# MiniCPM5-1B vs Qwen3.5-122B-A10B

> Side-by-side benchmark comparison for MiniCPM5-1B and Qwen3.5-122B-A10B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/minicpm5-1b-vs-qwen3-5-122b-a10b
- Last updated: November 11, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Qwen3.5-122B-A10B leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Qwen3.5-122B-A10B has the higher overall point estimate 52.64 to 5.26. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in instruction following, where the averages are 9.7 for MiniCPM5-1B and 93 for Qwen3.5-122B-A10B.
- The biggest single benchmark swing is LiveCodeBench v6 in Coding, with scores of 33.5% and 78.9%.
- Qwen3.5-122B-A10B also has the larger context window at 262K.

## Model Snapshot

| Property | MiniCPM5-1B | Qwen3.5-122B-A10B |
|----------|----------|----------|
| Creator | OpenBMB | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 131K | 262K |
| Overall Score | 5.26 | 52.64 |
| Benchmarks Covered | 14 | 18 |
| Pricing (input/output) | N/A | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- MiniCPM5-1B public-lane score: Coming soon
- Qwen3.5-122B-A10B public-lane score: 33.4 (Estimated · #95/132)

| Benchmark | MiniCPM5-1B | Qwen3.5-122B-A10B | Winner |
|-----------|-----------|-----------|--------|
| BFCL v4 | 25.1% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 49.4% | Coming soon |
| BrowseComp | Coming soon | 63.8% | Coming soon |
| OSWorld-Verified | Coming soon | 58% | Coming soon |

### Coding

- Winner: Not comparable
- MiniCPM5-1B public-lane score: Coming soon
- Qwen3.5-122B-A10B public-lane score: 35.4 (Supported · #87/158)

| Benchmark | MiniCPM5-1B | Qwen3.5-122B-A10B | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pro | 22.7% | Coming soon | Coming soon |
| LiveCodeBench v6 | 33.5% | 78.9% | Qwen3.5-122B-A10B |
| SWE-bench Verified | Coming soon | 72% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 49.4% | Coming soon |

### Reasoning

- Winner: Not comparable
- MiniCPM5-1B public-lane score: Coming soon
- Qwen3.5-122B-A10B public-lane score: 40.2 (Supported · #81/158)

| Benchmark | MiniCPM5-1B | Qwen3.5-122B-A10B | Winner |
|-----------|-----------|-----------|--------|
| BBH | 71.9% | Coming soon | Coming soon |
| LongBench v2 | Coming soon | 60.2% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- MiniCPM5-1B public-lane score: Coming soon
- Qwen3.5-122B-A10B public-lane score: 51.4 (Estimated · #52/67)

| Benchmark | MiniCPM5-1B | Qwen3.5-122B-A10B | Winner |
|-----------|-----------|-----------|--------|
| MMMU | Coming soon | 83.9% | Coming soon |
| MMVU | Coming soon | 74.7% | Coming soon |
| MMMU-Pro | Coming soon | 76.9% | Coming soon |
| MathVision | Coming soon | 86.2% | Coming soon |
| CharXiv | Coming soon | 77.2% | Coming soon |
| V* | Coming soon | 93.2% | Coming soon |

### Knowledge

- Winner: Directional only
- MiniCPM5-1B public-lane score: 9.9 (Estimated · #179/179)
- Qwen3.5-122B-A10B public-lane score: 48 (Estimated · #89/179)

| Benchmark | MiniCPM5-1B | Qwen3.5-122B-A10B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 48.9% | 86.7% | Qwen3.5-122B-A10B |
| MMLU-Redux | 70.1% | Coming soon | Coming soon |
| GPQA-D | 26.3% | Coming soon | Coming soon |
| SuperGPQA | 23.1% | 67.1% | Qwen3.5-122B-A10B |
| GPQA | Coming soon | 86.6% | Coming soon |

### Multilingual

- Winner: Not comparable
- MiniCPM5-1B public-lane score: Coming soon
- Qwen3.5-122B-A10B public-lane score: 87.1 (#9/17)

| Benchmark | MiniCPM5-1B | Qwen3.5-122B-A10B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 82.2% | Coming soon |

### Instruction Following

- Winner: Directional only
- MiniCPM5-1B public-lane score: 9.7 (#150/157)
- Qwen3.5-122B-A10B public-lane score: 93 (#13/157)

| Benchmark | MiniCPM5-1B | Qwen3.5-122B-A10B | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 46.7% | Coming soon | Coming soon |
| IFEval | 80.4% | 93.4% | Qwen3.5-122B-A10B |

### Mathematics

- Winner: Not comparable
- MiniCPM5-1B public-lane score: 12.1 (Unranked · 4 rankable rows)
- Qwen3.5-122B-A10B public-lane score: Coming soon

| Benchmark | MiniCPM5-1B | Qwen3.5-122B-A10B | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 40.4% | Coming soon | Coming soon |
| AIME26 | 40.4% | Coming soon | Coming soon |
| HMMT Feb 2026 | 25.8% | Coming soon | Coming soon |
| MATH-500 | 91.6% | Coming soon | Coming soon |

## FAQ

### Which is better overall, MiniCPM5-1B or Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between MiniCPM5-1B and Qwen3.5-122B-A10B?

The widest category gap is in instruction following, where the averages are 9.7 for MiniCPM5-1B and 93 for Qwen3.5-122B-A10B.

### How many benchmarks does MiniCPM5-1B cover on BenchLM?

MiniCPM5-1B currently has 14 sourced benchmark scores on BenchLM.

### How many benchmarks does Qwen3.5-122B-A10B cover on BenchLM?

Qwen3.5-122B-A10B currently has 18 sourced benchmark scores on BenchLM.

## Related Comparisons

- [MiniCPM5-1B vs MiniCPM5-2B](/compare/minicpm5-1b-vs-minicpm5-2b)
- [Qwen3.5-122B-A10B vs MiniCPM5-2B](/compare/minicpm5-2b-vs-qwen3-5-122b-a10b)
- [MiniCPM5-1B vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-minicpm5-1b)
- [Qwen3.5-122B-A10B vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-qwen3-5-122b-a10b)

## Explore More

- [MiniCPM5-1B profile](/models/minicpm5-1b)
- [Qwen3.5-122B-A10B profile](/models/qwen3-5-122b-a10b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)