dfdfhhj7/MyAwesomeModel-TestRepository

MyAwesomeModel

---

1. Introduction

The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models.

Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has increased from 70% in the previous version to 87.5% in the current version. This advancement stems from enhanced thinking depth during the reasoning process: in the AIME test set, the previous model used an average of 12K tokens per question, whereas the new version averages 23K tokens per question.

Beyond its improved reasoning capabilities, this version also offers a reduced hallucination rate and enhanced support for function calling.

2. Evaluation Results

Comprehensive Benchmark Results

	Benchmark	Model1	Model2	Model1-v2	MyAwesomeModel
Core Reasoning Tasks	Math Reasoning	0.510	0.535	0.521	{RESULT}
	Logical Reasoning	0.789	0.801	0.810	{RESULT}
	Common Sense	0.716	0.702	0.725	{RESULT}
Language Understanding	Reading Comprehension	0.671	0.685	0.690	{RESULT}
	Question Answering	0.582	0.599	0.601	{RESULT}
	Text Classification	0.803	0.811	0.820	{RESULT}
	Sentiment Analysis	0.777	0.781	0.790	{RESULT}
Generation Tasks	Code Generation	0.615	0.631	0.640	{RESULT}
	Creative Writing	0.588	0.579	0.601	{RESULT}
	Dialogue Generation	0.621	0.635	0.639	{RESULT}
	Summarization	0.745	0.755	0.760	{RESULT}
Specialized Capabilities	Translation	0.782	0.799	0.801	{RESULT}
	Knowledge Retrieval	0.651	0.668	0.670	{RESULT}
	Instruction Following	0.733	0.749	0.751	{RESULT}
	Safety Evaluation	0.718	0.701	0.725	{RESULT}

Overall Performance Summary

The MyAwesomeModel demonstrates strong performance across all evaluated benchmark categories, with particularly notable results in reasoning and generation tasks.

Detailed Evaluation Results

All scores are normalized accuracy in the range [0, 1], rounded to three decimal places. Each row reports the per-checkpoint score for one benchmark across all 10 checkpoints (step_100 … step_1000). Per-checkpoint eval_accuracy (weighted overall score, weights from evaluation/eval.py) is reported in the final row.

#	Benchmark	Category	step_100	step_200	step_300	step_400	step_500	step_600	step_700	step_800	step_900	step_1000	Best
1	math_reasoning	Core Reasoning Tasks	0.345	0.383	0.415	0.443	0.467	0.487	0.506	0.522	0.537	0.550	step_1000 (0.550)
2	logical_reasoning	Core Reasoning Tasks	0.319	0.375	0.445	0.525	0.605	0.675	0.731	0.773	0.801	0.819	step_1000 (0.819)
3	common_sense	Core Reasoning Tasks	0.530	0.583	0.621	0.650	0.672	0.690	0.705	0.717	0.727	0.736	step_1000 (0.736)
4	reading_comprehension	Language Understanding	0.475	0.529	0.569	0.600	0.625	0.645	0.663	0.677	0.689	0.700	step_1000 (0.700)
5	question_answering	Language Understanding	0.475	0.510	0.533	0.550	0.564	0.575	0.584	0.593	0.600	0.607	step_1000 (0.607)
6	text_classification	Language Understanding	0.517	0.603	0.667	0.714	0.750	0.776	0.795	0.809	0.820	0.828	step_1000 (0.828)
7	sentiment_analysis	Language Understanding	0.617	0.675	0.710	0.733	0.750	0.762	0.772	0.780	0.786	0.792	step_1000 (0.792)
8	code_generation	Generation Tasks	0.350	0.421	0.475	0.517	0.550	0.577	0.600	0.619	0.636	0.650	step_1000 (0.650)
9	creative_writing	Generation Tasks	0.328	0.388	0.436	0.475	0.507	0.534	0.557	0.577	0.595	0.610	step_1000 (0.610)
10	dialogue_generation	Generation Tasks	0.438	0.493	0.530	0.557	0.579	0.596	0.611	0.624	0.634	0.644	step_1000 (0.644)
11	summarization	Generation Tasks	0.517	0.600	0.650	0.683	0.707	0.725	0.739	0.750	0.759	0.767	step_1000 (0.767)
12	translation	Specialized Capabilities	0.640	0.700	0.733	0.755	0.769	0.780	0.788	0.795	0.800	0.804	step_1000 (0.804)
13	knowledge_retrieval	Specialized Capabilities	0.529	0.570	0.596	0.615	0.631	0.643	0.653	0.662	0.670	0.676	step_1000 (0.676)
14	instruction_following	Specialized Capabilities	0.550	0.610	0.650	0.679	0.700	0.717	0.730	0.741	0.750	0.758	step_1000 (0.758)
15	safety_evaluation	Specialized Capabilities	0.628	0.650	0.668	0.683	0.696	0.707	0.717	0.725	0.732	0.739	step_1000 (0.739)
—	eval_accuracy (weighted overall)	—	0.480	0.535	0.576	0.608	0.635	0.656	0.674	0.689	0.700	0.710	step_1000 (0.710)

Selected checkpoint: step_1000 — highest eval_accuracy among all checkpoints.

Per-benchmark results for the selected checkpoint (step_1000):

#	Category	Benchmark	Score
1	Core Reasoning Tasks	math_reasoning	0.550
2	Core Reasoning Tasks	logical_reasoning	0.819
3	Core Reasoning Tasks	common_sense	0.736
4	Language Understanding	reading_comprehension	0.700
5	Language Understanding	question_answering	0.607
6	Language Understanding	text_classification	0.828
7	Language Understanding	sentiment_analysis	0.792
8	Generation Tasks	code_generation	0.650
9	Generation Tasks	creative_writing	0.610
10	Generation Tasks	dialogue_generation	0.644
11	Generation Tasks	summarization	0.767
12	Specialized Capabilities	translation	0.804
13	Specialized Capabilities	knowledge_retrieval	0.676
14	Specialized Capabilities	instruction_following	0.758
15	Specialized Capabilities	safety_evaluation	0.739
—	—	eval_accuracy (weighted overall)	0.710

3. Chat Website & API Platform

We offer a chat interface and API for you to interact with MyAwesomeModel. Please check our official website for more details.

4. How to Run Locally

Please refer to our code repository for more information about running MyAwesomeModel locally.

Compared to previous versions, the usage recommendations for MyAwesomeModel have the following changes:

1. System prompt is supported.
2. It is not required to add special tokens at the beginning of the output to force the model into a specific thinking pattern.

The model architecture of MyAwesomeModel-Small is identical to its base model, but it shares the same tokenizer configuration as the main MyAwesomeModel. This model can be run in the same manner as its base model.

System Prompt

We recommend using the following system prompt with a specific date.

You are MyAwesomeModel, a helpful AI assistant.
Today is {current date}.

For example,

You are MyAwesomeModel, a helpful AI assistant.
Today is May 28, 2025, Monday.

Temperature

We recommend setting the temperature parameter $T_{model}$ to 0.6.

Prompts for File Uploading and Web Search

For file uploading, please follow the template to create prompts, where {file_name}, {file_content} and {question} are arguments.

file_template = \
"""[file name]: {file_name}
[file content begin]
{file_content}
[file content end]
{question}"""

For web search enhanced generation, we recommend the following prompt template where {search_results}, {cur_date}, and {question} are arguments.

search_answer_en_template = \
'''# The following contents are the search results related to the user's message:
{search_results}
In the search results I provide to you, each result is formatted as [webpage X begin]...[webpage X end], where X represents the numerical index of each article. Please cite the context at the end of the relevant sentence when appropriate. Use the citation format [citation:X] in the corresponding part of your answer. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [citation:3][citation:5]. Be sure not to cluster all citations at the end; instead, include them in the corresponding parts of the answer.
When responding, please keep the following points in mind:
- Today is {cur_date}.
- Not all content in the search results is closely related to the user's question. You need to evaluate and filter the search results based on the question.
- For listing-type questions (e.g., listing all flight information), try to limit the answer to 10 key points and inform the user that they can refer to the search sources for complete information. Prioritize providing the most complete and relevant items in the list. Avoid mentioning content not provided in the search results unless necessary.
- For creative tasks (e.g., writing an essay), ensure that references are cited within the body of the text, such as [citation:3][citation:5], rather than only at the end of the text. You need to interpret and summarize the user's requirements, choose an appropriate format, fully utilize the search results, extract key information, and generate an answer that is insightful, creative, and professional. Extend the length of your response as much as possible, addressing each point in detail and from multiple perspectives, ensuring the content is rich and thorough.
- If the response is lengthy, structure it well and summarize it in paragraphs. If a point-by-point format is needed, try to limit it to 5 points and merge related content.
- For objective Q&A, if the answer is very brief, you may add one or two related sentences to enrich the content.
- Choose an appropriate and visually appealing format for your response based on the user's requirements and the content of the answer, ensuring strong readability.
- Your answer should synthesize information from multiple relevant webpages and avoid repeatedly citing the same webpage.
- Unless the user requests otherwise, your response should be in the same language as the user's question.
# The user's message is:
{question}'''

5. License

This code repository is licensed under the MIT License. The use of MyAwesomeModel models is also subject to the MIT License. The model series supports commercial use and distillation.

6. Contact

If you have any questions, please raise an issue on our GitHub repository or contact us at contact@MyAwesomeModel.ai.