{"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": "2026-11-10-cad1a1ab581e", "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": "anthropic-claude-fable-5-2", "model_name": "Claude Fable 5.2", "developer": "Anthropic", "score": 90.4, "benchmarks": 5, "of": 5, "catalogbench": 85.2, "deckbench": 92.9, "surveybench": 100.0, "roasbench": 100.0, "bulletbench": 73.8}, {"rank": 1, "model": "openai-gpt-6-1-sol", "model_name": "GPT-6.1 Sol", "developer": "OpenAI", "score": 89.8, "benchmarks": 4, "of": 5, "catalogbench": 95.4, "deckbench": 89.3, "surveybench": 82.4, "roasbench": null, "bulletbench": 92.1}, {"rank": 3, "model": "openai-gpt-6-sol", "model_name": "GPT-6 Sol", "developer": "OpenAI", "score": 84.1, "benchmarks": 4, "of": 5, "catalogbench": 89.8, "deckbench": 96.4, "surveybench": null, "roasbench": 85.7, "bulletbench": 64.3}, {"rank": 3, "model": "openai-gpt-6-astra", "model_name": "GPT-6 Astra", "developer": "OpenAI", "score": 83.7, "benchmarks": 4, "of": 5, "catalogbench": 99.1, "deckbench": 100.0, "surveybench": null, "roasbench": 92.9, "bulletbench": 42.9}, {"rank": 5, "model": "anthropic-claude-opus-5-5", "model_name": "Claude Opus 5.5", "developer": "Anthropic", "score": 78.7, "benchmarks": 4, "of": 5, "catalogbench": 65.7, "deckbench": 85.7, "surveybench": 88.2, "roasbench": 75.0, "bulletbench": null}, {"rank": 6, "model": "openai-gpt-6-1-terra", "model_name": "GPT-6.1 Terra", "developer": "OpenAI", "score": 77.1, "benchmarks": 5, "of": 5, "catalogbench": 87.0, "deckbench": 78.6, "surveybench": 70.6, "roasbench": 96.4, "bulletbench": 52.8}, {"rank": 7, "model": "meta-muse-wonder", "model_name": "Muse Wonder", "developer": "Meta", "score": 66.6, "benchmarks": 5, "of": 5, "catalogbench": 85.2, "deckbench": 57.1, "surveybench": 94.1, "roasbench": 39.3, "bulletbench": 57.1}, {"rank": 8, "model": "openai-gpt-6-luna", "model_name": "GPT-6 Luna", "developer": "OpenAI", "score": 64.8, "benchmarks": 4, "of": 5, "catalogbench": 75.9, "deckbench": 67.9, "surveybench": null, "roasbench": 82.1, "bulletbench": 33.3}, {"rank": 9, "model": "anthropic-claude-fable-5-1", "model_name": "Claude Fable 5.1", "developer": "Anthropic", "score": 60.2, "benchmarks": 3, "of": 5, "catalogbench": 34.3, "deckbench": 75.0, "surveybench": null, "roasbench": 71.4, "bulletbench": null}, {"rank": 10, "model": "xai-grok-4-7", "model_name": "Grok 4.7", "developer": "xAI", "score": 56.2, "benchmarks": 3, "of": 5, "catalogbench": 72.2, "deckbench": 64.3, "surveybench": null, "roasbench": 32.1, "bulletbench": null}, {"rank": 11, "model": "anthropic-claude-sonnet-5-5", "model_name": "Claude Sonnet 5.5", "developer": "Anthropic", "score": 52.4, "benchmarks": 4, "of": 5, "catalogbench": 43.5, "deckbench": 82.1, "surveybench": null, "roasbench": 78.6, "bulletbench": 5.6}, {"rank": 12, "model": "google-gemini-3-1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "developer": "Google", "score": 48.6, "benchmarks": 5, "of": 5, "catalogbench": 55.6, "deckbench": 17.9, "surveybench": 35.3, "roasbench": 53.6, "bulletbench": 81.0}, {"rank": 13, "model": "google-gemini-3-8-flash", "model_name": "Gemini 3.8 Flash", "developer": "Google", "score": 48.0, "benchmarks": 4, "of": 5, "catalogbench": 38.0, "deckbench": 25.0, "surveybench": null, "roasbench": 67.9, "bulletbench": 61.1}, {"rank": 13, "model": "google-gemini-4-argon", "model_name": "Gemini 4 Argon", "developer": "Google", "score": 47.9, "benchmarks": 5, "of": 5, "catalogbench": 68.5, "deckbench": 35.7, "surveybench": 47.1, "roasbench": 64.3, "bulletbench": 23.8}, {"rank": 15, "model": "moonshotai-kimi-k3-1-pro", "model_name": "Kimi K3.1 Pro", "developer": "Moonshot AI", "score": 44.9, "benchmarks": 4, "of": 5, "catalogbench": null, "deckbench": 60.7, "surveybench": 5.9, "roasbench": 89.3, "bulletbench": 23.8}, {"rank": 16, "model": "anthropic-claude-haiku-5-5", "model_name": "Claude Haiku 5.5", "developer": "Anthropic", "score": 42.1, "benchmarks": 5, "of": 5, "catalogbench": 38.9, "deckbench": 50.0, "surveybench": 76.5, "roasbench": 7.1, "bulletbench": 38.1}, {"rank": 16, "model": "particle-ai-particle-1", "model_name": "Particle-1", "developer": "Particle AI", "score": 41.7, "benchmarks": 4, "of": 5, "catalogbench": 5.6, "deckbench": 46.4, "surveybench": 64.7, "roasbench": 50.0, "bulletbench": null}, {"rank": 18, "model": "minimax-minimax-m3-1-flash", "model_name": "MiniMax M3.1 Flash", "developer": "MiniMax", "score": 39.4, "benchmarks": 5, "of": 5, "catalogbench": 68.5, "deckbench": 71.4, "surveybench": 0.0, "roasbench": 42.9, "bulletbench": 14.3}, {"rank": 18, "model": "zai-glm-5-3-flashx-legal", "model_name": "GLM-5.3 FlashX Legal", "developer": "Z.ai", "score": 39.0, "benchmarks": 5, "of": 5, "catalogbench": 5.6, "deckbench": 28.6, "surveybench": 52.9, "roasbench": 60.7, "bulletbench": 47.2}, {"rank": 20, "model": "moonshotai-kimi-k3", "model_name": "Kimi K3", "developer": "Moonshot AI", "score": 38.1, "benchmarks": 4, "of": 5, "catalogbench": 37.0, "deckbench": 53.6, "surveybench": null, "roasbench": 57.1, "bulletbench": 4.8}, {"rank": 20, "model": "deepseek-deepseek-v4-1-flash-1017", "model_name": "DeepSeek-V4.1-Flash-1017", "developer": "DeepSeek", "score": 37.9, "benchmarks": 5, "of": 5, "catalogbench": 17.6, "deckbench": 42.9, "surveybench": 58.8, "roasbench": 46.4, "bulletbench": 23.8}, {"rank": 22, "model": "inception-mercury-3", "model_name": "Mercury 3", "developer": "Inception", "score": 37.0, "benchmarks": 4, "of": 5, "catalogbench": null, "deckbench": 21.4, "surveybench": 29.4, "roasbench": 21.4, "bulletbench": 75.8}, {"rank": 23, "model": "google-gemini-3-5-flash-lite", "model_name": "Gemini 3.5 Flash-Lite", "developer": "Google", "score": 33.9, "benchmarks": 5, "of": 5, "catalogbench": 25.9, "deckbench": 10.7, "surveybench": 23.5, "roasbench": 14.3, "bulletbench": 95.2}, {"rank": 24, "model": "meta-muse-spark-1-3", "model_name": "Muse Spark 1.3", "developer": "Meta", "score": 29.6, "benchmarks": 4, "of": 5, "catalogbench": 52.8, "deckbench": 32.1, "surveybench": null, "roasbench": 28.6, "bulletbench": 4.8}, {"rank": 25, "model": "mistral-mistral-large-4-0", "model_name": "Mistral Large 4", "developer": "Mistral AI", "score": 27.4, "benchmarks": 5, "of": 5, "catalogbench": 19.4, "deckbench": 7.1, "surveybench": 41.2, "roasbench": 35.7, "bulletbench": 33.3}, {"rank": 25, "model": "alibaba-qwen3-8-max-0902", "model_name": "Qwen3.8-Max (0902)", "developer": "Alibaba", "score": 26.8, "benchmarks": 3, "of": 5, "catalogbench": 23.1, "deckbench": 39.3, "surveybench": null, "roasbench": 17.9, "bulletbench": null}, {"rank": 27, "model": "mistral-mistral-medium-3-5", "model_name": "Mistral Medium 3.5", "developer": "Mistral AI", "score": 26.1, "benchmarks": 5, "of": 5, "catalogbench": 33.3, "deckbench": 3.6, "surveybench": 17.6, "roasbench": 0.0, "bulletbench": 76.2}, {"rank": 28, "model": "anthropic-claude-haiku-4-5", "model_name": "Claude Haiku 4.5", "developer": "Anthropic", "score": 14.8, "benchmarks": 5, "of": 5, "catalogbench": 9.3, "deckbench": 14.3, "surveybench": 11.8, "roasbench": 3.6, "bulletbench": 34.9}]}