{"licence": "Creative Commons Attribution 4.0 International (CC BY 4.0)", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "attribution": "Spring Prompt (springprompt.com)", "source_url": "https://springprompt.com/data", "release": "2026-11-19-3608133e8331", "test_your_prompt": "These are our tasks, not yours. Test your own prompt on these models: https://springprompt.com/prompt-test", "name": "Spring Prompt Score", "method": "Each of our benchmarks becomes a percentile from 0 to 100 among the models with one of our commerce benchmarks (CatalogBench or ROASBench), each model at its best setting, on the headline measure the overall leaderboard uses. The score is the plain average of the percentiles a model has; it needs at least 3. No third-party results are used.", "min_benchmarks": 3, "benchmarks": ["catalogbench", "deckbench", "surveybench", "roasbench", "bulletbench"], "scores": [{"rank": 1, "model": "openai-gpt-6-1-sol", "model_name": "GPT-6.1 Sol", "developer": "OpenAI", "score": 90.4, "benchmarks": 4, "of": 5, "catalogbench": 91.2, "deckbench": 88.6, "surveybench": 88.5, "roasbench": null, "bulletbench": 93.2}, {"rank": 2, "model": "anthropic-claude-fable-5-2", "model_name": "Claude Fable 5.2", "developer": "Anthropic", "score": 88.0, "benchmarks": 5, "of": 5, "catalogbench": 80.9, "deckbench": 91.4, "surveybench": 100.0, "roasbench": 100.0, "bulletbench": 67.9}, {"rank": 3, "model": "openai-gpt-6-2-astra", "model_name": "GPT-6.2 Astra", "developer": "OpenAI", "score": 83.0, "benchmarks": 5, "of": 5, "catalogbench": 91.9, "deckbench": 54.3, "surveybench": 96.2, "roasbench": 94.3, "bulletbench": 78.6}, {"rank": 4, "model": "openai-gpt-6-2-sol", "model_name": "GPT-6.2 Sol", "developer": "OpenAI", "score": 80.9, "benchmarks": 5, "of": 5, "catalogbench": 97.1, "deckbench": 85.7, "surveybench": 76.9, "roasbench": 77.1, "bulletbench": 67.9}, {"rank": 4, "model": "openai-gpt-6-sol", "model_name": "GPT-6 Sol", "developer": "OpenAI", "score": 80.9, "benchmarks": 4, "of": 5, "catalogbench": 84.6, "deckbench": 94.3, "surveybench": null, "roasbench": 85.7, "bulletbench": 58.9}, {"rank": 4, "model": "openai-gpt-6-astra", "model_name": "GPT-6 Astra", "developer": "OpenAI", "score": 80.7, "benchmarks": 4, "of": 5, "catalogbench": 94.9, "deckbench": 97.1, "surveybench": null, "roasbench": 91.4, "bulletbench": 39.3}, {"rank": 7, "model": "openai-gpt-6-1-terra", "model_name": "GPT-6.1 Terra", "developer": "OpenAI", "score": 74.0, "benchmarks": 5, "of": 5, "catalogbench": 82.4, "deckbench": 77.1, "surveybench": 65.4, "roasbench": 97.1, "bulletbench": 48.2}, {"rank": 7, "model": "anthropic-claude-opus-5-5", "model_name": "Claude Opus 5.5", "developer": "Anthropic", "score": 73.9, "benchmarks": 4, "of": 5, "catalogbench": 59.6, "deckbench": 80.0, "surveybench": 84.6, "roasbench": 71.4, "bulletbench": null}, {"rank": 9, "model": "meta-muse-wonder", "model_name": "Muse Wonder", "developer": "Meta", "score": 63.6, "benchmarks": 5, "of": 5, "catalogbench": 80.9, "deckbench": 60.0, "surveybench": 92.3, "roasbench": 31.4, "bulletbench": 53.6}, {"rank": 10, "model": "openai-gpt-6-luna", "model_name": "GPT-6 Luna", "developer": "OpenAI", "score": 60.4, "benchmarks": 5, "of": 5, "catalogbench": 72.1, "deckbench": 68.6, "surveybench": 50.0, "roasbench": 82.9, "bulletbench": 28.6}, {"rank": 10, "model": "google-gemini-4-hydrogen", "model_name": "Gemini 4 Hydrogen", "developer": "Google", "score": 59.7, "benchmarks": 5, "of": 5, "catalogbench": 66.9, "deckbench": 42.9, "surveybench": 53.8, "roasbench": 48.6, "bulletbench": 86.4}, {"rank": 12, "model": "meta-muse-ember", "model_name": "Muse Ember", "developer": "Meta", "score": 59.3, "benchmarks": 5, "of": 5, "catalogbench": 64.0, "deckbench": 51.4, "surveybench": 73.1, "roasbench": 74.3, "bulletbench": 33.9}, {"rank": 13, "model": "alibaba-qwen4-max", "model_name": "Qwen4-Max", "developer": "Alibaba", "score": 57.4, "benchmarks": 5, "of": 5, "catalogbench": 35.3, "deckbench": 100.0, "surveybench": 80.8, "roasbench": 51.4, "bulletbench": 19.6}, {"rank": 14, "model": "anthropic-claude-fable-5-1", "model_name": "Claude Fable 5.1", "developer": "Anthropic", "score": 55.7, "benchmarks": 3, "of": 5, "catalogbench": 27.2, "deckbench": 71.4, "surveybench": null, "roasbench": 68.6, "bulletbench": null}, {"rank": 15, "model": "google-gemini-4-neon", "model_name": "Gemini 4 Neon", "developer": "Google", "score": 55.0, "benchmarks": 5, "of": 5, "catalogbench": 82.4, "deckbench": 34.3, "surveybench": 15.4, "roasbench": 57.1, "bulletbench": 85.7}, {"rank": 16, "model": "xai-grok-4-7", "model_name": "Grok 4.7", "developer": "xAI", "score": 53.0, "benchmarks": 3, "of": 5, "catalogbench": 67.6, "deckbench": 65.7, "surveybench": null, "roasbench": 25.7, "bulletbench": null}, {"rank": 17, "model": "anthropic-claude-sonnet-5-5", "model_name": "Claude Sonnet 5.5", "developer": "Anthropic", "score": 51.0, "benchmarks": 4, "of": 5, "catalogbench": 36.0, "deckbench": 82.9, "surveybench": null, "roasbench": 80.0, "bulletbench": 5.0}, {"rank": 18, "model": "google-gemini-4-carbon", "model_name": "Gemini 4 Carbon", "developer": "Google", "score": 47.8, "benchmarks": 5, "of": 5, "catalogbench": 52.2, "deckbench": 31.4, "surveybench": 46.2, "roasbench": 62.9, "bulletbench": 46.4}, {"rank": 19, "model": "moonshotai-kimi-k3-1-pro", "model_name": "Kimi K3.1 Pro", "developer": "Moonshot AI", "score": 45.7, "benchmarks": 4, "of": 5, "catalogbench": null, "deckbench": 62.9, "surveybench": 11.5, "roasbench": 88.6, "bulletbench": 19.6}, {"rank": 20, "model": "google-gemini-3-8-flash", "model_name": "Gemini 3.8 Flash", "developer": "Google", "score": 42.1, "benchmarks": 5, "of": 5, "catalogbench": 30.1, "deckbench": 20.0, "surveybench": 34.6, "roasbench": 65.7, "bulletbench": 60.0}, {"rank": 20, "model": "google-gemini-4-argon", "model_name": "Gemini 4 Argon", "developer": "Google", "score": 41.7, "benchmarks": 5, "of": 5, "catalogbench": 61.8, "deckbench": 28.6, "surveybench": 38.5, "roasbench": 60.0, "bulletbench": 19.6}, {"rank": 20, "model": "google-gemini-3-1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "developer": "Google", "score": 41.5, "benchmarks": 5, "of": 5, "catalogbench": 48.5, "deckbench": 14.3, "surveybench": 26.9, "roasbench": 42.9, "bulletbench": 75.0}, {"rank": 23, "model": "anthropic-claude-haiku-5-5", "model_name": "Claude Haiku 5.5", "developer": "Anthropic", "score": 38.0, "benchmarks": 5, "of": 5, "catalogbench": 32.4, "deckbench": 48.6, "surveybench": 69.2, "roasbench": 5.7, "bulletbench": 33.9}, {"rank": 23, "model": "particle-ai-particle-1", "model_name": "Particle-1", "developer": "Particle AI", "score": 37.9, "benchmarks": 4, "of": 5, "catalogbench": 4.4, "deckbench": 45.7, "surveybench": 61.5, "roasbench": 40.0, "bulletbench": null}, {"rank": 25, "model": "minimax-minimax-m3-1-flash", "model_name": "MiniMax M3.1 Flash", "developer": "MiniMax", "score": 36.5, "benchmarks": 5, "of": 5, "catalogbench": 63.2, "deckbench": 74.3, "surveybench": 0.0, "roasbench": 34.3, "bulletbench": 10.7}, {"rank": 26, "model": "moonshotai-kimi-k3", "model_name": "Kimi K3", "developer": "Moonshot AI", "score": 34.3, "benchmarks": 4, "of": 5, "catalogbench": 30.9, "deckbench": 57.1, "surveybench": null, "roasbench": 45.7, "bulletbench": 3.6}, {"rank": 26, "model": "zai-glm-5-3-flashx-legal", "model_name": "GLM-5.3 FlashX Legal", "developer": "Z.ai", "score": 34.0, "benchmarks": 5, "of": 5, "catalogbench": 4.4, "deckbench": 25.7, "surveybench": 42.3, "roasbench": 54.3, "bulletbench": 43.2}, {"rank": 26, "model": "deepseek-deepseek-v4-1-flash-1017", "model_name": "DeepSeek-V4.1-Flash-1017", "developer": "DeepSeek", "score": 33.7, "benchmarks": 5, "of": 5, "catalogbench": 14.0, "deckbench": 40.0, "surveybench": 57.7, "roasbench": 37.1, "bulletbench": 19.6}, {"rank": 29, "model": "inception-mercury-3", "model_name": "Mercury 3", "developer": "Inception", "score": 31.6, "benchmarks": 4, "of": 5, "catalogbench": null, "deckbench": 17.1, "surveybench": 23.1, "roasbench": 17.1, "bulletbench": 68.9}, {"rank": 30, "model": "google-gemini-3-5-flash-lite", "model_name": "Gemini 3.5 Flash-Lite", "developer": "Google", "score": 30.9, "benchmarks": 5, "of": 5, "catalogbench": 20.6, "deckbench": 8.6, "surveybench": 19.2, "roasbench": 11.4, "bulletbench": 94.6}, {"rank": 31, "model": "meta-muse-spark-1-3", "model_name": "Muse Spark 1.3", "developer": "Meta", "score": 23.5, "benchmarks": 4, "of": 5, "catalogbench": 44.9, "deckbench": 22.9, "surveybench": null, "roasbench": 22.9, "bulletbench": 3.6}, {"rank": 32, "model": "alibaba-qwen3-8-max-0902", "model_name": "Qwen3.8-Max (0902)", "developer": "Alibaba", "score": 23.3, "benchmarks": 3, "of": 5, "catalogbench": 18.4, "deckbench": 37.1, "surveybench": null, "roasbench": 14.3, "bulletbench": null}, {"rank": 33, "model": "mistral-mistral-large-4-0", "model_name": "Mistral Large 4", "developer": "Mistral AI", "score": 22.1, "benchmarks": 5, "of": 5, "catalogbench": 15.4, "deckbench": 5.7, "surveybench": 30.8, "roasbench": 28.6, "bulletbench": 30.0}, {"rank": 33, "model": "mistral-mistral-medium-3-5", "model_name": "Mistral Medium 3.5", "developer": "Mistral AI", "score": 21.9, "benchmarks": 5, "of": 5, "catalogbench": 27.9, "deckbench": 2.9, "surveybench": 7.7, "roasbench": 0.0, "bulletbench": 71.1}, {"rank": 35, "model": "anthropic-claude-haiku-4-5", "model_name": "Claude Haiku 4.5", "developer": "Anthropic", "score": 11.5, "benchmarks": 5, "of": 5, "catalogbench": 7.4, "deckbench": 11.4, "surveybench": 3.8, "roasbench": 2.9, "bulletbench": 32.0}]}