SKT A.X K2 Card - KMO 2026 (1st Round): leaderboard
Korean Mathematical Olympiad 2026 first-round problems, run by SK Telecom. SKT A.X K2 model card benchmark table (July 2026), all models in thinking mode; accuracy in percent, higher is better.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4 Flash (Reasoning) | 94.4 | #155 (DeepSeek V4 Flash) |
| 2 | Kimi K2.6 (Thinking) | 88.1 | #113 (Kimi K2.6) |
| 3 | A.X K1 (Thinking) | 85 | #441 (A.X K1) |
| 4 | MiniMax-M2.7 | 80 | #270 |
| 5 | Qwen 3.5 397B A17B (Reasoning) | 78.8 | #154 (Qwen 3.5 397B A17B) |
| 6 | GLM-5.1 (Thinking) | 78.1 | #109 (GLM-5.1) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=skt-a-x-k2-card-kmo-2026-1st-round · How It Works · Data refreshed daily, snapshot 2026-11-05.