Compare
A.X K2 vs GPT-6 Astra
A.X K2 (SK Telecom) and GPT-6 Astra (OpenAI) compared on benchmarks, pricing, context window, and use-case rankings.
- GPT-6 Astra ranks higher for coding (95th vs 30th percentile).
| Attribute | A.X K2 | GPT-6 Astra |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | — | 169 |
| Coding | 30 | 95 |
| Math | — | 96 |
| Reasoning & Knowledge | 47 | 99 |
| Agentic & Tools | — | 96 |
| Specifications | ||
| Developer | SK Telecom | OpenAI |
| Family | — | GPT |
| Released | Jul 29, 2026 | Sep 3, 2026 |
| Parameters | 688B | — |
| Availability | Open weights (unrestricted) | API access |
| Context window | — | 1.1M |
| Price — $/M input | — | $10.00 |
| Price — $/M output | — | $50.00 |
| Inputs | — | file, image, text |
| Outputs | — | text |
| Benchmarks | ||
| GPQA Diamond | 86% | 96% |
| Humanity's Last Exam | 30% | 55% |
| SciCode | 41% | 56% |
| AIME 2024/2025 | — | 100% |
| APEX | — | 47% |
| ARC-AGI | — | 99% |
| ARC-AGI-2 | — | 95% |
| SimpleQA Verified | — | 76% |
| WebDev Arena | — | 1797 |
| WeirdML | — | 93% |
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 GPT-6 Astra?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, GPT-6 Astra ranks higher — 95th 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.