Compare
A.X K2 vs DeepSeek-V4-Pro-0813
A.X K2 (SK Telecom) and DeepSeek-V4-Pro-0813 (DeepSeek) compared on benchmarks, pricing, context window, and use-case rankings.
- DeepSeek-V4-Pro-0813 ranks higher for coding (78th vs 30th percentile).
| Attribute | A.X K2 | DeepSeek-V4-Pro-0813 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | — | 155 |
| Coding | 30 | 78 |
| Math | — | 88 |
| Reasoning & Knowledge | 47 | 69 |
| Agentic & Tools | — | — |
| Specifications | ||
| Developer | SK Telecom | DeepSeek |
| Family | — | DeepSeek |
| Released | Jul 29, 2026 | Aug 13, 2026 |
| Parameters | 688B | 1.6T |
| Availability | Open weights (unrestricted) | Open weights (unrestricted) |
| Context window | — | 1M |
| Price — $/M input | — | $0.58 |
| Price — $/M output | — | $1.74 |
| Inputs | — | text |
| Outputs | — | text |
| Benchmarks | ||
| GPQA Diamond | 86% | 92% |
| Humanity's Last Exam | 30% | 41% |
| SciCode | 41% | 51% |
| AIME 2024/2025 | — | 99% |
| ARC-AGI | — | 91% |
| ARC-AGI-2 | — | 61% |
| SimpleQA Verified | — | 53% |
| WebDev Arena | — | 1582 |
| WeirdML | — | 66% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Which is better for coding, A.X K2 or DeepSeek-V4-Pro-0813?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, DeepSeek-V4-Pro-0813 ranks higher — 78th vs 30th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.