Contamination MapText / LLM / Dataset
AIME 2025
The 30 problems of the 2025 American Invitational Mathematics Examination (AIME I and AIME II, 15 each); integer answers. No official dataset release: commonly used HF copies are opencompass/AIME2025 (configs AIME2025-I / AIME2025-II) and MathArena/aime_2025 (30 problems).
- Also known as
- AIME 2025, AIME25, AIME'25
- Domain
- math
- Test items from
- 2025-02-06
Evidence
“2025 AIME I problems and solutions. The test was held on Thursday, February 6, 2025.”
web.archive.org · website · retrieved 2026-10-15 “This year the AIME I will take place on February 6, 2025, while the alternate AIME II will take place on February 12, 2025.”
maa.org · website · retrieved 2026-10-15
Exposure by model
| Benchmark | Model | Level | Reason |
|---|---|---|---|
| Recent LLM benchmarks | LLM360 Amber | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | BLOOM | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Claude 3.5 Sonnet | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-04-01) |
| Recent LLM benchmarks | Claude 3.7 Sonnet | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-11-01) |
| Recent LLM benchmarks | Claude 3 (Opus, Sonnet, Haiku) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-08-01) |
| Recent LLM benchmarks | Claude Opus 4 and Claude Sonnet 4 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Claude Fable 5 / Claude Mythos 5 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Claude Mythos Preview | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Claude Opus 4.5 | Test data seen | a contamination analysis found test examples in the training data (Developer found rephrased AIME questions, official solutions and model answers in the training corpus despite decontamination; the AIME 2025 score may be inflated (example answer suggesting memorisation)) |
| Recent LLM benchmarks | Claude Opus 5 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Claude Sonnet 5 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DCLM-7B-IT (DCLM-IT-7B) | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DCLM-7B (DCLM-Baseline-7B) | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DeepSeek-R1-0528 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DeepSeek-R1-Distill | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DeepSeek-R1 | Not seen | the authors state the dataset was excluded from training |
| Recent LLM benchmarks | DeepSeek-V3-0324 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DeepSeek-V3.1 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DeepSeek-V3.2-Exp | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DeepSeek-V3.2 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DeepSeek-V3 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-07-01) |
| Recent LLM benchmarks | DeepSeek-V4.1-Flash | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | DeepSeek-V4 (Pro / Flash) | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Gemini 1.5 (Pro, Flash) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-11-01) |
| Recent LLM benchmarks | Gemini 2.5 (Pro, Flash) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2025-01-01) |
| Recent LLM benchmarks | Gemini 3 Pro | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2025-01-01) |
| Recent LLM benchmarks | Gemini 4 Argon | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Gemma 2 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Gemma 3 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-08-01) |
| Recent LLM benchmarks | Gemma 3n | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-06-01) |
| Recent LLM benchmarks | Gemma 4 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2025-01-01) |
| Recent LLM benchmarks | GPT-4 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2021-09-01) |
| Recent LLM benchmarks | GPT-4o | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-10-01) |
| Recent LLM benchmarks | GPT-5.2 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | GPT-5 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-09-30) |
| Recent LLM benchmarks | GPT-6 Astra | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | gpt-oss | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-06-01) |
| Recent LLM benchmarks | InternVL3.5 | Unknown | unknown for its base model Qwen3: training data not disclosed in enough detail |
| Recent LLM benchmarks | InternVL3 | Unknown | unknown for its base model Qwen2.5: training data not disclosed in enough detail |
| Recent LLM benchmarks | LLM360 K2-65B (K2 Diamond) | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | K2-Horizon | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | K2-V2 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Llama 2 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2022-09-01) |
| Recent LLM benchmarks | Llama 3.1 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-12-01) |
| Recent LLM benchmarks | Llama 3.2-Vision (11B, 90B) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-12-01) |
| Recent LLM benchmarks | Llama 3.2 (1B, 3B) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-12-01) |
| Recent LLM benchmarks | Llama 3.3 70B | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-12-01) |
| Recent LLM benchmarks | Meta Llama 3 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-12-01) |
| Recent LLM benchmarks | Llama 4 (Scout, Maverick) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-08-01) |
| Recent LLM benchmarks | LLaVA-OneVision-1.5 | Unknown | unknown for its base model Qwen3: training data not disclosed in enough detail |
| Recent LLM benchmarks | LLaVA-OneVision | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Ministral 3 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Mistral 7B | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Mistral Large 3 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Mistral Medium 3.5 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-11-01) |
| Recent LLM benchmarks | Mistral Small 4 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-11-01) |
| Recent LLM benchmarks | Mixtral 8x7B | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Molmo (0924) | Unknown | unknown for its base model OpenAI CLIP: training data not disclosed in enough detail |
| Recent LLM benchmarks | Molmo2 | Unknown | unknown for its base model Qwen3: training data not disclosed in enough detail |
| Recent LLM benchmarks | OpenAI o1 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-10-01) |
| Recent LLM benchmarks | OpenAI o3 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-06-01) |
| Recent LLM benchmarks | OLMo (February 2024) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-02-01) |
| Recent LLM benchmarks | OLMo 2 (November 2024) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-12-01) |
| Recent LLM benchmarks | Olmo 3.1 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-12-01) |
| Recent LLM benchmarks | Olmo 3 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-12-01) |
| Recent LLM benchmarks | Olmo Hybrid 7B | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-12-01) |
| Recent LLM benchmarks | Phi-3.5 (mini / MoE) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-10-01) |
| Recent LLM benchmarks | Phi-3 (mini / small / medium) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-10-01) |
| Recent LLM benchmarks | Phi-4-mini-flash-reasoning | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2025-02-01) |
| Recent LLM benchmarks | Phi-4-mini-reasoning | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2025-02-01) |
| Recent LLM benchmarks | Phi-4-mini | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-06-01) |
| Recent LLM benchmarks | Phi-4-reasoning / Phi-4-reasoning-plus | Not seen | the authors state the dataset was excluded from training |
| Recent LLM benchmarks | Phi-4 | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-06-01) |
| Recent LLM benchmarks | Phi-mini-MoE / Phi-tiny-MoE (SlimMoE) | Not seen | its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-10-01) |
| Recent LLM benchmarks | Pixtral 12B | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Pixtral Large | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Pythia (deduplicated) | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Pythia | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen2.5-VL | Unknown | unknown for its base model Qwen2.5: training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen2.5 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen3-2507 (Instruct-2507 / Thinking-2507) | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen3-Next | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen3-VL | Unknown | unknown for its base model Qwen3: training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen3.5 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen3.6 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen3.8-Flash-Next | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen3.8 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | Qwen3 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | SmolLM2 | Unknown | training data not disclosed in enough detail |
| Recent LLM benchmarks | SmolLM3 | Unknown | training data not disclosed in enough detail |
Notes
AIME I held 2025-02-06 (AoPS); MAA announced AIME II for 2025-02-12. MathArena reports that 8 AIME 2025 problems could already be found online in a similar form before the contest (arXiv 2505.23281v3, Section 4).
Sources
- 2025 AIME I - AoPS Wiki (Wayback snapshot 2025-05-01) · website · retrieved 2026-10-15
- 2024-25 AIME Thresholds Are Available (MAA) · website · retrieved 2026-10-15
- opencompass/AIME2025 dataset card · dataset card · retrieved 2026-10-15
- MathArena/aime_2025 dataset card · dataset card · retrieved 2026-10-15