{"benchmark_id":"gdpval-aa","name":"GDPval-AA","parent_benchmark":null,"categories":["legal","reasoning","finance","general","agents"],"modality":"text","multilingual":false,"max_score":3000.0,"language":"en","description":"GDPval-AA is an evaluation of AI model performance on economically valuable knowledge work tasks across professional domains including finance, legal, and other sectors. Run independently by Artificial Analysis, it uses Elo scoring to rank models on real-world work task performance.","paper_link":null,"implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:23.385998+00:00","updated_at":"2026-07-17T06:42:51.729827+00:00","statistics":{"total_models":39,"average_score":1291.6820512820511,"min_score":783.0,"max_score":1815.0,"score_stddev":259.91090262038773,"verified_count":0,"self_reported_count":6},"child_benchmarks":[{"benchmark_id":"gdpval-mm","name":"GDPval-MM","categories":["multimodal","reasoning","finance","general"],"modality":"multimodal","max_score":1.0,"description":"GDPval-MM is the multimodal variant of the GDPval benchmark, evaluating AI model performance on real-world economically valuable tasks that require processing and generating multimodal content including documents, slides, diagrams, spreadsheets, images, and other professional deliverables across diverse industries."}],"linked_dataset":null,"models":[{"rank":1,"model_id":"claude-fable-5","model_name":"Claude Fable 5","organization_id":"anthropic","organization_name":"Anthropic","organization_country":"US","score":1815.0,"normalized_score":0.605,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Adaptive Reasoning, Max Effort, Opus 4.8 Fallback","verification_date":null,"provider_id":"anthropic","input_cost_per_million":10.0,"output_cost_per_million":50.0,"context_window":1000000,"announcement_date":"2026-06-09","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Anthropic","best_throughput":null,"throughput_provider":"Anthropic","context_provider":"Anthropic"},{"rank":2,"model_id":"gpt-5.6-sol","model_name":"GPT-5.6 Sol","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":1747.8,"normalized_score":0.5826,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-5-6/","analysis_method":"GDPval-AA v2 Elo. Max reasoning effort.","verification_date":null,"provider_id":"openai","input_cost_per_million":5.0,"output_cost_per_million":30.0,"context_window":1050000,"announcement_date":"2026-07-09","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"OpenAI","best_throughput":null,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":3,"model_id":"kimi-k3","model_name":"Kimi K3","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":1668.0,"normalized_score":0.556,"verified":false,"self_reported":false,"self_reported_source":"https://www.kimi.com/blog/kimi-k3","analysis_method":"GDPval-AA v2 Elo; Artificial Analysis","verification_date":null,"provider_id":"moonshot","input_cost_per_million":3.0,"output_cost_per_million":15.0,"context_window":1048576,"announcement_date":"2026-07-16","param_count":2800000000000,"is_open_source":true,"is_new":true,"best_latency":null,"latency_provider":"Moonshot AI","best_throughput":null,"throughput_provider":"Moonshot AI","context_provider":"Moonshot AI"},{"rank":4,"model_id":"claude-opus-4-8","model_name":"Claude Opus 4.8","organization_id":"anthropic","organization_name":"Anthropic","organization_country":"US","score":1638.0,"normalized_score":0.546,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Adaptive Reasoning, Max Effort","verification_date":null,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"context_window":1000000,"announcement_date":"2026-05-28","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.5,"latency_provider":"Anthropic","best_throughput":42.0,"throughput_provider":"Anthropic","context_provider":"Anthropic"},{"rank":5,"model_id":"claude-sonnet-5","model_name":"Claude Sonnet 5","organization_id":"anthropic","organization_name":"Anthropic","organization_country":"US","score":1618.0,"normalized_score":0.5393,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"GDPval-AA v2 Elo (Artificial Analysis), as of June 6, 2026. Adaptive reasoning, max effort.","verification_date":null,"provider_id":"anthropic","input_cost_per_million":3.0,"output_cost_per_million":15.0,"context_window":1000000,"announcement_date":"2026-06-30","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.4,"latency_provider":"Anthropic","best_throughput":42.0,"throughput_provider":"Anthropic","context_provider":"Anthropic"},{"rank":6,"model_id":"claude-opus-4-6","model_name":"Claude Opus 4.6","organization_id":"anthropic","organization_name":"Anthropic","organization_country":"US","score":1606.0,"normalized_score":0.5353,"verified":false,"self_reported":true,"self_reported_source":"https://www.anthropic.com/news/claude-opus-4-6","analysis_method":"Elo score. Run independently by Artificial Analysis. Outperforms GPT-5.2 by ~144 Elo points and Claude Opus 4.5 by 190 points.","verification_date":null,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"context_window":1000000,"announcement_date":"2026-02-05","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.5,"latency_provider":"Anthropic","best_throughput":42.0,"throughput_provider":"Anthropic","context_provider":"Anthropic"},{"rank":7,"model_id":"gpt-5.6-terra","model_name":"GPT-5.6 Terra","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":1593.0,"normalized_score":0.531,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-5-6/","analysis_method":"GDPval-AA v2 Elo. Max reasoning effort.","verification_date":null,"provider_id":"openai","input_cost_per_million":2.5,"output_cost_per_million":15.0,"context_window":1050000,"announcement_date":"2026-07-09","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"OpenAI","best_throughput":null,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":8,"model_id":"gpt-5.6-luna","model_name":"GPT-5.6 Luna","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":1591.8,"normalized_score":0.5306,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-5-6/","analysis_method":"GDPval-AA v2 Elo. Max reasoning effort.","verification_date":null,"provider_id":"openai","input_cost_per_million":1.0,"output_cost_per_million":6.0,"context_window":1050000,"announcement_date":"2026-07-09","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"OpenAI","best_throughput":null,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":9,"model_id":"grok-4.5","model_name":"Grok 4.5","organization_id":"xai","organization_name":"xAI","organization_country":"US","score":1543.0,"normalized_score":0.5143,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/articles/grok-4-5-brings-spacexai-to-the-the-intelligence-frontier","analysis_method":"GDPval-AA v2 Elo, run independently by Artificial Analysis.","verification_date":null,"provider_id":"xai","input_cost_per_million":2.0,"output_cost_per_million":6.0,"context_window":500000,"announcement_date":"2026-07-08","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"xAI","best_throughput":90.0,"throughput_provider":"xAI","context_provider":"xAI"},{"rank":10,"model_id":"claude-opus-4-7","model_name":"Claude Opus 4.7","organization_id":"anthropic","organization_name":"Anthropic","organization_country":"US","score":1542.0,"normalized_score":0.514,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Adaptive Reasoning, Max Effort","verification_date":null,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"context_window":1000000,"announcement_date":"2026-04-16","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.5,"latency_provider":"Anthropic","best_throughput":42.0,"throughput_provider":"Anthropic","context_provider":"Anthropic"},{"rank":11,"model_id":"minimax-m3","model_name":"MiniMax M3","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":1431.0,"normalized_score":0.477,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":"fireworks","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":1000000,"announcement_date":"2026-06-01","param_count":null,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Fireworks","best_throughput":null,"throughput_provider":"Fireworks","context_provider":"Novita"},{"rank":12,"model_id":"gpt-5.4","model_name":"GPT-5.4","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":1429.0,"normalized_score":0.4763,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"xhigh","verification_date":null,"provider_id":"openai","input_cost_per_million":2.5,"output_cost_per_million":15.0,"context_window":1000000,"announcement_date":"2026-03-05","param_count":null,"is_open_source":false,"is_new":false,"best_latency":3.0,"latency_provider":"OpenAI","best_throughput":50.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":13,"model_id":"mimo-v2-pro","model_name":"MiMo-V2-Pro","organization_id":"xiaomi","organization_name":"Xiaomi","organization_country":"CN","score":1426.0,"normalized_score":0.4753,"verified":false,"self_reported":true,"self_reported_source":"https://mimo.xiaomi.com/mimo-v2-pro","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-18","param_count":1000000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":14,"model_id":"claude-sonnet-4-6","model_name":"Claude Sonnet 4.6","organization_id":"anthropic","organization_name":"Anthropic","organization_country":"US","score":1417.0,"normalized_score":0.4723,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Adaptive Reasoning, Max Effort","verification_date":null,"provider_id":"anthropic","input_cost_per_million":3.0,"output_cost_per_million":15.0,"context_window":200000,"announcement_date":"2026-02-17","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.4,"latency_provider":"Anthropic","best_throughput":42.0,"throughput_provider":"Anthropic","context_provider":"Anthropic"},{"rank":15,"model_id":"mimo-v2-omni","model_name":"MiMo-V2-Omni","organization_id":"xiaomi","organization_name":"Xiaomi","organization_country":"CN","score":1410.0,"normalized_score":0.47,"verified":false,"self_reported":true,"self_reported_source":"https://mimo.xiaomi.com/mimo-v2-omni","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-18","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":16,"model_id":"gemini-3.5-flash","model_name":"Gemini 3.5 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":1370.0,"normalized_score":0.4567,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"high","verification_date":null,"provider_id":"google","input_cost_per_million":1.5,"output_cost_per_million":9.0,"context_window":1048576,"announcement_date":"2026-05-19","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Google","best_throughput":null,"throughput_provider":"Google","context_provider":"Google"},{"rank":17,"model_id":"deepseek-v4-pro-max","model_name":"DeepSeek-V4-Pro-Max","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":1332.0,"normalized_score":0.444,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning, Max Effort","verification_date":null,"provider_id":"novita","input_cost_per_million":1.6,"output_cost_per_million":3.2,"context_window":1048576,"announcement_date":"2026-04-23","param_count":1600000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"DeepInfra"},{"rank":18,"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":1308.0,"normalized_score":0.436,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":"novita","input_cost_per_million":1.25,"output_cost_per_million":3.75,"context_window":1000000,"announcement_date":"2026-05-19","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Together"},{"rank":19,"model_id":"mimo-v2.5-pro","model_name":"MiMo-V2.5-Pro","organization_id":"xiaomi","organization_name":"Xiaomi","organization_country":"CN","score":1286.0,"normalized_score":0.4287,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":"xiaomi","input_cost_per_million":0.435,"output_cost_per_million":0.87,"context_window":1048576,"announcement_date":"2026-04-27","param_count":1023244718976,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Xiaomi","best_throughput":null,"throughput_provider":"Xiaomi","context_provider":"Novita"},{"rank":20,"model_id":"glm-5.1","model_name":"GLM-5.1","organization_id":"zai-org","organization_name":"Zhipu AI","organization_country":"CN","score":1281.0,"normalized_score":0.427,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning","verification_date":null,"provider_id":"friendli","input_cost_per_million":1.4,"output_cost_per_million":4.4,"context_window":200000,"announcement_date":"2026-04-07","param_count":754000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"FriendliAI","best_throughput":null,"throughput_provider":"FriendliAI","context_provider":"FriendliAI"},{"rank":21,"model_id":"deepseek-v4-flash-max","model_name":"DeepSeek-V4-Flash-Max","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":1203.0,"normalized_score":0.401,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning, Max Effort","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.2,"context_window":1048576,"announcement_date":"2026-04-23","param_count":284000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepSeek"},{"rank":22,"model_id":"kimi-k2.6","model_name":"Kimi K2.6","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":1202.0,"normalized_score":0.4007,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.75,"output_cost_per_million":3.5,"context_window":262144,"announcement_date":"2026-04-20","param_count":1000000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"Fireworks"},{"rank":23,"model_id":"gpt-5.4-mini","model_name":"GPT-5.4 mini","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":1190.0,"normalized_score":0.3967,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"xhigh","verification_date":null,"provider_id":"openai","input_cost_per_million":0.75,"output_cost_per_million":4.5,"context_window":400000,"announcement_date":"2026-03-17","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"OpenAI","best_throughput":null,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":24,"model_id":"nemotron-3-ultra-550b-a55b","model_name":"Nemotron 3 Ultra (550B A55B)","organization_id":"nvidia","organization_name":"NVIDIA","organization_country":"US","score":1183.0,"normalized_score":0.3943,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-06-04","param_count":550000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":25,"model_id":"minimax-m2.7","model_name":"MiniMax M2.7","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":1178.0,"normalized_score":0.3927,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":204800,"announcement_date":"2026-03-18","param_count":null,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":26,"model_id":"muse-spark","model_name":"Muse Spark","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":1164.0,"normalized_score":0.388,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-08","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":27,"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":1160.0,"normalized_score":0.3867,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":"together","input_cost_per_million":0.5,"output_cost_per_million":3.0,"context_window":1000000,"announcement_date":"2026-04-02","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":28,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":1158.0,"normalized_score":0.386,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning","verification_date":null,"provider_id":"novita","input_cost_per_million":0.6,"output_cost_per_million":3.6,"context_window":262144,"announcement_date":"2026-04-21","param_count":27781427952,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":29,"model_id":"gpt-5.5","model_name":"GPT-5.5","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":1135.0,"normalized_score":0.3783,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Non-reasoning","verification_date":null,"provider_id":"openai","input_cost_per_million":5.0,"output_cost_per_million":30.0,"context_window":1050000,"announcement_date":"2026-04-23","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"OpenAI","best_throughput":null,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":30,"model_id":"gpt-5.4-nano","model_name":"GPT-5.4 nano","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":1115.0,"normalized_score":0.3717,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"xhigh","verification_date":null,"provider_id":"openai","input_cost_per_million":0.2,"output_cost_per_million":1.25,"context_window":400000,"announcement_date":"2026-03-17","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"OpenAI","best_throughput":null,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":31,"model_id":"grok-4.3","model_name":"Grok 4.3","organization_id":"xai","organization_name":"xAI","organization_country":"US","score":1100.0,"normalized_score":0.3667,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"high","verification_date":null,"provider_id":"xai","input_cost_per_million":1.25,"output_cost_per_million":2.5,"context_window":1000000,"announcement_date":"2026-05-06","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"xAI","best_throughput":null,"throughput_provider":"xAI","context_provider":"xAI"},{"rank":32,"model_id":"qwen3.6-35b-a3b","model_name":"Qwen3.6-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":1056.0,"normalized_score":0.352,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-16","param_count":35000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":33,"model_id":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":985.0,"normalized_score":0.3283,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","param_count":122000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":34,"model_id":"gemini-3.1-pro-preview","model_name":"Gemini 3.1 Pro","organization_id":"google","organization_name":"Google","organization_country":"US","score":976.0,"normalized_score":0.3253,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":"google","input_cost_per_million":2.5,"output_cost_per_million":15.0,"context_window":1048576,"announcement_date":"2026-02-19","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.6,"latency_provider":"Google","best_throughput":90.0,"throughput_provider":"Google","context_provider":"Google"},{"rank":35,"model_id":"qwen3.5-397b-a17b","model_name":"Qwen3.5-397B-A17B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":961.0,"normalized_score":0.3203,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-16","param_count":397000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":36,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":946.0,"normalized_score":0.3153,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":"together","input_cost_per_million":0.32,"output_cost_per_million":1.28,"context_window":1000000,"announcement_date":"2026-05-31","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":37,"model_id":"mistral-medium-3-5","model_name":"Mistral Medium 3.5","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":926.0,"normalized_score":0.3087,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":null,"verification_date":null,"provider_id":"mistral","input_cost_per_million":1.5,"output_cost_per_million":7.5,"context_window":256000,"announcement_date":"2026-04-29","param_count":128000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Mistral AI","best_throughput":null,"throughput_provider":"Mistral AI","context_provider":"Mistral AI"},{"rank":38,"model_id":"claude-haiku-4-5-20251001","model_name":"Claude Haiku 4.5","organization_id":"anthropic","organization_name":"Anthropic","organization_country":"US","score":902.0,"normalized_score":0.3007,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning","verification_date":null,"provider_id":"anthropic","input_cost_per_million":1.0,"output_cost_per_million":5.0,"context_window":200000,"announcement_date":"2025-10-15","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.3,"latency_provider":"Anthropic","best_throughput":100.0,"throughput_provider":"Anthropic","context_provider":"Anthropic"},{"rank":39,"model_id":"gemma-4-31b-it","model_name":"Gemma 4 31B","organization_id":"google","organization_name":"Google","organization_country":"US","score":783.0,"normalized_score":0.261,"verified":false,"self_reported":false,"self_reported_source":"https://artificialanalysis.ai/evaluations/gdpval-aa","analysis_method":"Reasoning","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.13,"output_cost_per_million":0.38,"context_window":262144,"announcement_date":"2026-04-02","param_count":30700000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"Novita"}]}