Model comparison
Hy3 Preview vs MiniCPM5-1B
Head-to-head evidence from 2 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Evidence parity. Hy3 Preview and MiniCPM5-1B share 2 comparable benchmark results. 2 of 8 categories are comparable. 20 results are unique to Hy3 Preview; 12 to MiniCPM5-1B.
Updated July 23, 2026- Shared results
- 2
- Hy3 Preview only
- 20
- MiniCPM5-1B only
- 12
- Comparable categories
- 2 / 8
Treat this as a split decision. Hy3 Preview makes more sense if instruction following is the priority or you need the larger 256K context window; MiniCPM5-1B is the better fit if knowledge is the priority.
Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 2 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Hy3 Preview and MiniCPM5-1B finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
Hy3 Preview gives you the larger context window at 256K, compared with 131K for MiniCPM5-1B.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Hy3 Preview | Δ | MiniCPM5-1B |
|---|---|---|---|
| Knowledge | Hy3 Preview33.8 | Margin→ 10.2 | MiniCPM5-1B44.0 |
| Inst. Following | Hy3 Preview63.1 | Margin← 4.6 | MiniCPM5-1B58.5 |
| Agentic | Hy3 Preview54.4 | MarginNo overlap | MiniCPM5-1BNot measured |
| Coding | Hy3 Preview57.8 | MarginNo overlap | MiniCPM5-1BNot measured |
| Math | Hy3 PreviewNot measured | MarginNo overlap | MiniCPM5-1B33.1 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
IFBench
Inst. FollowingA 63.1%B 46.7%Winner: Hy3 PreviewΔ 16.4IFBench: Hy3 Preview scored 63.1%; MiniCPM5-1B scored 46.7%. Hy3 Preview wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Hy3 Preview | MiniCPM5-1B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Hy3 Preview$0 input / $0 output | MiniCPM5-1BNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Hy3 PreviewNot available | MiniCPM5-1BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Hy3 PreviewNot available | MiniCPM5-1BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Hy3 Preview256K | MiniCPM5-1B131K | Hy3 Preview lists the larger context window. |
Benchmark Deep Dive
Agentic6 benchmarks
Coding7 benchmarks
| Benchmark | Hy3 Preview | MiniCPM5-1B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 74.4% | — | Not comparable |
| Terminal-Bench 2.0Source | 54.4% | — | Not comparable |
| SciCodeSource | 41.2% | — | Not comparable |
| AA-SciCodeSource | 47.6% | — | Not comparable |
| AA Coding IndexSource | 58.8% | — | Not comparable |
| LiveCodeBench ProSource | — | 22.7% | Not comparable |
| LiveCodeBench v6Source | — | 33.5% | Not comparable |
Reasoning3 benchmarks
KnowledgeMiniCPM5-1B wins12 benchmarks
| Benchmark | Hy3 Preview | MiniCPM5-1B | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 41.2% | — | Not comparable |
| GPQASource | 87.2% | — | Not comparable |
| GPQA-DSource | 87.2% | 26.3% | Hy3 Preview leads |
| HLESource | 25.5% | — | Not comparable |
| AA-Omniscience AccuracySource | 31.5% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 73.0% | — | Not comparable |
| AA-GPQA DiamondSource | 89.7% | — | Not comparable |
| AA-HLESource | 31.6% | — | Not comparable |
| AA-Omniscience IndexSource | -18.5% | — | Not comparable |
| MMLU-ProSource | — | 48.9% | Not comparable |
| MMLU-ReduxSource | — | 70.1% | Not comparable |
| SuperGPQASource | — | 23.1% | Not comparable |
Math4 benchmarks
Frequently Asked Questions (3)
Which is better, Hy3 Preview or MiniCPM5-1B?
Hy3 Preview and MiniCPM5-1B are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for knowledge tasks, Hy3 Preview or MiniCPM5-1B?
MiniCPM5-1B has the edge for knowledge tasks in this comparison, averaging 44 versus 33.8. Inside this category, GPQA-D is the benchmark that creates the most daylight between them.
Which is better for instruction following, Hy3 Preview or MiniCPM5-1B?
Hy3 Preview has the edge for instruction following in this comparison, averaging 63.1 versus 58.5. Inside this category, IFBench is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.