Mathematical Problem Solving on AIME Seeds 2024 II (Avg@5 (%))
94.3Avg@5 (%)GLM-4.6
Evaluation results
| Method | Links | |
|---|---|---|
| GLM-4.62026.01 | 94.3 | |
| GPT-5.1-high2026.01 | 94.3 | |
| Gemini-2.5-Pro2026.01 | 92.9 | |
| Seed-1.6-1015-high2026.01 | 92.9 | |
| DeepSeek-V3.2-thinking2026.01 | 91.4 | |
| Claude-Sonnet-4.5-thinking2026.01 | 90 | |
| DeepSeek-V3.1-thinking2026.01 | 90 | |
| GPT-5-high2026.01 | 88.6 | |
| Seed-1.6-Lite-1015-high2026.01 | 88.6 | |
| Seed-1.6-Thinking-07152026.01 | 87.1 | |
| Kimi-K2-thinking2026.01 | 85.7 | |
| Minimax-M22026.01 | 82.9 | |
| Qwen3-max-09232026.01 | 80 | |
| Gemini-3-Pro-Preview2026.01 | 75.7 | |
| Kimi-K2-09052026.01 | 71.4 | |
| GPT-5.1-chat-latest2026.01 | 52.9 |