Agentic
Not comparable- Inkling-Small
- 70.1
- Trinity-Large-Preview
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Model comparison
Inkling-Small vs Trinity-Large-Preview
Updated July 30, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
1 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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
Inkling-Small
Inkling-Small has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Trinity-Large-Preview
Trinity-Large-Preview has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Inkling-Small
Inkling-Small has the lower estimated token cost for this stated workload. Trinity-Large-Preview has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Trinity-Large-Preview
Trinity-Large-Preview has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
19 Inkling-Small only
1 Shared
3 Trinity-Large-Preview only
- Shared results
- 1
- Inkling-Small only
- 19
- Trinity-Large-Preview only
- 3
- Like-for-like categories
- 0 / 8
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Coding
Not comparable- Inkling-Small
- 62.4
- Trinity-Large-Preview
- Not measured
- Weighted basis
- 3 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Inkling-Small
- 40.1
- Trinity-Large-Preview
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Inkling-Small
- 53.4
- Trinity-Large-Preview
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Inkling-Small
- 92.9
- Trinity-Large-Preview
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Inkling-Small
- Not measured
- Trinity-Large-Preview
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Inkling-Small
- 76.6
- Trinity-Large-Preview
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Inkling-Small
- 82.2
- Trinity-Large-Preview
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
| Category | Inkling-Small | Trinity-Large-Preview | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 70.1 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Coding | 62.4 | Not measured | Not comparable3 vs 0 rows | Not comparable |
| Reasoning | 40.1 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Knowledge | 53.4 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Math | 92.9 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 76.6 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Instruction following | 82.2 | Not measured | Not comparable1 vs 0 rows | Not comparable |
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
- Inkling-Small
- $0.0013
- Fits in one request
- Trinity-Large-Preview
- $0.00075
- Fits in one request
Trinity-Large-Preview has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Inkling-Small
- $0.03332
- Fits in one request
- Trinity-Large-Preview
- $0.0155
- Fits in one request
Trinity-Large-Preview has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Inkling-Small
- $0.0492
- Fits in one request
- Trinity-Large-Preview
- $0.065
- Fits in one request
- Cached input priced at the published list-input rate
Inkling-Small has the lower modeled cost
Trinity-Large-Preview has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationInkling-SmallTrinity-Large-Preview
Context window
Maximum documented context; output-token limits may be lower.
Inkling-Small
1M
Trinity-Large-Preview
512K
API model ID
Inkling-Small
Not sourced
Trinity-Large-Preview
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Inkling-Small
$0.116 per 1M cached input tokens
Trinity-Large-Preview
Not published
Documented inputs
Inkling-Small
Not sourced
Trinity-Large-Preview
Not sourced
Documented outputs
Inkling-Small
Not sourced
Trinity-Large-Preview
Not sourced
Provider availability
Inkling-Small
Not sourced
Trinity-Large-Preview
Not sourced
Reasoning profile
Inkling-Small
Hybrid
Trinity-Large-Preview
Non-Reasoning
Weight access
Inkling-Small
Open Weight
Trinity-Large-Preview
Open Weight
License
Inkling-Small
Open Weight
Trinity-Large-Preview
Open Weight
Release date
Inkling-Small
2026-07-30
Trinity-Large-Preview
2026-01-27
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
- At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
- Workload cost
- Repository review: $0.03332 vs $0.0155. Cache-heavy agent loop: $0.0492 vs $0.065.
- Context tradeoff
- Inkling-Small has the larger documented window (1M).
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 evidence23 rows
Agentic
Terminal-Bench 2.0
Inkling-Small64.7%SourceTrinity-Large-Preview—Not directly comparable
BrowseComp
Inkling-Small77.4%SourceTrinity-Large-Preview—Not directly comparable
MCP Atlas
Inkling-Small79.6%SourceTrinity-Large-Preview—Not directly comparable
Toolathlon-Verified
Inkling-Small54.4%SourceTrinity-Large-Preview—Not directly comparable
Coding
SWE-bench Verified
Inkling-Small80.2%SourceTrinity-Large-Preview—Not directly comparable
SWE-bench Pro
Inkling-Small55.9%SourceTrinity-Large-Preview—Not directly comparable
Terminal-Bench 2.0
Inkling-Small64.7%SourceTrinity-Large-Preview—Not directly comparable
SciCode
Inkling-Small48.7%SourceTrinity-Large-Preview—Not directly comparable
Reasoning
Knowledge
GPQA
Inkling-Small89.5%SourceTrinity-Large-Preview—Not directly comparable
GPQA-D
Inkling-Small89.5%SourceTrinity-Large-Preview63.3%SourceInkling-Small leads this result
HLE
Inkling-Small47.8%SourceTrinity-Large-Preview—Not directly comparable
HLE w/o tools
Inkling-Small31.6%SourceTrinity-Large-Preview—Not directly comparable
MMLU
Inkling-Small—Trinity-Large-Preview87.2%SourceNot directly comparable
MMLU-Pro (Arcee)
Inkling-Small—Trinity-Large-Preview75.2%SourceNot directly comparable
Math
Multimodal
Instruction following
IFBench
Inkling-Small82.2%SourceTrinity-Large-Preview—Not directly comparable
Frequently asked questions
Which is better, Inkling-Small or Trinity-Large-Preview?
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Inkling-Small or Trinity-Large-Preview?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, Inkling-Small or Trinity-Large-Preview?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Inkling-Small or Trinity-Large-Preview?
For the stated presets, chat costs $0.0013 on Inkling-Small and $0.00075 on Trinity-Large-Preview; repository review costs $0.03332 and $0.0155; the cache-heavy agent loop costs $0.0492 and $0.065. Trinity-Large-Preview has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Inkling-Small or Trinity-Large-Preview?
Inkling-Small has the larger documented context window: 1M, compared with 512K.
Related comparisons
Last updated July 30, 2026
Watch Inkling-Small vs Trinity-Large-Preview
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.