Compare
A.X K2 vs Claude Fable 5
A.X K2 (SK Telecom) and Claude Fable 5 (Anthropic) compared on benchmarks, pricing, context window, and use-case rankings.
- Claude Fable 5 ranks higher for coding (96th vs 30th percentile).
| Attribute | A.X K2 | Claude Fable 5 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | — | 163 |
| Coding | 30 | 96 |
| Math | — | 96 |
| Reasoning & Knowledge | 48 | 89 |
| Agentic & Tools | — | 96 |
| Specifications | ||
| Developer | SK Telecom | Anthropic |
| Family | — | Claude |
| Released | Jul 29, 2026 | Jun 9, 2026 |
| Parameters | 688B | — |
| Availability | Open weights (unrestricted) | API access |
| Context window | — | 1M |
| Price — $/M input | — | $10.00 |
| Price — $/M output | — | $50.00 |
| Inputs | — | text, image, file |
| Outputs | — | text |
| Benchmarks | ||
| GPQA Diamond | 86% | 86% |
| Humanity's Last Exam | 30% | 56% |
| SciCode | 41% | 61% |
| AIME 2024/2025 | — | 100% |
| APEX | — | 45% |
| ARC-AGI | — | 99% |
| ARC-AGI-2 | — | 89% |
| SimpleBench | — | 82% |
| SimpleQA Verified | — | 71% |
| WebDev Arena | — | 1626 |
| WeirdML | — | 92% |
| τ²-bench | — | 99% |
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 Claude Fable 5?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Claude Fable 5 ranks higher — 96th 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.