Data as of November 21, 2026 · How the score is built
Decision readingMiniCPM5-1B scores 12.9 out of 100 and ranks #216 of 216. This profile shows 14 source-displayable benchmark rows; its strongest eligible category is Mathematics at #125. No comparable first-party API price is published in the catalog.
Email me when its price, rank or availability changes.
Capability
12.9/100
field median 47.5#216 of 216 ranked models
Public
#216of 216
Verified —
Price
Not listed
input median $0.60No comparable first-party hosted token rate
Speed
Not measured
field median 93.5 tok/sTime to first token not measured
Context
131Ktokens
field median 256,000Reported for this model; direct source link not stored
Decision snapshot
Where this model sits in the ranked field, its strongest published evidence, and what to validate before choosing it. The marker compares it with the current ranked catalog, not with an absolute quality threshold.
Strongest published evidence
Mathematics ranks #125. Particularly strong for mathematical reasoning, scientific computing, and quantitative analysis.
Validate before choosing
14 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 14 displayable benchmark rows
Is MiniCPM5-1B right for your job?
Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.
Where MiniCPM5-1B ranks by benchmark score:
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #182 of 182Percentile 0thWeight 22%1 benchmarkVerified | 16.1 | 1 benchmark | Verified | |||
| CodingRank #180 of 180Percentile 0thWeight 20%2 benchmarksVerified | 9.8 | 2 benchmarks | Verified | |||
| ReasoningWeight 17%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #158 of 158Percentile 0thWeight 12%4 benchmarksVerified | 9.9 | 4 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingRank #143 of 143Percentile 0thWeight 5%2 benchmarksVerified | 12.6 | 2 benchmarks | Verified | |||
| MathRank #125 of 125Percentile 0thWeight 5%4 benchmarksVerified | 12.9 | 4 benchmarks | Verified |
14 of 952 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic1/1 verified
- Coding2/2 verified
- Reasoning1/1 verified
- MultimodalNot measured
- Knowledge4/4 verified
- MultilingualNot measured
- Inst. Following2/2 verified
- Math4/4 verified
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
MiniCPM5-1B category percentile values
- Agentic0th percentile
- Coding0th percentile
- ReasoningNot eligible
- MultimodalNot eligible
- Knowledge0th percentile
- MultilingualNot eligible
- Instruction following0th percentile
- Math0th percentile
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#182/182
- Coding#180/180
- ReasoningNot ranked
- MultimodalNot ranked
- Knowledge#158/158
- MultilingualNot ranked
- Inst. Following#143/143
- Math#125/125
Benchmark ledger
Every result says who ran the test. For this model, OpenBMB ran all 14. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.
Coding2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| LiveCodeBench v6 | 33.5% | Best verified: Sakana Fugu-Ultra · 93.2% | Gap59.7 behind | Reported by OpenBMB | Counts5% ref. weight |
| LiveCodeBench Pro | 22.7% | Best verified: Sakana Fugu-Ultra · 90.8% | Gap68.1 behind | Reported by OpenBMB | Counts2% ref. weight |
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| BFCL v4Berkeley Function Calling Leaderboard v4 | 25.1% | Best verified: BTL-3 · 88.5% | Gap63.4 behind | Reported by OpenBMB | Counts2% ref. weight |
Reasoning1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| BBHBIG-Bench Hard | 71.9% | Best verified: Claude 3.5 Haiku · 86.6% | Gap14.7 behind | Reported by OpenBMB | Shown only |
Knowledge4 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MMLU-ProMassive Multitask Language Understanding Professional | 48.9% | Best verified: Qwen3.7 Max · 89.6% | Gap40.7 behind | Reported by OpenBMB | Counts4% ref. weight |
| GPQA-DGPQA Diamond | 26.3% | Best verified: GPT-6.2 Astra · 97.0% | Gap70.7 behind | Reported by OpenBMB | Counts3% ref. weight |
| SuperGPQASuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | 23.1% | Best verified: Qwen 3.6 Max (preview) · 73.9% | Gap50.8 behind | Reported by OpenBMB | Counts1% ref. weight |
| MMLU-Redux | 70.1% | Best verified: Qwen3.7 Max · 95% | Gap24.9 behind | Reported by OpenBMB | Counts1% ref. weight |
Inst. Following2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| IFBenchInstruction Following Benchmark | 46.7% | Best verified: Flint · 89.2% | Gap42.5 behind | Reported by OpenBMB | Counts18% ref. weight |
| IFEvalInstruction-Following Eval | 80.4% | Best verified: LFM2.5-24B-A2B · 96.8% | Gap16.3 behind | Reported by OpenBMB | Shown only |
Math4 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| HMMT Feb 2026Harvard-MIT Mathematics Tournament February 2026 | 25.8% | Best verified: Qwen3.7 Max · 97.1% | Gap71.3 behind | Reported by OpenBMB | Counts8% ref. weight |
| AIME 2025American Invitational Mathematics Examination 2025 | 40.4% | Best verified: GPT-5.2 · 100% | Gap59.6 behind | Reported by OpenBMB | Counts6% ref. weight |
| AIME26AIME 2026 | 40.4% | Best verified: GLM-5.2 · 99.2% | Gap58.8 behind | Reported by OpenBMB | Counts6% ref. weight |
| MATH-500MATH-500 Problem Set | 91.6% | Best verified: Ternary Bonsai 2 27B · 98.8% | Gap7.2 behind | Reported by OpenBMB | Shown only |
Outlined bars are lab-reported. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 131K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- textMiniCPM5-1B model card
- Output modalities
- textMiniCPM5-1B model card
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- MiniCPM5-1B needs ~24GB VRAM (1× NVIDIA RTX 4090 (24GB)).
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
MiniCPM5-1B ranks #216 of 216 on the public leaderboard with a score of 12.9/100. It does not yet have enough sourced coverage for a verified position.
MiniCPM5-1B is a open weight model with a 131K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Tracked from OpenBMB's MiniCPM5-1B Hugging Face, GitHub, and ModelScope release pages. The official model card describes MiniCPM5-1B as an Apache-2.0 dense 1.08B LlamaForCausalLM checkpoint with BF16 safetensors, a 131,072-token context window, bilingual English/Chinese support, local/on-device deployment focus, tool-calling support, and hybrid Think / No Think chat modes via enable_thinking. BenchLM maps exact benchmark rows from OpenBMB's published MiniCPM5-1B evaluation table.
MiniCPM5-1B sits in the MiniCPM5 family with MiniCPM5-2B. 14 of 952 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Mathematics at #125, while its lowest eligible position is Agentic at #182. particularly strong for mathematical reasoning, scientific computing, and quantitative analysis.
Last updated November 21, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Questions
How does MiniCPM5-1B perform overall in AI benchmarks?
MiniCPM5-1B ranks #216 out of 216 models on the public BenchAlign leaderboard, with a score of 12.9/100. Its evidence status is Estimated, and this profile shows 14 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is MiniCPM5-1B good for knowledge and understanding?
MiniCPM5-1B ranks #158 out of 158 eligible models for knowledge and understanding, with a public category score of 9.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is MiniCPM5-1B good for coding and programming?
MiniCPM5-1B ranks #180 out of 180 eligible models for coding and programming, with a public category score of 9.8/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is MiniCPM5-1B good for mathematics?
MiniCPM5-1B ranks #125 out of 125 eligible models for mathematics, with a public category score of 12.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is MiniCPM5-1B good for reasoning and logic?
MiniCPM5-1B has source-displayable benchmark coverage for reasoning and logic, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is MiniCPM5-1B good for agentic tool use and computer tasks?
MiniCPM5-1B ranks #182 out of 182 eligible models for agentic tool use and computer tasks, with a public category score of 16.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is MiniCPM5-1B good for instruction following?
MiniCPM5-1B ranks #143 out of 143 eligible models for instruction following, with a public category score of 12.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is MiniCPM5-1B open source?
MiniCPM5-1B is an open-weight model from OpenBMB. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to MiniCPM5-1B?
MiniCPM5-1B belongs to the MiniCPM5 family. Related tracked variants include MiniCPM5-2B. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does MiniCPM5-1B have full benchmark coverage on BenchLM?
No. MiniCPM5-1B currently has 15 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of MiniCPM5-1B?
MiniCPM5-1B has a reported context window of 131K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.