soon |

### Reasoning

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Muse Spark public-lane score: 45.1 (Unranked · 3 rankable rows)

| Benchmark | MiniCPM5-2B | Muse Spark | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 43.7% | Coming soon | Coming soon |
| ARC-AGI-2 | Coming soon | 42.5% | Coming soon |

### Knowledge

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Muse Spark public-lane score: 65.4 (Supported · #24/183)

| Benchmark | MiniCPM5-2B | Muse Spark | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 70.8% | Coming soon | Coming soon |
| MMLU-Redux | 84.7% | Coming soon | Coming soon |
| HLE | 8.9% | 50.4% | Muse Spark |
| GPQA-D | 70.2% | 89.5% | Muse Spark |
| SuperGPQA | 40.8% | Coming soon | Coming soon |
| HLE w/o tools | Coming soon | 42.8% | Coming soon |
| HealthBench Hard | Coming soon | 42.8% | Coming soon |
| MedXpertQA (Text) | Coming soon | 52.6% | Coming soon |

### Instruction Following

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Muse Spark public-lane score: 93.2 (#8/123)

| Benchmark | MiniCPM5-2B | Muse Spark | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 66.3% | Coming soon | Coming soon |
| IFEval | 86.7% | Coming soon | Coming soon |

### Mathematics

- Winner: Coming soon
- MiniCPM5-2B public-lane score: Coming soon
- Muse Spark public-lane score: 55.3 (Unranked · 2 rankable rows)

| Benchmark | MiniCPM5-2B | Muse Spark | 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 |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 39.000% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 14.600% | Coming soon |

## FAQ

### Which is better overall, MiniCPM5-2B or Muse Spark?

Muse Spark 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 Muse Spark cover on BenchLM?

Muse Spark currently has 24 sourced benchmark scores on BenchLM.

## Related Comparisons

- [MiniCPM5-2B vs MiniCPM5-1B](/compare/minicpm5-1b-vs-minicpm5-2b)
- [Muse Spark vs MiniCPM5-1B](/compare/minicpm5-1b-vs-muse-spark)
- [MiniCPM5-2B vs Muse Spark 1.2](/compare/minicpm5-2b-vs-muse-spark-1-2)
- [Muse Spark vs Muse Spark 1.2](/compare/muse-spark-vs-muse-spark-1-2)

## Explore More

- [MiniCPM5-2B profile](/models/minicpm5-2b)
- [Muse Spark profile](/models/muse-spark)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)
