Agentic
Not comparable- A.X K2
- Not ranked
- dots3-note Preview
- 59.3
- Estimated · #25/152
- Basis
- BenchAlign lane · 1 vs 9 public rows
- Reading
- Not comparable
A.X K2 vs dots3-note Preview
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
5 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.
Long documents
Prompts that approach the documented context limit
dots3-note Preview
dots3-note Preview has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
A.X K2 is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
A.X K2 is not ranked on the public lane for agentic, so no winner is named for agentic.
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
A complete comparable API-rate estimate is not available for both models.
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.
5 A.X K2 only
5 Shared
26 dots3-note Preview only
- Shared results
- 5
- A.X K2 only
- 5
- dots3-note Preview only
- 26
- Like-for-like categories
- 0 / 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
Not comparable- A.X K2
- Not ranked
- dots3-note Preview
- 57.2
- Estimated · #34/151
- Basis
- BenchAlign lane · 3 vs 7 public rows
- Reading
- Not comparable
Reasoning
Not comparable- A.X K2
- Not ranked
- dots3-note Preview
- 68.3
- Unranked · 1 rankable row
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- A.X K2
- Not ranked
- dots3-note Preview
- 57.9
- Estimated · #42/183
- Basis
- BenchAlign lane · 2 vs 1 public rows
- Reading
- Not comparable
Math
Not comparable- A.X K2
- Not ranked
- dots3-note Preview
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- A.X K2
- Not ranked
- dots3-note Preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- A.X K2
- Not ranked
- dots3-note Preview
- 66.1
- Unranked · 10 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- A.X K2
- Not ranked
- dots3-note Preview
- 86.3
- #38/123
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Not comparable
| Category | A.X K2 | dots3-note Preview | Basis | Reading |
|---|---|---|---|---|
| Agentic | Not ranked | 59.3Estimated · #25/152 | Not comparableBenchAlign lane · 1 vs 9 public rows | Not comparable |
| Coding | Not ranked | 57.2Estimated · #34/151 | Not comparableBenchAlign lane · 3 vs 7 public rows | Not comparable |
| Reasoning | Not ranked | 68.3Unranked · 1 rankable row | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Knowledge | Not ranked | 57.9Estimated · #42/183 | Not comparableBenchAlign lane · 2 vs 1 public rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 66.1Unranked · 10 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Instruction following | Not ranked | 86.3#38/123 | Not comparableProvisional lane · 1 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.
HLE
Knowledge
IFBench
Instruction following
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
- A.X K2
- Self-hosted; infrastructure cost varies
- Fits in one request
- dots3-note Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
A.X K2 has no comparable published API token rate. dots3-note Preview has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- A.X K2
- Self-hosted; infrastructure cost varies
- Fits in one request
- dots3-note Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
A.X K2 has no comparable published API token rate. dots3-note Preview has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- A.X K2
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
- dots3-note Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
A.X K2 has no comparable published API token rate. dots3-note Preview 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.
SpecificationA.X K2dots3-note Preview
Context window
Maximum documented context; output-token limits may be lower.
A.X K2
dots3-note Preview
API model ID
A.X K2
skt/A.X-K2
SK Telecom A.X K2 model carddots3-note Preview
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
A.X K2
No comparable hosted API rate
SK Telecom A.X K2 model carddots3-note Preview
No comparable hosted API rate
dots3-note Preview model cardDocumented inputs
A.X K2
Not sourced
dots3-note Preview
Not sourced
Documented outputs
A.X K2
Not sourced
dots3-note Preview
Not sourced
Provider availability
A.X K2
Not sourced
dots3-note Preview
Not sourced
Reasoning profile
A.X K2
Reasoning
dots3-note Preview
Reasoning
Weight access
A.X K2
Open Weight
dots3-note Preview
Open Weight
License
A.X K2
Open Weight
dots3-note Preview
Open Weight
Release date
A.X K2
2026-07-29
dots3-note Preview
2026-08-14
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
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- dots3-note Preview has the larger documented window (512K).
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 evidence36 rows
Agentic
Terminal-Bench 2.1
A.X K236.0%Sourcedots3-note Preview75.1%Sourcedots3-note Preview leads this result
Claw-Eval
A.X K2—dots3-note Preview73.4%SourceNot directly comparable
Toolathlon-Verified
A.X K2—dots3-note Preview55.6%SourceNot directly comparable
skillsBench
A.X K2—dots3-note Preview52.8%SourceNot directly comparable
APEX-Agents
A.X K2—dots3-note Preview30.8%SourceNot directly comparable
BrowseComp
A.X K2—dots3-note Preview83.3%SourceNot directly comparable
HLE w/ tools
A.X K2—dots3-note Preview52.6%SourceNot directly comparable
DeepSearchQA
A.X K2—dots3-note Preview92.1%SourceNot directly comparable
WideResearch
A.X K2—dots3-note Preview78.9%SourceNot directly comparable
Coding
LiveCodeBench v6
A.X K284.0%Sourcedots3-note Preview91.5%Sourcedots3-note Preview leads this result
SciCode
A.X K241%Sourcedots3-note Preview—Not directly comparable
Terminal-Bench 2.1
A.X K236.0%Sourcedots3-note Preview75.1%Sourcedots3-note Preview leads this result
Codeforces
A.X K2—dots3-note Preview3056.0SourceNot directly comparable
SWE-bench Verified
A.X K2—dots3-note Preview78.4%SourceNot directly comparable
SWE Multilingual
A.X K2—dots3-note Preview75.7%SourceNot directly comparable
SWE-bench Pro
A.X K2—dots3-note Preview61%SourceNot directly comparable
NL2Repo
A.X K2—dots3-note Preview49.8%SourceNot directly comparable
Reasoning
ARC-AGI-2
A.X K2—dots3-note Preview81.4%SourceNot directly comparable
Knowledge
Math
Multimodal
SimpleVQA
A.X K2—dots3-note Preview72.5%SourceNot directly comparable
MMMU-Pro
A.X K2—dots3-note Preview79.1%SourceNot directly comparable
MathVision
A.X K2—dots3-note Preview87.7%SourceNot directly comparable
ZeroBench
A.X K2—dots3-note Preview19.0%SourceNot directly comparable
CharXiv w/o tools
A.X K2—dots3-note Preview83.1%SourceNot directly comparable
GDP.pdf (no tools)
A.X K2—dots3-note Preview60.7%SourceNot directly comparable
PerceptionBench
A.X K2—dots3-note Preview53.4%SourceNot directly comparable
BabyVision
A.X K2—dots3-note Preview50.0%SourceNot directly comparable
MMVU
A.X K2—dots3-note Preview79.9%SourceNot directly comparable
VideoMMMU
A.X K2—dots3-note Preview86.8%SourceNot directly comparable
Instruction following
Frequently asked questions
Which is better, A.X K2 or dots3-note 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, A.X K2 or dots3-note Preview?
A.X K2 is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, A.X K2 or dots3-note Preview?
A.X K2 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, A.X K2 or dots3-note Preview?
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, A.X K2 or dots3-note Preview?
dots3-note Preview has the larger documented context window: 512K, compared with 262K.
Related comparisons
Last updated September 10, 2026
Watch A.X K2 vs dots3-note Preview
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.