Long documents
Prompts that approach the documented context limit
Inkling 2 Small
Inkling 2 Small has the larger documented context window.
Confidence: documented
Command A+ vs Inkling 2 Small
Updated November 7, 2026. Rank says Inkling 2 Small is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Share or export
Decision reading
Inkling 2 Small has the higher public point estimate, 59.06 versus 29.73. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Model B
Thinking Machines Lab
59.06/100
Estimated · Public rank #56
Conditional range 44.7–73.4
- Shared results
- 1
- Command A+ only
- 4
- Inkling 2 Small only
- 24
- Like-for-like categories
- 0 / 8
Estimated: Command A+ and Inkling 2 Small. 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.
Chat turn cost
1K fresh input + 500 output tokens
Inkling 2 Small
Inkling 2 Small has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Inkling 2 Small
Inkling 2 Small has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCoding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Command A+ is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Command A+ is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limitedCache-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. Command A+ does not fit this workload in one request. Command A+ has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
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.
16.9Command A+59.7Inkling 2 Small
Directional only · BenchAlign v5.8
Inkling 2 Small has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
4 Command A+ only
1 Shared
24 Inkling 2 Small only
4 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.
CharXivMultimodal
Normalized gap 35.0Command A+:52.7%Inkling 2 Small:87.7%
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 v5.8 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- Command A+
- 14.1
- Estimated · #128/131
- Inkling 2 Small
- 59.9
- Supported · #26/131
- Basis
- BenchAlign v5.8 lane · 2 vs 5 public rows
- Reading
- Directional only
Coding
Directional only- Command A+
- 16.9
- Estimated · #145/157
- Inkling 2 Small
- 59.7
- Supported · #20/157
- Basis
- BenchAlign v5.8 lane · 0 vs 6 public rows
- Reading
- Directional only
Multimodal
Directional only- Command A+
- 32.8
- #56/59
- Inkling 2 Small
- 86.6
- #12/59
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Directional only
Knowledge
Directional only- Command A+
- 26.7
- Estimated · #167/178
- Inkling 2 Small
- 60.4
- Estimated · #46/178
- Basis
- BenchAlign v5.8 lane · 0 vs 2 public rows
- Reading
- Directional only
Reasoning
Not comparable- Command A+
- 59.5
- Unranked · 2 rankable rows
- Inkling 2 Small
- 86.1
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Command A+
- Not ranked
- Inkling 2 Small
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Command A+
- 90.7
- #26/157
- Inkling 2 Small
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Command A+
- Not ranked
- Inkling 2 Small
- 85.9
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
| Category | Command A+ | Inkling 2 Small | Basis | Reading |
|---|---|---|---|---|
| Agentic | 14.1Estimated · #128/131 | 59.9Supported · #26/131 | Directional onlyBenchAlign v5.8 lane · 2 vs 5 public rows | Directional only |
| Coding | 16.9Estimated · #145/157 | 59.7Supported · #20/157 | Directional onlyBenchAlign v5.8 lane · 0 vs 6 public rows | Directional only |
| Multimodal | 32.8#56/59 | 86.6#12/59 | Directional onlyProvisional lane · 2 vs 1 weighted rows | Directional only |
| Knowledge | 26.7Estimated · #167/178 | 60.4Estimated · #46/178 | Directional onlyBenchAlign v5.8 lane · 0 vs 2 public rows | Directional only |
| Reasoning | 59.5Unranked · 2 rankable rows | 86.1Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 90.7#26/157 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | 85.9Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. 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
- Command A+
- $0.0075
- Fits in one request
- Inkling 2 Small
- $0.0008
- Fits in one request
Inkling 2 Small has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Command A+
- $0.155
- Fits in one request
- Inkling 2 Small
- $0.018
- Fits in one request
Inkling 2 Small has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Command A+
- $0.65
- Does not fit in one request
- Cached input priced at the published list-input rate
- Inkling 2 Small
- $0.022
- Fits in one request
Command A+ does not fit this workload in one request. Command A+ has no published cached-input rate, so cached tokens use its listed input rate.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationCommand A+Inkling 2 Small
Context window
Maximum documented context; output-token limits may be lower.
Command A+
128K
Inkling 2 Small
API model ID
Command A+
Not sourced
Inkling 2 Small
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Command A+
Not published
Inkling 2 Small
$0.03 per 1M cached input tokens
Tinker models and pricingDocumented inputs
Command A+
Not sourced
Inkling 2 Small
Not sourced
Documented outputs
Command A+
Not sourced
Inkling 2 Small
Not sourced
Provider availability
Command A+
Not sourced
Inkling 2 Small
Not sourced
Reasoning profile
Command A+
Reasoning
Inkling 2 Small
Hybrid
Weight access
Command A+
Open Weight
Inkling 2 Small
Proprietary
License
Command A+
Open Weight
Inkling 2 Small
Proprietary
Release date
Command A+
2026-05-20
Inkling 2 Small
2026-11-05
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
- Inkling 2 Small has the higher public point estimate, 59.06 versus 29.73. Their conditional score ranges do not overlap. These ranges do not establish rank confidence.
- Workload cost
- Repository review: $0.155 vs $0.018. Cache-heavy agent loop: $0.65 vs $0.022.
- Context tradeoff
- Inkling 2 Small has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Command A+ or Inkling 2 Small?
Inkling 2 Small has the higher public point estimate, 59.06 versus 29.73. Their conditional score ranges do not 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, Command A+ or Inkling 2 Small?
Inkling 2 Small scores higher for coding on the public lane, 59.7 to 16.9. Command A+ is 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, Command A+ or Inkling 2 Small?
Inkling 2 Small scores higher for agentic tasks on the public lane, 59.9 to 14.1. Command A+ 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, Command A+ or Inkling 2 Small?
For the stated presets, chat costs $0.0075 on Command A+ and $0.0008 on Inkling 2 Small; repository review costs $0.155 and $0.018; the cache-heavy agent loop costs $0.65 and $0.022. Command A+ does not fit this workload in one request. Command A+ has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Command A+ or Inkling 2 Small?
Inkling 2 Small has the larger documented context window: 1M, compared with 128K.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Command A+
API / mo$9,375
Self-host / mo$6,990
Break-even49M/day
Inkling 2 Small
API / mo$975
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence29 rows
Agentic
τ²-bench results
Command A+85%SourceInkling 2 Small—Not directly comparable
Terminal-Bench 2.1 (Vals)
Command A+17.6%SourceInkling 2 Small—Not directly comparable
Terminal-Bench 2.1
Command A+—Inkling 2 Small85.1%SourceNot directly comparable
BrowseComp
Command A+—Inkling 2 Small90.2%SourceNot directly comparable
DeepSearchQA
Command A+—Inkling 2 Small90.9%SourceNot directly comparable
MCP Atlas
Command A+—Inkling 2 Small85%SourceNot directly comparable
JobBench
Command A+—Inkling 2 Small70.5%SourceNot directly comparable
Coding
SWE-bench Verified
Command A+—Inkling 2 Small82.2%SourceNot directly comparable
SWE Multilingual
Command A+—Inkling 2 Small81.2%SourceNot directly comparable
sweMarathon
Command A+—Inkling 2 Small38.8%SourceNot directly comparable
Terminal-Bench 2.1
Command A+—Inkling 2 Small85.1%SourceNot directly comparable
DeepSWE
Command A+—Inkling 2 Small72.1%SourceNot directly comparable
PostTrainBench v1.2
Command A+—Inkling 2 Small31.9%SourceNot directly comparable
Reasoning
LongBench v2
Command A+—Inkling 2 Small70.6%SourceNot directly comparable
Multimodal
MMMU
Command A+75.1%SourceInkling 2 Small—Not directly comparable
MMMU-Pro
Command A+63%SourceInkling 2 Small—Not directly comparable
CharXiv
Command A+52.7%SourceInkling 2 Small87.7%SourceInkling 2 Small leads this result
CharXiv w/o tools
Command A+—Inkling 2 Small85.6%SourceNot directly comparable
Chartography (no tools)
Command A+—Inkling 2 Small36.7%SourceNot directly comparable
Chartography (tools)
Command A+—Inkling 2 Small80.4%SourceNot directly comparable
BabyVision
Command A+—Inkling 2 Small68.6%SourceNot directly comparable
BabyVision w/ Python
Command A+—Inkling 2 Small93.7%SourceNot directly comparable
ScreenSpot Pro
Command A+—Inkling 2 Small83.8%SourceNot directly comparable
PerceptionBench
Command A+—Inkling 2 Small64.7%SourceNot directly comparable
MathVision
Command A+—Inkling 2 Small92.8%SourceNot directly comparable
Knowledge
Math
29 public results · 1 shared
Watch Command A+ vs Inkling 2 Small
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 6,100+ subscribers.
Last updated November 7, 2026