GPQA DiamondVerified
85.7%
GPQA Diamond (AA run)
Models / Other
A.X-K2
A.X · Released 2026-08-12
SK Telecom's A.X-K2 open agentic MoE. AA lists $0 / $0 per 1M tokens.
Korean sovereign-model lane on Artificial Analysis. Prefer sourced ledger rows over launch claims.
Composite53
ContextUnlisted
Input / 1MFree
Output / 1MFree
Knowledge cutoffunpublished
Statussolid
Family profile
Best published score in each covered benchmark family.
59/100 avg
- Reasoning
- 86
- Coding
- 41
- Agentic
- 39
- Long context
- 70
4 tested benchmark families
Editor's note
SK Telecom is the AA creator. Editorial depth still needs a desk pass.Benchmark placements
Per-benchmark positions
Where A.X-K2 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| SciCode | Coding | #80/ 97 | 41 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #84/ 186 | 30 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #89/ 184 | 86 | Artificial Analysis | 2026-09-28 |
| Terminal-Bench | Agentic | #103/ 167 | 39 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #122/ 184 | 70 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #146/ 195 | Artificial Analysis | 2026-09-28 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where A.X-K2 shows up, it's highlighted.
ReasoningA.X-K2 · 86
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingA.X-K2 · 41
- 174
- 273
- 370
AgenticA.X-K2 · 39
- 191
- 289
- 389
Long contextA.X-K2 · 70
- 189
- 286
- 385
Newest receipts
6 recentLast 120 days
Benchmark rows added to the public ledger for A.X-K2 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA-LCR | Long context | 70% | Artificial Analysis | 24 |
| AA output speed | Performance | 0 t/s | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 85.7% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 29.6% | Artificial Analysis | 24 |
| SciCode | Coding | 41% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 38.95% | Artificial Analysis | 24 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where A.X-K2 sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for A.X-K2. Scores link to the original source; gaps mean no public row exists yet.
6 of 13 catalog benchmarks have a sourced row for A.X-K2.
Reasoning
Humanity's Last ExamVerified
29.6%
HLE (AA run)
Coding
SciCodeVerified
41%
SciCode (AA run)
Agentic
Terminal-BenchVerified
38.95%
Terminal-Bench v2.1 (AA run)
Long context
AA-LCRVerified
70%
AA-LCR (AA run)
Performance
AA output speedVerified
0 t/s
Median output tokens/s (1k prompt, default provider)
Sources
Where the numbers come from
- Artificial Analysis A.X-K2· checked 2026-08-15
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is A.X-K2?
A.X-K2 is a Other model: SK Telecom's A.X-K2 open agentic MoE. AA lists $0 / $0 per 1M tokens.
What is A.X-K2 for?
Korean sovereign-model lane on Artificial Analysis. Prefer sourced ledger rows over launch claims.
What does A.X-K2 cost?
A.X-K2 lists Free input and Free output per 1M tokens. Pricing last checked 2026-08-15.
How large is the A.X-K2 context window?
A.X-K2 does not publish a context window on the sources checked for this page.
What is the VerdictPal status of A.X-K2?
A.X-K2 carries Solid status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.