BENCHMARK EXPLORER · math
OTIS Mock AIME 2024–2025
OTIS Mock AIME 2024–2025 results published in Epoch AI’s benchmark data.
What it measures
Mean score in the named Epoch AI evaluation; reasoning configurations remain separate.
Interpretation caveats
Scores apply to the reported benchmark and exact model configuration. Other evaluators, dataset revisions and tool settings may differ.
Original benchmarkPublished results
| # | Modalities | Compare | ||||
|---|---|---|---|---|---|---|
| 1 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 1 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 1 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 1 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 1 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 1 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 1 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 1 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 1 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 1 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 1 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 1 | Google DeepMind | InputAudioFileImageTextVideoOutputText | 1,048,576tokens | |||
| 1 | Alibaba | InputTextImageVideoOutputText | 1,000,000tokens | |||
| 2 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 2 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 3 | DeepSeek | InputTextImageOutputText | 1,048,576tokens | |||
| 3 | Meta AI | InputTextImageVideoFileAudioOutputText | 1,048,576tokens | |||
| 3 | Alibaba | InputTextOutputText | —Not documented | |||
| 4 | xAI | InputTextImageFileOutputText | 500,000tokens | |||
| 4 | Meta AI | InputTextImageVideoFileOutputText | 1,048,576tokens | |||
| 5 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 5 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 5 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 5 | Google DeepMind | InputTextImageVideoFileAudioOutputText | 1,048,576tokens | |||
| 6 | DeepSeek | InputTextOutputText | 1,048,576tokens | |||
| 7 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 7 | DeepSeek | InputTextImageOutputText | 1,048,576tokens | |||
| 7 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 7 | Mistral AI | InputTextImageOutputText | 1,048,576tokens | |||
| 8 | xAI | InputTextImageFileOutputText | 500,000tokens | |||
| 8 | Meta AI | InputTextImageVideoFileAudioOutputText | 1,048,576tokens | |||
| 9 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 10 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 10 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 10 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 10 | OpenAI | InputTextImageFileOutputText | 1,050,000tokens | |||
| 10 | xAI | InputTextImageFileOutputText | 500,000tokens | |||
| 10 | xAI | InputTextImageFileOutputText | 500,000tokens | |||
| 11 | Anthropic | InputTextImageFileOutputText | 1,000,000tokens | |||
| 11 | Google DeepMind | InputTextImageVideoFileAudioOutputText | 1,048,576tokens | |||
| 11 | Moonshot | InputTextImageVideoOutputText | 1,048,576tokens | |||
| 12 | DeepSeek | InputTextOutputText | —Not documented | |||
| 13 | OpenAI | InputFileImageTextOutputText | 400,000tokens | |||
| 13 | Moonshot | InputTextImageOutputText | 262,144tokens | |||
| 14 | OpenAI | InputFileImageTextOutputText | 400,000tokens | |||
| 15 | Google DeepMind | InputAudioFileImageTextVideoOutputText | 1,048,576tokens | |||
| 16 | DeepSeek | InputTextOutputText | —Not documented | |||
| 16 | OpenAI | InputTextImageFileOutputText | 1,050,000tokens | |||
| 16 | OpenAI | InputFileImageTextOutputText | 1,050,000tokens | |||
| 16 | Google DeepMind | InputTextImageFileAudioVideoOutputText | 1,048,576tokens |