{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/measuring-general-intelligence-with-generated","title":"Measuring General Intelligence with Generated Games","arxiv_id":"2505.07215","date":"2025-05-12","proceeding":null,"authors":["Vivek Verma","David Huang","William Chen","Dan Klein","Nicholas Tomlin"],"abstract":"We present gg-bench, a collection of game environments designed to evaluate general reasoning capabilities in language models. Unlike most static benchmarks, gg-bench is a data generating process where new evaluation instances can be generated at will. In particular, gg-bench is synthetically generated by (1) using a large language model (LLM) to generate natural language descriptions of novel games, (2) using the LLM to implement each game in code as a Gym environment, and (3) training reinforcement learning (RL) agents via self-play on the generated games. We evaluate language models by their winrate against these RL agents by prompting models with the game description, current board state, and a list of valid moves, after which models output the moves they wish to take. gg-bench is challenging: state-of-the-art LLMs such as GPT-4o and Claude 3.7 Sonnet achieve winrates of 7-9% on gg-bench using in-context learning, while reasoning models such as o1, o3-mini and DeepSeek-R1 achieve average winrates of 31-36%. We release the generated games, data generation process, and evaluation code in order to support future modeling work and expansion of our benchmark.","url_abs":"https://arxiv.org/abs/2505.07215v1","url_pdf":"https://arxiv.org/pdf/2505.07215v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"measuring-general-intelligence-with-generated","repo_url":"https://github.com/vivek3141/gg-bench","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.07215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07215"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vivek3141/gg-bench","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5555027230c54cd2","entry":"extract_python_code","repo":"vivek3141/gg-bench","repo_kind":"official","path":"gg_bench/utils/markdown.py","file_url":"https://github.com/vivek3141/gg-bench/blob/HEAD/gg_bench/utils/markdown.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5555027230c54cd2"}},{"code_sha256_prefix":"7e50d41df248d74f","entry":"get_valid_moves","repo":"vivek3141/gg-bench","repo_kind":"official","path":"gg_bench/utils/minimax.py","file_url":"https://github.com/vivek3141/gg-bench/blob/HEAD/gg_bench/utils/minimax.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e50d41df248d74f"}},{"code_sha256_prefix":"44ae92767e1cb329","entry":"load_yaml","repo":"vivek3141/gg-bench","repo_kind":"official","path":"gg_bench/utils/load_yaml.py","file_url":"https://github.com/vivek3141/gg-bench/blob/HEAD/gg_bench/utils/load_yaml.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44ae92767e1cb329"}},{"code_sha256_prefix":"a41c3f2b7c9f70f1","entry":"minimax","repo":"vivek3141/gg-bench","repo_kind":"official","path":"gg_bench/utils/minimax.py","file_url":"https://github.com/vivek3141/gg-bench/blob/HEAD/gg_bench/utils/minimax.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a41c3f2b7c9f70f1"}},{"code_sha256_prefix":"a8e2bbda4d37adde","entry":"pick_minimax_action","repo":"vivek3141/gg-bench","repo_kind":"official","path":"gg_bench/utils/minimax.py","file_url":"https://github.com/vivek3141/gg-bench/blob/HEAD/gg_bench/utils/minimax.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8e2bbda4d37adde"}},{"code_sha256_prefix":"fd9cee29d50d81d3","entry":"remove_think_block","repo":"vivek3141/gg-bench","repo_kind":"official","path":"gg_bench/utils/chat_completion/deepseek_chat_completion.py","file_url":"https://github.com/vivek3141/gg-bench/blob/HEAD/gg_bench/utils/chat_completion/deepseek_chat_completion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd9cee29d50d81d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}