Agentic
Like-for-like- Grok 4.20
- 26.7
- Supported · #145/152
- Inkling-Small
- 36.9
- Supported · #128/152
- Basis
- BenchAlign lane · 4 vs 5 public rows
- Reading
- Inkling-Small leads · intervals overlap
Grok 4.20 vs Inkling-Small
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Grok 4.20 has the higher public score estimate, 67.13 versus 59.25, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
13 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
Inkling-Small
Inkling-Small leads on the public coding lane, 43.8 to 28.2, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Inkling-Small
Inkling-Small leads on the public agentic lane, 36.9 to 26.7, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Grok 4.20
Grok 4.20 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
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. Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
10 Grok 4.20 only
13 Shared
12 Inkling-Small only
- Shared results
- 13
- Grok 4.20 only
- 10
- Inkling-Small only
- 12
- Like-for-like categories
- 4 / 8
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- Grok 4.20
- 28.2
- Supported · #141/151
- Inkling-Small
- 43.8
- Supported · #97/151
- Basis
- BenchAlign lane · 6 vs 6 public rows
- Reading
- Inkling-Small leads · intervals overlap
Knowledge
Like-for-like- Grok 4.20
- 49.4
- Supported · #85/183
- Inkling-Small
- 56.5
- Supported · #46/183
- Basis
- BenchAlign lane · 6 vs 6 public rows
- Reading
- Inkling-Small leads · intervals overlap
Multimodal
Like-for-like- Grok 4.20
- 34.6
- #43/48
- Inkling-Small
- 48.8
- #39/48
- Basis
- Provisional lane · 2 vs 2 weighted rows
- Reading
- Inkling-Small leads
Reasoning
Not comparable- Grok 4.20
- 34.2
- Unranked · 2 rankable rows
- Inkling-Small
- 42.7
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- Grok 4.20
- Not ranked
- Inkling-Small
- 76.9
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Grok 4.20
- Not ranked
- Inkling-Small
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Grok 4.20
- Not ranked
- Inkling-Small
- 89.6
- #25/123
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
| Category | Grok 4.20 | Inkling-Small | Basis | Reading |
|---|---|---|---|---|
| Agentic | 26.7Supported · #145/152 | 36.9Supported · #128/152 | Like-for-likeBenchAlign lane · 4 vs 5 public rows | Inkling-Small leads · intervals overlap |
| Coding | 28.2Supported · #141/151 | 43.8Supported · #97/151 | Like-for-likeBenchAlign lane · 6 vs 6 public rows | Inkling-Small leads · intervals overlap |
| Knowledge | 49.4Supported · #85/183 | 56.5Supported · #46/183 | Like-for-likeBenchAlign lane · 6 vs 6 public rows | Inkling-Small leads · intervals overlap |
| Multimodal | 34.6#43/48 | 48.8#39/48 | Like-for-likeProvisional lane · 2 vs 2 weighted rows | Inkling-Small leads |
| Reasoning | 34.2Unranked · 2 rankable rows | 42.7Unranked · 3 rankable rows | Not comparableProvisional lane · 2 vs 1 weighted rows | Not comparable |
| Math | Not ranked | 76.9Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 89.6#25/123 | 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) 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.
CharXiv
Multimodal
Terminal-Bench 2.0
Agentic
ARC-AGI-2
Reasoning
SWE-bench Pro
Coding
SWE-bench Verified
Coding
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
- Grok 4.20
- $0.005
- 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
- Grok 4.20
- $0.118
- 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
- Grok 4.20
- $0.5
- Fits in one request
- Cached input priced at the published list-input rate
- Inkling-Small
- $0.0492
- Fits in one request
Inkling-Small has the lower modeled cost
Grok 4.20 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.
SpecificationGrok 4.20Inkling-Small
Context window
Maximum documented context; output-token limits may be lower.
Grok 4.20
2M
Inkling-Small
1M
API model ID
Grok 4.20
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.
Grok 4.20
Not published
Inkling-Small
$0.116 per 1M cached input tokens
Documented inputs
Grok 4.20
Not sourced
Inkling-Small
Not sourced
Documented outputs
Grok 4.20
Not sourced
Inkling-Small
Not sourced
Provider availability
Grok 4.20
Not sourced
Inkling-Small
Not sourced
Reasoning profile
Grok 4.20
Reasoning
Inkling-Small
Hybrid
Weight access
Grok 4.20
Proprietary
Inkling-Small
Open Weight
License
Grok 4.20
Proprietary
Inkling-Small
Open Weight
Release date
Grok 4.20
2026-03-10
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
- Grok 4.20 has the higher public score estimate, 67.13 versus 59.25, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.118 vs $0.03332. Cache-heavy agent loop: $0.5 vs $0.0492.
- Context tradeoff
- Grok 4.20 has the larger documented window (2M).
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 evidence35 rows
Agentic
Terminal-Bench 2.0
Grok 4.2047.1%SourceInkling-Small64.7%SourceInkling-Small leads this result
DeepSearchQA
Grok 4.2062.8%SourceInkling-Small—Not directly comparable
Gert Labs
Grok 4.2038.36%SourceInkling-Small—Not directly comparable
Terminal-Bench 2.1 (Vals)
Grok 4.2044.2%SourceInkling-Small55.1%SourceInkling-Small leads this result
BrowseComp
Grok 4.20—Inkling-Small77.4%SourceNot directly comparable
MCP Atlas
Grok 4.20—Inkling-Small79.6%SourceNot directly comparable
Toolathlon-Verified
Grok 4.20—Inkling-Small54.4%SourceNot directly comparable
Coding
LiveCodeBench Pro
Grok 4.2074.2%SourceInkling-Small—Not directly comparable
SWE-bench Verified
Grok 4.2076.7%SourceInkling-Small80.2%SourceInkling-Small leads this result
SWE-bench Pro
Grok 4.2051.8%SourceInkling-Small55.9%SourceInkling-Small leads this result
Vibe Code Bench
Grok 4.204.06%SourceInkling-Small—Not directly comparable
LiveCodeBench (Vals)
Grok 4.2084.3%SourceInkling-Small85.9%SourceInkling-Small leads this result
SWE-bench (Vals)
Grok 4.2072.2%SourceInkling-Small82.2%SourceInkling-Small leads this result
Terminal-Bench 2.0
Grok 4.20—Inkling-Small64.7%SourceNot directly comparable
SciCode
Grok 4.20—Inkling-Small48.7%SourceNot directly comparable
Reasoning
Knowledge
GPQA-D
Grok 4.2088.5%SourceInkling-Small89.5%SourceInkling-Small leads this result
HLE w/o tools
Grok 4.2031.6%SourceInkling-Small31.6%SourceTie
HealthBench Hard
Grok 4.2020.3%SourceInkling-Small—Not directly comparable
MedXpertQA (Text)
Grok 4.2050.2%SourceInkling-Small—Not directly comparable
GPQA Diamond (Vals)
Grok 4.2088.6%SourceInkling-Small83.6%SourceGrok 4.20 leads this result
MMLU-Pro (Vals)
Grok 4.2086.3%SourceInkling-Small85.6%SourceGrok 4.20 leads this result
GPQA
Grok 4.20—Inkling-Small89.5%SourceNot directly comparable
HLE
Grok 4.20—Inkling-Small47.8%SourceNot directly comparable
Math
Multimodal
MMMU-Pro
Grok 4.2075.2%SourceInkling-Small74%SourceGrok 4.20 leads this result
CharXiv
Grok 4.2060.9%SourceInkling-Small81.3%SourceInkling-Small leads this result
ERQA
Grok 4.2054.1%SourceInkling-Small—Not directly comparable
SimpleVQA
Grok 4.2057.4%SourceInkling-Small—Not directly comparable
MedXpertQA (MM)
Grok 4.2065.8%SourceInkling-Small—Not directly comparable
CharXiv w/o tools
Grok 4.20—Inkling-Small77.4%SourceNot directly comparable
Instruction following
IFBench
Grok 4.20—Inkling-Small82.2%SourceNot directly comparable
Frequently asked questions
Which is better, Grok 4.20 or Inkling-Small?
Grok 4.20 has the higher public score estimate, 67.13 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, Grok 4.20 or Inkling-Small?
Inkling-Small leads the public coding lane, 43.8 to 28.2, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Grok 4.20 or Inkling-Small?
Inkling-Small leads the public agentic tasks lane, 36.9 to 26.7, with Supported evidence for both models, although the 90% intervals overlap.
Which costs less, Grok 4.20 or Inkling-Small?
For the stated presets, chat costs $0.005 on Grok 4.20 and $0.0013 on Inkling-Small; repository review costs $0.118 and $0.03332; the cache-heavy agent loop costs $0.5 and $0.0492. Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Grok 4.20 or Inkling-Small?
Grok 4.20 has the larger documented context window: 2M, compared with 1M.
Related comparisons
Last updated September 10, 2026
Watch Grok 4.20 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.