Updated daily at 05:00 UTC
- Released
- Dec 2025
- Status
- Legacy
- Context
- 131.1K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- apache-2.0
- Parameters
- 519B, 33B active
- Knowledge cutoff
- —
- Reasoning
- Yes
- Modalities
- text → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
Not enough independent results yet
Only independent and third-party results rank a model; self-reported and unattributed numbers never do.
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Humanity's Last Exam (HLE) | Accuracy | 8.6% | Self-reported | — | — | A.X K1 model card via Hugging Face Community Evals |
| MMLU-Pro | Accuracy | 81.5% | Self-reported | — | — | A.X K1 model card via Hugging Face Community Evals |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 74.0% | Self-reported | — | — | A.X K1 model card via Hugging Face Community Evals |
Other A.X versions
- A.X K2Jul 2026
- A.X 3.1Jul 2025
- A.X 3.1 LightJul 2025
- A.X 4.0Jul 2025
- A.X 4.0 LightJul 2025
- A.X 4.0 VL LightJul 2025