AIME 2024
AIME 2024: Measures mathematical reasoning, symbolic problem solving, proof construction, or competition-style problem solving.
5rows
scoreprimary metric
2026-05-27sampled
Metadata
Metrics
Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Grok 4 | 94.0 | Grok 4 x-ai-grok-4 | Imported | 2026-05-27 |
| 2 | Magistral Medium 1.2 | 91.8 | — | Imported | 2026-05-27 |
| 3 | DeepSeek R1 0528 | 91.4 |  R1 0528 deepseek-deepseek-r1-0528 | Imported | 2026-05-27 |
| 4 | Mistral Large 3 | 53.3 | — | Imported | 2026-05-27 |
| 5 | Reka Flash 3 | 51.0 | Reka Flash 3 rekaai-reka-flash-3 | Imported | 2026-05-27 |
No matching rows.