Skip to main content
BenchLM
Data

MiniCPM5-1B vs Trinity-Large-Thinking

Updated November 21, 2026. Rank says Trinity-Large-Thinking is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Trinity-Large-Thinking has the higher public point estimate, 36.8 versus 12.9. Their conditional score ranges overlap. These ranges do not establish rank confidence. 2 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
OpenBMB logo

OpenBMB

12.9/100

Estimated · Public rank #212

Conditional range 0.0–26.7

Model B
Arcee AI logo

Arcee AI

36.8/100

Supported · Public rank #175

Conditional range 23.4–50.2

API price per 1M tokens

MiniCPM5-1B: No comparable API price

Trinity-Large-Thinking: $0.25 input / $0.90 output

Context window

MiniCPM5-1B: 131K

Trinity-Large-Thinking: 512K

Released

MiniCPM5-1B: May 25, 2026

Trinity-Large-Thinking: March 10, 2026

Shared results
2
MiniCPM5-1B only
12
Trinity-Large-Thinking only
5
Like-for-like categories
0 / 8
Estimated: MiniCPM5-1B · Supported: Trinity-Large-Thinking. Conditional ranges do not establish rank confidence.How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Long documents

    Prompts that approach the documented context limit

    Trinity-Large-Thinking

    Trinity-Large-Thinking has the larger documented context window.

    Confidence: documented
Show secondary and unsupported calls
  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Trinity-Large-Thinking is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited
  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    MiniCPM5-1B is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited
  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. MiniCPM5-1B does not fit this workload in one request. Trinity-Large-Thinking has no published cached-input rate, so cached tokens use its listed input rate. MiniCPM5-1B has no comparable published API token rate.

    Confidence: rate-fallback
  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

9.8MiniCPM5-1B—Trinity-Large-Thinking

Not comparable · BenchAlign v6.0

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

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

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Directional only
MiniCPM5-1B
16.1
Estimated · #182/182
Trinity-Large-Thinking
38.3
Supported · #147/182
Basis
BenchAlign v6.0 lane · 1 vs 2 public rows
Reading
Directional only

Knowledge

Directional only
MiniCPM5-1B
9.9
Estimated · #158/158
Trinity-Large-Thinking
35.4
Estimated · #142/158
Basis
BenchAlign v6.0 lane · 4 vs 2 public rows
Reading
Directional only

Instruction following

Directional only
MiniCPM5-1B
12.6
Estimated · #143/143
Trinity-Large-Thinking
34.5
Estimated · #123/143
Basis
BenchAlign v6.0 lane · 2 vs 1 public rows
Reading
Directional only

Coding

Not comparable
MiniCPM5-1B
9.8
Estimated · #180/180
Trinity-Large-Thinking
Not ranked
Basis
BenchAlign v6.0 lane · 2 vs 1 public rows
Reading
Not comparable

Reasoning

Not comparable
MiniCPM5-1B
Not ranked
Trinity-Large-Thinking
35.5
Estimated · #157/161
Basis
BenchAlign v6.0 lane · 1 vs 0 public rows
Reading
Not comparable

Multimodal

Not comparable
MiniCPM5-1B
Not ranked
Trinity-Large-Thinking
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Multilingual

Not comparable
MiniCPM5-1B
Not ranked
Trinity-Large-Thinking
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Math

Not comparable
MiniCPM5-1B
12.9
Estimated · #125/125
Trinity-Large-Thinking
Not ranked
Basis
BenchAlign v6.0 lane · 4 vs 1 public rows
Reading
Not comparable

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

MiniCPM5-1B
API rate not published
Fits in one request
Trinity-Large-Thinking
$0.0007
Fits in one request

MiniCPM5-1B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

MiniCPM5-1B
API rate not published
Fits in one request
Trinity-Large-Thinking
$0.0152
Fits in one request

MiniCPM5-1B has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

MiniCPM5-1B
API rate not published
Does not fit in one request
Cached-input rate unavailable
Trinity-Large-Thinking
$0.064
Fits in one request
Cached input priced at the published list-input rate

MiniCPM5-1B does not fit this workload in one request. Trinity-Large-Thinking has no published cached-input rate, so cached tokens use its listed input rate. MiniCPM5-1B has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 21, 2026.

Trinity-Large-Thinking

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • MiniCPM5-1B has no public API price, so it is not plotted.
  • 13 cheaper models score at least as high as Trinity-Large-Thinking. The nearest is MiMo-V2.6-Pro (score 63.0, $0.87 per 1M output tokens).

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Trinity-Large-Thinking on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Context window

Maximum documented context; output-token limits may be lower.

MiniCPM5-1B

131K

Trinity-Large-Thinking

512K

API model ID

MiniCPM5-1B

Not sourced

Trinity-Large-Thinking

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

MiniCPM5-1B

No comparable hosted API rate

Trinity-Large-Thinking

Not published

Provider availability

MiniCPM5-1B

Not sourced

Trinity-Large-Thinking

Not sourced

Reasoning profile

MiniCPM5-1B

Reasoning

Trinity-Large-Thinking

Reasoning

Weight access

MiniCPM5-1B

Open Weight

Trinity-Large-Thinking

Open Weight

License

MiniCPM5-1B

Open Weight

Trinity-Large-Thinking

Open Weight

Release date

MiniCPM5-1B

2026-05-25

Trinity-Large-Thinking

2026-03-10

If you already use one of these models

Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
Trinity-Large-Thinking has the higher public point estimate, 36.8 versus 12.9. Their conditional score ranges overlap. These ranges do not establish rank confidence.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Trinity-Large-Thinking has the larger documented window (512K).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, MiniCPM5-1B or Trinity-Large-Thinking?

Trinity-Large-Thinking has the higher public point estimate, 36.8 versus 12.9. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, MiniCPM5-1B or Trinity-Large-Thinking?

Trinity-Large-Thinking is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, MiniCPM5-1B or Trinity-Large-Thinking?

Trinity-Large-Thinking scores higher for agentic tasks on the public lane, 38.3 to 16.1. MiniCPM5-1B is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, MiniCPM5-1B or Trinity-Large-Thinking?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, MiniCPM5-1B or Trinity-Large-Thinking?

Trinity-Large-Thinking has the larger documented context window: 512K, compared with 131K.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

MiniCPM5-1B
API / moNo API price on file
Self-host / mo$298
Break-even—
Trinity-Large-Thinking
API / mo$863
Self-host / mo$13,981
Break-evenNot reached at 70% load
Model the full break-even

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence19 rows

Agentic

  • BFCL v4

    MiniCPM5-1B25.1%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • τ²-bench Airline

    MiniCPM5-1B—
    Trinity-Large-Thinking88.0%
    Source

    Not directly comparable

  • Gert Labs

    MiniCPM5-1B—
    Trinity-Large-Thinking25.38%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pro

    MiniCPM5-1B22.7%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • LiveCodeBench v6

    MiniCPM5-1B33.5%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • SWE-bench Verified*

    MiniCPM5-1B—
    Trinity-Large-Thinking63.2%
    Source

    Not directly comparable

Reasoning

  • BBH

    MiniCPM5-1B71.9%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

Knowledge

  • MMLU-Pro

    MiniCPM5-1B48.9%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • MMLU-Redux

    MiniCPM5-1B70.1%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • GPQA-D

    MiniCPM5-1B26.3%
    Source
    Trinity-Large-Thinking76.3%
    Source

    Trinity-Large-Thinking leads this result

  • SuperGPQA

    MiniCPM5-1B23.1%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • MMLU-Pro (Arcee)

    MiniCPM5-1B—
    Trinity-Large-Thinking83.4%
    Source

    Not directly comparable

Instruction following

  • IFBench

    MiniCPM5-1B46.7%
    Source
    Trinity-Large-Thinking52.3%
    Source

    Trinity-Large-Thinking leads this result

  • IFEval

    MiniCPM5-1B80.4%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

Math

  • AIME 2025

    MiniCPM5-1B40.4%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • AIME26

    MiniCPM5-1B40.4%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • HMMT Feb 2026

    MiniCPM5-1B25.8%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • MATH-500

    MiniCPM5-1B91.6%
    Source
    Trinity-Large-Thinking—

    Not directly comparable

  • AIME25 (Arcee)

    MiniCPM5-1B—
    Trinity-Large-Thinking96.3%
    Source

    Not directly comparable

19 public results · 2 shared

Watch MiniCPM5-1B vs Trinity-Large-Thinking

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 21, 2026