Mathematics on AIME25 (EM)
86.67Exact MatchK-EXAONE-236B-A23B
Evaluation Results
| Method | Links | |
|---|---|---|
| K-EXAONE-236B-A23BReasoning=On2026.03 | 86.67 | |
| Qwen-3-30B-A3BReasoning=On2026.03 | 86.67 | |
| K-EXAONE-236B-A23BReasoning=On2026.03 | 86.67 | |
| Qwen-3-30B-A3BReasoning=On2026.03 | 86.67 | |
| Solar-Open-100BReasoning=On2026.03 | 76.67 | |
| Solar-open-100BReasoning=On2026.03 | 76.67 | |
| Mi:dm K 2.5 Pro (March ‘26)Reasoning=On2026.03 | 70 | |
| Mi:dm K 2.5 Pro (March ‘26)Reasoning=On2026.03 | 70 | |
| Qwen-3-30B-A3BReasoning=Off2026.03 | 63.3 | |
| HyperCLOVAX-SEED-Think-32BReasoning=On2026.03 | 56.67 | |
| Qwen-3-30B-A3BReasoning=Off2026.03 | 50 | |
| K-EXAONE-236B-A23BReasoning=Off2026.03 | 43.3 | |
| K-EXAONE-236B-A23BReasoning=Off2026.03 | 40 | |
| HyperCLOVAX-SEED-Think-32BReasoning=On2026.03 | 40 | |
| Mi:dm K 2.5 Pro (March ‘26)Reasoning=Off2026.03 | 33.3 | |
| Mi:dm K 2.5 Pro (March ‘26)Reasoning=Off2026.03 | 16.6 | |
| HyperCLOVAX-SEED-Think-32BReasoning=Off2026.03 | 3.3 | |
| HyperCLOVAX-SEED-Think-32BReasoning=Off2026.03 | 3.3 |