Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

Composer 2 vs Ternary Bonsai 2 27B

Decision reading

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.

0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Cursor logo
Model A
Composer 2

Cursor

—

Evidence status unavailable

90% interval unavailable

Prism ML logo
Model B
Ternary Bonsai 2 27B

Prism ML

50.78/100

Estimated · Public rank #122

90% interval 40.9–60.6

Updated September 18, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.

Share or export

Share on XLinkedInSocial cardCSVJSON

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

    Ternary Bonsai 2 27B

    Ternary Bonsai 2 27B 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

    Composer 2 and Ternary Bonsai 2 27B are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    Composer 2 and Ternary Bonsai 2 27B are 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. Composer 2 does not fit this workload in one request. Composer 2 has no published cached-input rate, so cached tokens use its listed input rate. Ternary Bonsai 2 27B 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

What is actually comparable

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

Shared results
0
Composer 2 only
5
Ternary Bonsai 2 27B only
21
Like-for-like categories
0 / 8

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

Category results, on a stated basis

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

Agentic

Directional only
Composer 2
49.3
Estimated · #63/154
Ternary Bonsai 2 27B
49.9
Estimated · #59/154
Basis
BenchAlign lane · 1 vs 3 public rows
Reading
Directional only

Coding

Directional only
Composer 2
49.3
Estimated · #67/154
Ternary Bonsai 2 27B
49.9
Estimated · #64/154
Basis
BenchAlign lane · 4 vs 4 public rows
Reading
Directional only

Reasoning

Not comparable
Composer 2
Not ranked
Ternary Bonsai 2 27B
73.9
Unranked · 1 rankable row
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Composer 2
Not ranked
Ternary Bonsai 2 27B
50.6
Estimated · #78/184
Basis
BenchAlign lane · 0 vs 3 public rows
Reading
Not comparable

Math

Not comparable
Composer 2
Not ranked
Ternary Bonsai 2 27B
76.8
Unranked · 4 rankable rows
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Composer 2
Not ranked
Ternary Bonsai 2 27B
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Composer 2
Not ranked
Ternary Bonsai 2 27B
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Composer 2
Not ranked
Ternary Bonsai 2 27B
71.0
#64/124
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

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.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

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

Composer 2
$0.00175
Fits in one request
Ternary Bonsai 2 27B
Self-hosted; infrastructure cost varies
Fits in one request

Ternary Bonsai 2 27B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Composer 2
$0.0325
Fits in one request
Ternary Bonsai 2 27B
Self-hosted; infrastructure cost varies
Fits in one request

Ternary Bonsai 2 27B has no comparable published API token rate.

Cache-heavy agent loop

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

Composer 2
$0.135
Does not fit in one request
Cached input priced at the published list-input rate
Ternary Bonsai 2 27B
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

Composer 2 does not fit this workload in one request. Composer 2 has no published cached-input rate, so cached tokens use its listed input rate. Ternary Bonsai 2 27B has no comparable published API token rate.

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.

Composer 2

200K

Ternary Bonsai 2 27B

262K

PrismML Bonsai 2 collection

Cached-input rate

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

Composer 2

Not published

Ternary Bonsai 2 27B

No comparable hosted API rate

PrismML Bonsai 2 collection

Documented inputs

Composer 2

Not sourced

Ternary Bonsai 2 27B

Not sourced

Documented outputs

Composer 2

Not sourced

Ternary Bonsai 2 27B

Not sourced

Provider availability

Composer 2

Not sourced

Ternary Bonsai 2 27B

Not sourced

Reasoning profile

Composer 2

Reasoning

Ternary Bonsai 2 27B

Reasoning

Weight access

Composer 2

Proprietary

Ternary Bonsai 2 27B

Open Weight

License

Composer 2

Proprietary

Ternary Bonsai 2 27B

Open Weight

Release date

Composer 2

2026-03-19

Ternary Bonsai 2 27B

2026-09-17

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Ternary Bonsai 2 27B has the larger documented window (262K).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

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

Browse raw public benchmark evidence26 rows

Agentic

  • Terminal-Bench 2.0

    Composer 261.7%
    Source
    Ternary Bonsai 2 27B—

    Not directly comparable

  • τ²-bench results

    Composer 2—
    Ternary Bonsai 2 27B80.2%
    Source

    Not directly comparable

  • BFCL v3

    Composer 2—
    Ternary Bonsai 2 27B74.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Composer 2—
    Ternary Bonsai 2 27B52.8%
    Source

    Not directly comparable

Coding

  • SWE Multilingual

    Composer 273.7%
    Source
    Ternary Bonsai 2 27B—

    Not directly comparable

  • SWE-Rebench

    Composer 258%
    Source
    Ternary Bonsai 2 27B—

    Not directly comparable

  • React Native Evals

    Composer 296.1%
    Source
    Ternary Bonsai 2 27B—

    Not directly comparable

  • Terminal-Bench 2.0

    Composer 261.7%
    Source
    Ternary Bonsai 2 27B—

    Not directly comparable

  • LiveCodeBench v6

    Composer 2—
    Ternary Bonsai 2 27B90.1%
    Source

    Not directly comparable

  • BigCodeBench

    Composer 2—
    Ternary Bonsai 2 27B58.1%
    Source

    Not directly comparable

  • SWE-bench Verified

    Composer 2—
    Ternary Bonsai 2 27B60.8%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Composer 2—
    Ternary Bonsai 2 27B52.8%
    Source

    Not directly comparable

Knowledge

  • MMLU-Redux

    Composer 2—
    Ternary Bonsai 2 27B89.1%
    Source

    Not directly comparable

  • GPQA

    Composer 2—
    Ternary Bonsai 2 27B85.8%
    Source

    Not directly comparable

  • GPQA-D

    Composer 2—
    Ternary Bonsai 2 27B85.8%
    Source

    Not directly comparable

Math

  • GSM8K

    Composer 2—
    Ternary Bonsai 2 27B96.7%
    Source

    Not directly comparable

  • MATH-500

    Composer 2—
    Ternary Bonsai 2 27B98.8%
    Source

    Not directly comparable

  • AIME 2025

    Composer 2—
    Ternary Bonsai 2 27B95%
    Source

    Not directly comparable

  • AIME26

    Composer 2—
    Ternary Bonsai 2 27B95.8%
    Source

    Not directly comparable

Multimodal

  • CharXiv (overall)

    Composer 2—
    Ternary Bonsai 2 27B80.0%
    Source

    Not directly comparable

  • A-OKVQA

    Composer 2—
    Ternary Bonsai 2 27B86.8%
    Source

    Not directly comparable

  • OmniDocBench 1.6

    Composer 2—
    Ternary Bonsai 2 27B89.1%
    Source

    Not directly comparable

  • RealWorldQA

    Composer 2—
    Ternary Bonsai 2 27B80.1%
    Source

    Not directly comparable

  • OCRBench V2

    Composer 2—
    Ternary Bonsai 2 27B56.9%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Composer 2—
    Ternary Bonsai 2 27B91.3%
    Source

    Not directly comparable

  • IFBench

    Composer 2—
    Ternary Bonsai 2 27B74%
    Source

    Not directly comparable

Questions

Which is better, Composer 2 or Ternary Bonsai 2 27B?

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Composer 2 or Ternary Bonsai 2 27B?

Ternary Bonsai 2 27B scores higher for coding on the public lane, 49.9 to 49.3. Composer 2 and Ternary Bonsai 2 27B are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Composer 2 or Ternary Bonsai 2 27B?

Ternary Bonsai 2 27B scores higher for agentic tasks on the public lane, 49.9 to 49.3. Composer 2 and Ternary Bonsai 2 27B are 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, Composer 2 or Ternary Bonsai 2 27B?

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, Composer 2 or Ternary Bonsai 2 27B?

Ternary Bonsai 2 27B has the larger documented context window: 262K, compared with 200K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 18, 2026

Watch Composer 2 vs Ternary Bonsai 2 27B

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

Read a sample issue

Join 2,000+ readers.