Agentic
Like-for-like- Claude Sonnet 4.6
- 44.0
- Supported · #93/152
- Inkling-Small
- 36.9
- Supported · #128/152
- Basis
- BenchAlign lane · 9 vs 5 public rows
- Reading
- Claude Sonnet 4.6 leads · intervals overlap
Claude Sonnet 4.6 vs Inkling-Small
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Sonnet 4.6 has the higher public score estimate, 62.96 versus 59.25, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
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.
Coding work
Code generation, repair, and software-engineering tasks
Claude Sonnet 4.6
Claude Sonnet 4.6 leads on the public coding lane, 52.2 to 43.8, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Claude Sonnet 4.6
Claude Sonnet 4.6 leads on the public agentic lane, 44 to 36.9, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Inkling-Small
Inkling-Small has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Chat turn cost
1K fresh input + 500 output tokens
Inkling-Small
Inkling-Small has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Inkling-Small
Inkling-Small 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
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. Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
16 Claude Sonnet 4.6 only
10 Shared
15 Inkling-Small only
- Shared results
- 10
- Claude Sonnet 4.6 only
- 16
- Inkling-Small only
- 15
- Like-for-like categories
- 3 / 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.
Coding
Like-for-like- Claude Sonnet 4.6
- 52.2
- Supported · #48/151
- Inkling-Small
- 43.8
- Supported · #97/151
- Basis
- BenchAlign lane · 8 vs 6 public rows
- Reading
- Claude Sonnet 4.6 leads · intervals overlap
Knowledge
Like-for-like- Claude Sonnet 4.6
- 55.8
- Supported · #51/183
- Inkling-Small
- 56.5
- Supported · #46/183
- Basis
- BenchAlign lane · 6 vs 6 public rows
- Reading
- Inkling-Small leads · intervals overlap
Multimodal
Directional only- Claude Sonnet 4.6
- 54.1
- #33/48
- Inkling-Small
- 48.8
- #39/48
- Basis
- Provisional lane · 1 vs 2 weighted rows
- Reading
- Directional only
Instruction following
Directional only- Claude Sonnet 4.6
- 48.2
- #86/123
- Inkling-Small
- 89.6
- #25/123
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Sonnet 4.6
- 67.9
- Unranked · 2 rankable rows
- Inkling-Small
- 42.7
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Sonnet 4.6
- 49.0
- Unranked · 2 rankable rows
- Inkling-Small
- 76.9
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 2 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Sonnet 4.6
- Not ranked
- Inkling-Small
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Sonnet 4.6 | Inkling-Small | Basis | Reading |
|---|---|---|---|---|
| Agentic | 44.0Supported · #93/152 | 36.9Supported · #128/152 | Like-for-likeBenchAlign lane · 9 vs 5 public rows | Claude Sonnet 4.6 leads · intervals overlap |
| Coding | 52.2Supported · #48/151 | 43.8Supported · #97/151 | Like-for-likeBenchAlign lane · 8 vs 6 public rows | Claude Sonnet 4.6 leads · intervals overlap |
| Knowledge | 55.8Supported · #51/183 | 56.5Supported · #46/183 | Like-for-likeBenchAlign lane · 6 vs 6 public rows | Inkling-Small leads · intervals overlap |
| Multimodal | 54.1#33/48 | 48.8#39/48 | Directional onlyProvisional lane · 1 vs 2 weighted rows | Directional only |
| Instruction following | 48.2#86/123 | 89.6#25/123 | Directional onlyProvisional lane · 0 vs 1 weighted rows | Directional only |
| Reasoning | 67.9Unranked · 2 rankable rows | 42.7Unranked · 3 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Math | 49.0Unranked · 2 rankable rows | 76.9Unranked · 2 rankable rows | Not comparableProvisional lane · 2 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | 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.
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.
Terminal-Bench 2.0
Agentic
Claude Sonnet 4.6: 59.1%Inkling-Small: 64.7%Normalized gap 5.6Claude Sonnet 4.6 source Inkling-Small sourceCharXiv
Multimodal
Claude Sonnet 4.6: 77.4%Inkling-Small: 81.3%Normalized gap 3.9Claude Sonnet 4.6 source Inkling-Small sourceLiveCodeBench (Vals)
Coding
Claude Sonnet 4.6: 82.1%Inkling-Small: 85.9%Normalized gap 3.8Claude Sonnet 4.6 source Inkling-Small sourceMMLU-Pro (Vals)
Knowledge
Claude Sonnet 4.6: 87.3%Inkling-Small: 85.6%Normalized gap 1.7Claude Sonnet 4.6 source Inkling-Small sourceHLE
Knowledge
Claude Sonnet 4.6: 49%Inkling-Small: 47.8%Normalized gap 1.2Claude Sonnet 4.6 source Inkling-Small source
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
- Claude Sonnet 4.6
- $0.0105
- Fits in one request
- Inkling-Small
- $0.0013
- Fits in one request
Inkling-Small has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Sonnet 4.6
- $0.195
- Fits in one request
- Inkling-Small
- $0.03332
- Fits in one request
Inkling-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
- Claude Sonnet 4.6
- $0.81
- Does not fit in one request
- Cached input priced at the published list-input rate
- Inkling-Small
- $0.0492
- Fits in one request
Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 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.
SpecificationClaude Sonnet 4.6Inkling-Small
Context window
Maximum documented context; output-token limits may be lower.
Claude Sonnet 4.6
200K
Inkling-Small
1M
API model ID
Claude Sonnet 4.6
Not sourced
Inkling-Small
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Sonnet 4.6
Not published
Inkling-Small
$0.116 per 1M cached input tokens
Documented inputs
Claude Sonnet 4.6
Not sourced
Inkling-Small
Not sourced
Documented outputs
Claude Sonnet 4.6
Not sourced
Inkling-Small
Not sourced
Provider availability
Claude Sonnet 4.6
Not sourced
Inkling-Small
Not sourced
Reasoning profile
Claude Sonnet 4.6
Non-Reasoning
Inkling-Small
Hybrid
Weight access
Claude Sonnet 4.6
Proprietary
Inkling-Small
Open Weight
License
Claude Sonnet 4.6
Proprietary
Inkling-Small
Open Weight
Release date
Claude Sonnet 4.6
2026-02-01
Inkling-Small
2026-07-30
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
- Claude Sonnet 4.6 has the higher public score estimate, 62.96 versus 59.25, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.195 vs $0.03332. Cache-heavy agent loop: $0.81 vs $0.0492.
- 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 evidence41 rows
Agentic
Terminal-Bench 2.0
Claude Sonnet 4.659.1%SourceInkling-Small64.7%SourceInkling-Small leads this result
OSWorld-Verified
Claude Sonnet 4.672.1%SourceInkling-Small—Not directly comparable
Claw-Eval
Claude Sonnet 4.667.8%SourceInkling-Small—Not directly comparable
CyberGym
Claude Sonnet 4.665.2%SourceInkling-Small—Not directly comparable
Gert Labs
Claude Sonnet 4.662.92%SourceInkling-Small—Not directly comparable
OSWorld 2.0
Claude Sonnet 4.68.3%SourceInkling-Small—Not directly comparable
JobBench
Claude Sonnet 4.636.9%SourceInkling-Small—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Sonnet 4.657.3%SourceInkling-Small55.1%SourceClaude Sonnet 4.6 leads this result
ApprenticeBench
Claude Sonnet 4.62%SourceInkling-Small—Not directly comparable
BrowseComp
Claude Sonnet 4.6—Inkling-Small77.4%SourceNot directly comparable
MCP Atlas
Claude Sonnet 4.6—Inkling-Small79.6%SourceNot directly comparable
Toolathlon-Verified
Claude Sonnet 4.6—Inkling-Small54.4%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Sonnet 4.679.6%SourceInkling-Small80.2%SourceInkling-Small leads this result
SWE-Rebench
Claude Sonnet 4.660.7%SourceInkling-Small—Not directly comparable
React Native Evals
Claude Sonnet 4.680.6%SourceInkling-Small—Not directly comparable
Vibe Code Bench
Claude Sonnet 4.651.48%SourceInkling-Small—Not directly comparable
cursorBench31
Claude Sonnet 4.648.8%SourceInkling-Small—Not directly comparable
FrontierCode 1.1 Main
Claude Sonnet 4.624.3%SourceInkling-Small—Not directly comparable
LiveCodeBench (Vals)
Claude Sonnet 4.682.1%SourceInkling-Small85.9%SourceInkling-Small leads this result
SWE-bench (Vals)
Claude Sonnet 4.677.4%SourceInkling-Small82.2%SourceInkling-Small leads this result
SWE-bench Pro
Claude Sonnet 4.6—Inkling-Small55.9%SourceNot directly comparable
Terminal-Bench 2.0
Claude Sonnet 4.6—Inkling-Small64.7%SourceNot directly comparable
SciCode
Claude Sonnet 4.6—Inkling-Small48.7%SourceNot directly comparable
Reasoning
Knowledge
GPQA
Claude Sonnet 4.689.9%SourceInkling-Small89.5%SourceClaude Sonnet 4.6 leads this result
SuperGPQA
Claude Sonnet 4.695%SourceInkling-Small—Not directly comparable
MMLU-Pro
Claude Sonnet 4.679.2%SourceInkling-Small—Not directly comparable
HLE
Claude Sonnet 4.649%SourceInkling-Small47.8%SourceClaude Sonnet 4.6 leads this result
GPQA Diamond (Vals)
Claude Sonnet 4.685.6%SourceInkling-Small83.6%SourceClaude Sonnet 4.6 leads this result
MMLU-Pro (Vals)
Claude Sonnet 4.687.3%SourceInkling-Small85.6%SourceClaude Sonnet 4.6 leads this result
GPQA-D
Claude Sonnet 4.6—Inkling-Small89.5%SourceNot directly comparable
HLE w/o tools
Claude Sonnet 4.6—Inkling-Small31.6%SourceNot directly comparable
Math
FrontierMath v2 (Tiers 1-3)
Claude Sonnet 4.632.400%SourceInkling-Small—Not directly comparable
FrontierMath v2 (Tier 4)
Claude Sonnet 4.68.300%SourceInkling-Small—Not directly comparable
AIME26
Claude Sonnet 4.6—Inkling-Small95.5%SourceNot directly comparable
HMMT Feb 2026
Claude Sonnet 4.6—Inkling-Small90.2%SourceNot directly comparable
Multimodal
Instruction following
IFBench
Claude Sonnet 4.6—Inkling-Small82.2%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Sonnet 4.6 or Inkling-Small?
Claude Sonnet 4.6 has the higher public score estimate, 62.96 versus 59.25, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Sonnet 4.6 or Inkling-Small?
Claude Sonnet 4.6 leads the public coding lane, 52.2 to 43.8, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Claude Sonnet 4.6 or Inkling-Small?
Claude Sonnet 4.6 leads the public agentic tasks lane, 44 to 36.9, with Supported evidence for both models, although the 90% intervals overlap.
Which costs less, Claude Sonnet 4.6 or Inkling-Small?
For the stated presets, chat costs $0.0105 on Claude Sonnet 4.6 and $0.0013 on Inkling-Small; repository review costs $0.195 and $0.03332; the cache-heavy agent loop costs $0.81 and $0.0492. Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Sonnet 4.6 or Inkling-Small?
Inkling-Small has the larger documented context window: 1M, compared with 200K.
Related comparisons
Last updated September 10, 2026
Watch Claude Sonnet 4.6 vs Inkling-Small
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.