Coding
Like-for-like- Granite 4.2 8B
- 36.5
- Inkling-Small
- 62.4
- Weighted basis
- 3 vs 3 rows
- Reading
- Inkling-Small leads
Granite 4.2 8B vs Inkling-Small
Updated August 31, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Inkling-Small has the higher public score, 64.21 versus 46.88, and the 90% score intervals do not overlap.
5 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.
Coding work
Code generation, repair, and software-engineering tasks
Inkling-Small
Inkling-Small leads on the same 3 weighted benchmark rows.
Confidence: stronger
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
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
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. Granite 4.2 8B does not fit this workload in one request. Granite 4.2 8B has no comparable published API token rate.
Confidence: listed-rates
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.
9 Granite 4.2 8B only
5 Shared
15 Inkling-Small only
- Shared results
- 5
- Granite 4.2 8B only
- 9
- Inkling-Small only
- 15
- Like-for-like categories
- 2 / 8
1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
Instruction following
Like-for-like- Granite 4.2 8B
- 79.3
- Inkling-Small
- 82.2
- Weighted basis
- 1 vs 1 rows
- Reading
- Inkling-Small leads
Knowledge
Directional only- Granite 4.2 8B
- 72.2
- Inkling-Small
- 53.4
- Weighted basis
- 2 vs 2 rows
- Reading
- Directional only
Agentic
Not comparable- Granite 4.2 8B
- Not measured
- Inkling-Small
- 70.1
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Reasoning
Not comparable- Granite 4.2 8B
- Not measured
- Inkling-Small
- 40.1
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- Granite 4.2 8B
- Not measured
- Inkling-Small
- 92.9
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Multilingual
Not comparable- Granite 4.2 8B
- Not measured
- Inkling-Small
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Granite 4.2 8B
- Not measured
- Inkling-Small
- 76.6
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
| Category | Granite 4.2 8B | Inkling-Small | Weighted basis | Reading |
|---|---|---|---|---|
| Coding | 36.5 | 62.4 | Like-for-like3 vs 3 rows | Inkling-Small leads |
| Instruction following | 79.3 | 82.2 | Like-for-like1 vs 1 rows | Inkling-Small leads |
| Knowledge | 72.2 | 53.4 | Directional only2 vs 2 rows | Directional only |
| Agentic | Not measured | 70.1 | Not comparable0 vs 2 rows | Not comparable |
| Reasoning | Not measured | 40.1 | Not comparable0 vs 1 rows | Not comparable |
| Math | Not measured | 92.9 | Not comparable0 vs 2 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | 76.6 | Not comparable0 vs 2 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.
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.
SWE-bench Pro
Coding
Granite 4.2 8B: 19.1%Inkling-Small: 55.9%Normalized gap 36.8Granite 4.2 8B source Inkling-Small sourceSWE-bench Verified
Coding
Granite 4.2 8B: 47.7%Inkling-Small: 80.2%Normalized gap 32.5Granite 4.2 8B source Inkling-Small sourceGPQA
Knowledge
Granite 4.2 8B: 64.1%Inkling-Small: 89.5%Normalized gap 25.4Granite 4.2 8B source Inkling-Small sourceSciCode
Coding
Granite 4.2 8B: 36.1%Inkling-Small: 48.7%Normalized gap 12.6Granite 4.2 8B source Inkling-Small sourceIFBench
Instruction following
Granite 4.2 8B: 79.3%Inkling-Small: 82.2%Normalized gap 2.9Granite 4.2 8B 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
- Granite 4.2 8B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Inkling-Small
- $0.0013
- Fits in one request
Granite 4.2 8B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Granite 4.2 8B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Inkling-Small
- $0.03332
- Fits in one request
Granite 4.2 8B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Granite 4.2 8B
- Self-hosted; infrastructure cost varies
- Does not fit in one request
- Cached-input rate unavailable
- Inkling-Small
- $0.0492
- Fits in one request
Granite 4.2 8B does not fit this workload in one request. Granite 4.2 8B 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.
SpecificationGranite 4.2 8BInkling-Small
Context window
Maximum documented context; output-token limits may be lower.
Granite 4.2 8B
Inkling-Small
1M
API model ID
Granite 4.2 8B
ibm-granite/granite-4.2-8b
IBM Granite 4.2 8B model cardInkling-Small
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Granite 4.2 8B
No comparable hosted API rate
IBM Granite 4.2 8B model cardInkling-Small
$0.116 per 1M cached input tokens
Documented inputs
Granite 4.2 8B
Not sourced
Inkling-Small
Not sourced
Documented outputs
Granite 4.2 8B
Not sourced
Inkling-Small
Not sourced
Provider availability
Granite 4.2 8B
Not sourced
Inkling-Small
Not sourced
Reasoning profile
Granite 4.2 8B
Reasoning
Inkling-Small
Hybrid
Weight access
Granite 4.2 8B
Open Weight
Inkling-Small
Open Weight
License
Granite 4.2 8B
Open Weight
Inkling-Small
Open Weight
Release date
Granite 4.2 8B
2026-08-25
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
- Inkling-Small has the higher public score, 64.21 versus 46.88, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- 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 evidence29 rows
Agentic
Terminal-Bench 2.1
Granite 4.2 8B20.6%SourceInkling-Small—Not directly comparable
τ³-bench results
Granite 4.2 8B58.1%SourceInkling-Small—Not directly comparable
BFCL v4
Granite 4.2 8B52.4%SourceInkling-Small—Not directly comparable
Terminal-Bench 2.0
Granite 4.2 8B—Inkling-Small64.7%SourceNot directly comparable
BrowseComp
Granite 4.2 8B—Inkling-Small77.4%SourceNot directly comparable
MCP Atlas
Granite 4.2 8B—Inkling-Small79.6%SourceNot directly comparable
Toolathlon-Verified
Granite 4.2 8B—Inkling-Small54.4%SourceNot directly comparable
Coding
SWE-bench Verified
Granite 4.2 8B47.7%SourceInkling-Small80.2%SourceInkling-Small leads this result
SWE-bench Pro
Granite 4.2 8B19.1%SourceInkling-Small55.9%SourceInkling-Small leads this result
SWE Multilingual
Granite 4.2 8B30.8%SourceInkling-Small—Not directly comparable
Terminal-Bench 2.1
Granite 4.2 8B20.6%SourceInkling-Small—Not directly comparable
LiveCodeBench v6
Granite 4.2 8B73.2%SourceInkling-Small—Not directly comparable
SciCode
Granite 4.2 8B36.1%SourceInkling-Small48.7%SourceInkling-Small leads this result
Terminal-Bench 2.0
Granite 4.2 8B—Inkling-Small64.7%SourceNot directly comparable
Reasoning
Knowledge
GPQA
Granite 4.2 8B64.1%SourceInkling-Small89.5%SourceInkling-Small leads this result
MMLU-Pro
Granite 4.2 8B74.0%SourceInkling-Small—Not directly comparable
GPQA-D
Granite 4.2 8B—Inkling-Small89.5%SourceNot directly comparable
HLE
Granite 4.2 8B—Inkling-Small47.8%SourceNot directly comparable
HLE w/o tools
Granite 4.2 8B—Inkling-Small31.6%SourceNot directly comparable
Math
Multimodal
Instruction following
Frequently asked questions
Which is better, Granite 4.2 8B or Inkling-Small?
Inkling-Small has the higher public score, 64.21 versus 46.88, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Granite 4.2 8B or Inkling-Small?
Inkling-Small leads the like-for-like coding comparison across 3 shared weighted benchmark rows.
Which is better for agentic tasks, Granite 4.2 8B or Inkling-Small?
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, Granite 4.2 8B or Inkling-Small?
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, Granite 4.2 8B or Inkling-Small?
Inkling-Small has the larger documented context window: 1M, compared with 128K.
Related comparisons
Last updated August 31, 2026
Watch Granite 4.2 8B 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.