{ "generatedAt": "2026-07-25", "benchmarks": { "robloxqa": { "name": "RobloxQA v2.0", "dataset": "https://huggingface.co/datasets/TorpedoSoftware/RobloxQA-v2.0", "description": "Knowledge testing. Question answering about Roblox and Luau.", "problemCounts": { "multipleChoice": 3000, "freeform": 3000 }, "topics": [ { "key": "classes", "label": "Engine classes", "n": 1157 }, { "key": "types", "label": "Enums & types", "n": 320 }, { "key": "luau", "label": "Luau", "n": 87 }, { "key": "scripting", "label": "Scripting & data", "n": 281 }, { "key": "gameplay", "label": "Gameplay systems", "n": 127 }, { "key": "visuals", "label": "Visuals & audio", "n": 116 }, { "key": "art", "label": "Art & avatars", "n": 162 }, { "key": "monetization", "label": "Monetization", "n": 198 }, { "key": "studio", "label": "Studio & tools", "n": 166 }, { "key": "learning", "label": "Tutorials", "n": 386 } ] }, "leetcode": { "name": "Luau Leetcode", "dataset": "https://huggingface.co/datasets/TorpedoSoftware/LuauLeetcode", "description": "Single shot code generation. Leetcode problems in Luau.", "problemCounts": { "easy": 47, "medium": 97, "hard": 64 } } }, "models": [ { "name": "Qwen 2.5 Coder 32B (Q4_K_M)", "provider": "Alibaba", "url": "https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct", "releaseDate": "2024-11-12", "size": 19851335840, "price": { "electricity": 0.2 }, "scores": { "robloxqa": { "freeform": { "correct": 1722, "noAnswer": 0, "inputTokens": 239246, "outputTokens": 157931, "kilowattHour": 0.838 }, "multipleChoice": { "correct": 2537, "noAnswer": 0, "inputTokens": 418468, "outputTokens": 553090, "kilowattHour": 1.808 }, "topics": { "classes": { "freeform": 632, "multipleChoice": 939 }, "types": { "freeform": 168, "multipleChoice": 270 }, "luau": { "freeform": 62, "multipleChoice": 75 }, "scripting": { "freeform": 165, "multipleChoice": 251 }, "gameplay": { "freeform": 50, "multipleChoice": 100 }, "visuals": { "freeform": 62, "multipleChoice": 98 }, "art": { "freeform": 76, "multipleChoice": 133 }, "monetization": { "freeform": 97, "multipleChoice": 153 }, "studio": { "freeform": 107, "multipleChoice": 150 }, "learning": { "freeform": 303, "multipleChoice": 368 } } }, "leetcode": { "easy": { "unitTestPassRate": 73.48, "fullPass": 26, "partialPass": 16, "fail": 5, "noCode": 0, "codeQuality": 86.8, "invalidSyntax": 2, "inputTokens": 20709, "outputTokens": 20645, "kilowattHour": 0.08 }, "medium": { "unitTestPassRate": 44.49, "fullPass": 21, "partialPass": 60, "fail": 16, "noCode": 0, "codeQuality": 84.8, "invalidSyntax": 2, "inputTokens": 51013, "outputTokens": 64070, "kilowattHour": 0.248 }, "hard": { "unitTestPassRate": 25.4, "fullPass": 4, "partialPass": 37, "fail": 23, "noCode": 0, "codeQuality": 76.2, "invalidSyntax": 3, "inputTokens": 32784, "outputTokens": 43817, "kilowattHour": 0.169 } } } }, { "name": "Qwen 3 4B Instruct 2507 (Q8_0)", "provider": "Alibaba", "url": "https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507", "releaseDate": "2025-08-06", "size": 4280405600, "price": { "electricity": 0.2 }, "scores": { "robloxqa": { "freeform": { "correct": 1401, "noAnswer": 0, "inputTokens": 239246, "outputTokens": 182527, "kilowattHour": 0.337 }, "multipleChoice": { "correct": 2464, "noAnswer": 0, "inputTokens": 418468, "outputTokens": 754052, "kilowattHour": 0.624 }, "topics": { "classes": { "freeform": 509, "multipleChoice": 923 }, "types": { "freeform": 151, "multipleChoice": 263 }, "luau": { "freeform": 48, "multipleChoice": 72 }, "scripting": { "freeform": 143, "multipleChoice": 245 }, "gameplay": { "freeform": 34, "multipleChoice": 88 }, "visuals": { "freeform": 45, "multipleChoice": 89 }, "art": { "freeform": 54, "multipleChoice": 132 }, "monetization": { "freeform": 75, "multipleChoice": 154 }, "studio": { "freeform": 79, "multipleChoice": 143 }, "learning": { "freeform": 263, "multipleChoice": 355 } } }, "leetcode": { "easy": { "unitTestPassRate": 52.08, "fullPass": 18, "partialPass": 16, "fail": 13, "noCode": 0, "codeQuality": 85.7, "invalidSyntax": 3, "inputTokens": 20709, "outputTokens": 23992, "kilowattHour": 0.021 }, "medium": { "unitTestPassRate": 25.41, "fullPass": 8, "partialPass": 38, "fail": 51, "noCode": 0, "codeQuality": 66.0, "invalidSyntax": 18, "inputTokens": 51013, "outputTokens": 149168, "kilowattHour": 0.132 }, "hard": { "unitTestPassRate": 17.34, "fullPass": 6, "partialPass": 22, "fail": 36, "noCode": 0, "codeQuality": 61.5, "invalidSyntax": 13, "inputTokens": 32784, "outputTokens": 119708, "kilowattHour": 0.106 } } } }, { "name": "Qwen 3 Coder 30B-A3B", "provider": "Alibaba", "url": "https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct", "releaseDate": "2025-07-31", "size": 61064245248, "price": { "input": 0.07, "output": 1.43 }, "scores": { "robloxqa": { "freeform": { "correct": 1705, "noAnswer": 0, "inputTokens": 239246, "outputTokens": 362822 }, "multipleChoice": { "correct": 2551, "noAnswer": 0, "inputTokens": 418468, "outputTokens": 789209 }, "topics": { "classes": { "freeform": 613, "multipleChoice": 945 }, "types": { "freeform": 184, "multipleChoice": 272 }, "luau": { "freeform": 65, "multipleChoice": 80 }, "scripting": { "freeform": 167, "multipleChoice": 247 }, "gameplay": { "freeform": 54, "multipleChoice": 107 }, "visuals": { "freeform": 57, "multipleChoice": 95 }, "art": { "freeform": 71, "multipleChoice": 131 }, "monetization": { "freeform": 92, "multipleChoice": 161 }, "studio": { "freeform": 109, "multipleChoice": 148 }, "learning": { "freeform": 293, "multipleChoice": 365 } } }, "leetcode": { "easy": { "unitTestPassRate": 90.08, "fullPass": 38, "partialPass": 7, "fail": 1, "noCode": 1, "codeQuality": 89.9, "invalidSyntax": 1, "inputTokens": 20709, "outputTokens": 102566 }, "medium": { "unitTestPassRate": 59.02, "fullPass": 34, "partialPass": 44, "fail": 17, "noCode": 2, "codeQuality": 76.0, "invalidSyntax": 4, "inputTokens": 51013, "outputTokens": 226333 }, "hard": { "unitTestPassRate": 41.78, "fullPass": 7, "partialPass": 40, "fail": 17, "noCode": 0, "codeQuality": 72.4, "invalidSyntax": 5, "inputTokens": 32784, "outputTokens": 191231 } } } }, { "name": "Qwen 3.5 9B", "provider": "Alibaba", "url": "https://huggingface.co/Qwen/Qwen3.5-9B", "releaseDate": "2026-03-02", "size": 19306216416, "price": { "input": 0.1, "output": 0.16949 }, "scores": { "robloxqa": { "freeform": { "correct": 1183, "noAnswer": 1217, "inputTokens": 245296, "outputTokens": 79341379 }, "multipleChoice": { "correct": 2235, "noAnswer": 492, "inputTokens": 433181, "outputTokens": 35971658 }, "topics": { "classes": { "freeform": 364, "multipleChoice": 781 }, "types": { "freeform": 125, "multipleChoice": 235 }, "luau": { "freeform": 51, "multipleChoice": 72 }, "scripting": { "freeform": 124, "multipleChoice": 231 }, "gameplay": { "freeform": 36, "multipleChoice": 75 }, "visuals": { "freeform": 37, "multipleChoice": 78 }, "art": { "freeform": 52, "multipleChoice": 121 }, "monetization": { "freeform": 64, "multipleChoice": 148 }, "studio": { "freeform": 80, "multipleChoice": 145 }, "learning": { "freeform": 250, "multipleChoice": 349 } } }, "leetcode": { "easy": { "unitTestPassRate": 51.99, "fullPass": 22, "partialPass": 5, "fail": 12, "noCode": 8, "codeQuality": 75.2, "invalidSyntax": 2, "inputTokens": 21828, "outputTokens": 574446 }, "medium": { "unitTestPassRate": 22.46, "fullPass": 16, "partialPass": 10, "fail": 25, "noCode": 46, "codeQuality": 41.6, "invalidSyntax": 6, "inputTokens": 53591, "outputTokens": 3113317 }, "hard": { "unitTestPassRate": 7.2, "fullPass": 2, "partialPass": 6, "fail": 8, "noCode": 48, "codeQuality": 15.7, "invalidSyntax": 4, "inputTokens": 34446, "outputTokens": 3197505 } } } }, { "name": "Qwen 3.6 27B", "provider": "Alibaba", "url": "https://huggingface.co/Qwen/Qwen3.6-27B", "releaseDate": "2026-04-22", "size": 55562855904, "price": { "input": 0.289, "output": 2.7573 }, "scores": { "robloxqa": { "freeform": { "correct": 2042, "noAnswer": 5, "inputTokens": 245241, "outputTokens": 3366161 }, "multipleChoice": { "correct": 2697, "noAnswer": 46, "inputTokens": 433158, "outputTokens": 4368786 }, "topics": { "classes": { "freeform": 730, "multipleChoice": 1006 }, "types": { "freeform": 215, "multipleChoice": 287 }, "luau": { "freeform": 67, "multipleChoice": 79 }, "scripting": { "freeform": 206, "multipleChoice": 257 }, "gameplay": { "freeform": 65, "multipleChoice": 104 }, "visuals": { "freeform": 74, "multipleChoice": 104 }, "art": { "freeform": 97, "multipleChoice": 155 }, "monetization": { "freeform": 114, "multipleChoice": 172 }, "studio": { "freeform": 129, "multipleChoice": 160 }, "learning": { "freeform": 345, "multipleChoice": 373 } } }, "leetcode": { "easy": { "unitTestPassRate": 90.36, "fullPass": 41, "partialPass": 3, "fail": 2, "noCode": 1, "codeQuality": 88.5, "invalidSyntax": 2, "inputTokens": 21828, "outputTokens": 178968 }, "medium": { "unitTestPassRate": 69.13, "fullPass": 49, "partialPass": 22, "fail": 17, "noCode": 9, "codeQuality": 72.9, "invalidSyntax": 7, "inputTokens": 53591, "outputTokens": 1010606 }, "hard": { "unitTestPassRate": 46.29, "fullPass": 17, "partialPass": 17, "fail": 17, "noCode": 13, "codeQuality": 59.5, "invalidSyntax": 6, "inputTokens": 34380, "outputTokens": 911399 } } } }, { "name": "Qwen 3.6 35B-A3B", "provider": "Alibaba", "url": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "releaseDate": "2026-04-16", "size": 71903645408, "price": { "input": 0.14, "output": 1.0747 }, "scores": { "robloxqa": { "freeform": { "correct": 1978, "noAnswer": 0, "inputTokens": 245234, "outputTokens": 4083237 }, "multipleChoice": { "correct": 2693, "noAnswer": 1, "inputTokens": 433158, "outputTokens": 3511454 }, "topics": { "classes": { "freeform": 699, "multipleChoice": 1010 }, "types": { "freeform": 204, "multipleChoice": 281 }, "luau": { "freeform": 64, "multipleChoice": 80 }, "scripting": { "freeform": 197, "multipleChoice": 261 }, "gameplay": { "freeform": 72, "multipleChoice": 103 }, "visuals": { "freeform": 72, "multipleChoice": 106 }, "art": { "freeform": 99, "multipleChoice": 148 }, "monetization": { "freeform": 107, "multipleChoice": 170 }, "studio": { "freeform": 126, "multipleChoice": 161 }, "learning": { "freeform": 338, "multipleChoice": 373 } } }, "leetcode": { "easy": { "unitTestPassRate": 94.36, "fullPass": 42, "partialPass": 4, "fail": 1, "noCode": 0, "codeQuality": 95.2, "invalidSyntax": 1, "inputTokens": 21828, "outputTokens": 214906 }, "medium": { "unitTestPassRate": 70.06, "fullPass": 50, "partialPass": 24, "fail": 21, "noCode": 2, "codeQuality": 73.9, "invalidSyntax": 14, "inputTokens": 53591, "outputTokens": 1049662 }, "hard": { "unitTestPassRate": 37.3, "fullPass": 12, "partialPass": 25, "fail": 24, "noCode": 3, "codeQuality": 53.7, "invalidSyntax": 18, "inputTokens": 34446, "outputTokens": 1028336 } } } }, { "name": "Claude Fable 5 (Medium)", "provider": "Anthropic", "url": "https://www.anthropic.com/claude/fable", "releaseDate": "2026-06-09", "size": null, "price": { "input": 10, "output": 50 }, "scores": { "robloxqa": { "freeform": { "correct": 2615, "noAnswer": 34, "inputTokens": 322087, "outputTokens": 419423 }, "multipleChoice": { "correct": 2909, "noAnswer": 27, "inputTokens": 594072, "outputTokens": 185583 }, "topics": { "classes": { "freeform": 1012, "multipleChoice": 1123 }, "types": { "freeform": 278, "multipleChoice": 312 }, "luau": { "freeform": 79, "multipleChoice": 86 }, "scripting": { "freeform": 237, "multipleChoice": 268 }, "gameplay": { "freeform": 106, "multipleChoice": 122 }, "visuals": { "freeform": 103, "multipleChoice": 113 }, "art": { "freeform": 133, "multipleChoice": 155 }, "monetization": { "freeform": 154, "multipleChoice": 188 }, "studio": { "freeform": 146, "multipleChoice": 159 }, "learning": { "freeform": 367, "multipleChoice": 383 } } }, "leetcode": { "easy": { "unitTestPassRate": 97.08, "fullPass": 44, "partialPass": 3, "fail": 0, "noCode": 0, "codeQuality": 99.6, "invalidSyntax": 0, "inputTokens": 27243, "outputTokens": 8570 }, "medium": { "unitTestPassRate": 98.38, "fullPass": 84, "partialPass": 13, "fail": 0, "noCode": 0, "codeQuality": 96.6, "invalidSyntax": 0, "inputTokens": 68243, "outputTokens": 68974 }, "hard": { "unitTestPassRate": 93.05, "fullPass": 49, "partialPass": 13, "fail": 2, "noCode": 0, "codeQuality": 93.6, "invalidSyntax": 0, "inputTokens": 43473, "outputTokens": 150372 } } } }, { "name": "Claude Haiku 4.5 (Extended Thinking)", "provider": "Anthropic", "url": "https://www.anthropic.com/claude/haiku", "releaseDate": "2025-10-15", "size": null, "price": { "input": 1, "output": 5 }, "scores": { "robloxqa": { "freeform": { "correct": 2032, "noAnswer": 0, "inputTokens": 335763, "outputTokens": 1044209 }, "multipleChoice": { "correct": 2685, "noAnswer": 0, "inputTokens": 535399, "outputTokens": 2130172 }, "topics": { "classes": { "freeform": 737, "multipleChoice": 1012 }, "types": { "freeform": 205, "multipleChoice": 288 }, "luau": { "freeform": 66, "multipleChoice": 81 }, "scripting": { "freeform": 202, "multipleChoice": 262 }, "gameplay": { "freeform": 68, "multipleChoice": 104 }, "visuals": { "freeform": 78, "multipleChoice": 106 }, "art": { "freeform": 101, "multipleChoice": 146 }, "monetization": { "freeform": 106, "multipleChoice": 156 }, "studio": { "freeform": 124, "multipleChoice": 158 }, "learning": { "freeform": 345, "multipleChoice": 372 } } }, "leetcode": { "easy": { "unitTestPassRate": 95.56, "fullPass": 43, "partialPass": 4, "fail": 0, "noCode": 0, "codeQuality": 96.2, "invalidSyntax": 0, "inputTokens": 23707, "outputTokens": 96163 }, "medium": { "unitTestPassRate": 80.77, "fullPass": 54, "partialPass": 32, "fail": 11, "noCode": 0, "codeQuality": 90.3, "invalidSyntax": 3, "inputTokens": 58625, "outputTokens": 317612 }, "hard": { "unitTestPassRate": 64.32, "fullPass": 27, "partialPass": 23, "fail": 14, "noCode": 0, "codeQuality": 88.9, "invalidSyntax": 2, "inputTokens": 37666, "outputTokens": 224090 } } } }, { "name": "Claude Opus 4.8 (Medium)", "provider": "Anthropic", "url": "https://www.anthropic.com/claude/opus", "releaseDate": "2026-05-28", "size": null, "price": { "input": 5, "output": 25 }, "scores": { "robloxqa": { "freeform": { "correct": 2486, "noAnswer": 0, "inputTokens": 322040, "outputTokens": 323578 }, "multipleChoice": { "correct": 2900, "noAnswer": 0, "inputTokens": 594072, "outputTokens": 94349 }, "topics": { "classes": { "freeform": 942, "multipleChoice": 1118 }, "types": { "freeform": 262, "multipleChoice": 306 }, "luau": { "freeform": 81, "multipleChoice": 86 }, "scripting": { "freeform": 238, "multipleChoice": 274 }, "gameplay": { "freeform": 101, "multipleChoice": 120 }, "visuals": { "freeform": 94, "multipleChoice": 110 }, "art": { "freeform": 119, "multipleChoice": 157 }, "monetization": { "freeform": 136, "multipleChoice": 184 }, "studio": { "freeform": 143, "multipleChoice": 163 }, "learning": { "freeform": 370, "multipleChoice": 382 } } }, "leetcode": { "easy": { "unitTestPassRate": 97.08, "fullPass": 44, "partialPass": 3, "fail": 0, "noCode": 0, "codeQuality": 99.7, "invalidSyntax": 0, "inputTokens": 27243, "outputTokens": 9412 }, "medium": { "unitTestPassRate": 92.5, "fullPass": 75, "partialPass": 17, "fail": 5, "noCode": 0, "codeQuality": 95.8, "invalidSyntax": 2, "inputTokens": 68243, "outputTokens": 131649 }, "hard": { "unitTestPassRate": 88.06, "fullPass": 47, "partialPass": 11, "fail": 6, "noCode": 0, "codeQuality": 94.2, "invalidSyntax": 1, "inputTokens": 47661, "outputTokens": 360836 } } } }, { "name": "Claude Opus 5 (Medium)", "provider": "Anthropic", "url": "https://www.anthropic.com/claude/opus", "releaseDate": "2026-07-24", "size": null, "price": { "input": 5, "output": 25 }, "scores": { "robloxqa": { "freeform": { "correct": 2570, "noAnswer": 4, "inputTokens": 322040, "outputTokens": 930410 }, "multipleChoice": { "correct": 2925, "noAnswer": 2, "inputTokens": 594072, "outputTokens": 372368 }, "topics": { "classes": { "freeform": 985, "multipleChoice": 1131 }, "types": { "freeform": 271, "multipleChoice": 310 }, "luau": { "freeform": 79, "multipleChoice": 85 }, "scripting": { "freeform": 241, "multipleChoice": 276 }, "gameplay": { "freeform": 106, "multipleChoice": 121 }, "visuals": { "freeform": 99, "multipleChoice": 114 }, "art": { "freeform": 128, "multipleChoice": 157 }, "monetization": { "freeform": 141, "multipleChoice": 188 }, "studio": { "freeform": 149, "multipleChoice": 162 }, "learning": { "freeform": 371, "multipleChoice": 381 } } }, "leetcode": { "easy": { "unitTestPassRate": 97.08, "fullPass": 44, "partialPass": 3, "fail": 0, "noCode": 0, "codeQuality": 99.7, "invalidSyntax": 0, "inputTokens": 27243, "outputTokens": 11107 }, "medium": { "unitTestPassRate": 96.73, "fullPass": 80, "partialPass": 17, "fail": 0, "noCode": 0, "codeQuality": 96.2, "invalidSyntax": 0, "inputTokens": 68243, "outputTokens": 89446 }, "hard": { "unitTestPassRate": 90.86, "fullPass": 47, "partialPass": 13, "fail": 4, "noCode": 0, "codeQuality": 95.3, "invalidSyntax": 0, "inputTokens": 43473, "outputTokens": 166051 } } } }, { "name": "Claude Sonnet 4 (Medium)", "provider": "Anthropic", "url": "https://www.anthropic.com/claude/sonnet", "releaseDate": "2025-05-22", "size": null, "price": { "input": 3, "output": 15 }, "scores": { "robloxqa": { "freeform": { "correct": 2190, "noAnswer": 0, "inputTokens": 335763, "outputTokens": 882703 }, "multipleChoice": { "correct": 2770, "noAnswer": 0, "inputTokens": 535399, "outputTokens": 2085669 }, "topics": { "classes": { "freeform": 811, "multipleChoice": 1054 }, "types": { "freeform": 232, "multipleChoice": 288 }, "luau": { "freeform": 72, "multipleChoice": 81 }, "scripting": { "freeform": 214, "multipleChoice": 268 }, "gameplay": { "freeform": 83, "multipleChoice": 111 }, "visuals": { "freeform": 88, "multipleChoice": 107 }, "art": { "freeform": 98, "multipleChoice": 153 }, "monetization": { "freeform": 113, "multipleChoice": 171 }, "studio": { "freeform": 132, "multipleChoice": 160 }, "learning": { "freeform": 347, "multipleChoice": 377 } } }, "leetcode": { "easy": { "unitTestPassRate": 91.04, "fullPass": 40, "partialPass": 5, "fail": 2, "noCode": 0, "codeQuality": 89.7, "invalidSyntax": 2, "inputTokens": 23707, "outputTokens": 197077 }, "medium": { "unitTestPassRate": 88.17, "fullPass": 68, "partialPass": 21, "fail": 8, "noCode": 0, "codeQuality": 84.9, "invalidSyntax": 3, "inputTokens": 58625, "outputTokens": 816953 }, "hard": { "unitTestPassRate": 70.8, "fullPass": 34, "partialPass": 17, "fail": 13, "noCode": 0, "codeQuality": 76.6, "invalidSyntax": 5, "inputTokens": 37666, "outputTokens": 698459 } } } }, { "name": "Claude Sonnet 5 (Medium)", "provider": "Anthropic", "url": "https://www.anthropic.com/claude/sonnet", "releaseDate": "2026-06-30", "size": null, "price": { "input": 2, "output": 10 }, "scores": { "robloxqa": { "freeform": { "correct": 2409, "noAnswer": 0, "inputTokens": 322040, "outputTokens": 282788 }, "multipleChoice": { "correct": 2819, "noAnswer": 0, "inputTokens": 594072, "outputTokens": 34592 }, "topics": { "classes": { "freeform": 896, "multipleChoice": 1071 }, "types": { "freeform": 260, "multipleChoice": 298 }, "luau": { "freeform": 79, "multipleChoice": 85 }, "scripting": { "freeform": 232, "multipleChoice": 270 }, "gameplay": { "freeform": 88, "multipleChoice": 117 }, "visuals": { "freeform": 89, "multipleChoice": 106 }, "art": { "freeform": 117, "multipleChoice": 154 }, "monetization": { "freeform": 133, "multipleChoice": 179 }, "studio": { "freeform": 147, "multipleChoice": 161 }, "learning": { "freeform": 368, "multipleChoice": 378 } } }, "leetcode": { "easy": { "unitTestPassRate": 93.76, "fullPass": 41, "partialPass": 5, "fail": 1, "noCode": 0, "codeQuality": 95.0, "invalidSyntax": 1, "inputTokens": 27243, "outputTokens": 11663 }, "medium": { "unitTestPassRate": 90.44, "fullPass": 69, "partialPass": 25, "fail": 3, "noCode": 0, "codeQuality": 95.2, "invalidSyntax": 1, "inputTokens": 69545, "outputTokens": 212537 }, "hard": { "unitTestPassRate": 77.45, "fullPass": 32, "partialPass": 26, "fail": 6, "noCode": 0, "codeQuality": 92.2, "invalidSyntax": 2, "inputTokens": 49463, "outputTokens": 461804 } } } }, { "name": "Deepseek R1 0528", "provider": "DeepSeek", "url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "releaseDate": "2025-05-28", "size": 1369062772000, "price": { "input": 0.5, "output": 2.18 }, "scores": { "robloxqa": { "freeform": { "correct": 2043, "noAnswer": 0, "inputTokens": 216371, "outputTokens": 1029639 }, "multipleChoice": { "correct": 2676, "noAnswer": 0, "inputTokens": 397218, "outputTokens": 3450188 }, "topics": { "classes": { "freeform": 747, "multipleChoice": 1011 }, "types": { "freeform": 216, "multipleChoice": 284 }, "luau": { "freeform": 66, "multipleChoice": 80 }, "scripting": { "freeform": 199, "multipleChoice": 257 }, "gameplay": { "freeform": 70, "multipleChoice": 103 }, "visuals": { "freeform": 78, "multipleChoice": 104 }, "art": { "freeform": 98, "multipleChoice": 145 }, "monetization": { "freeform": 106, "multipleChoice": 162 }, "studio": { "freeform": 125, "multipleChoice": 160 }, "learning": { "freeform": 338, "multipleChoice": 370 } } }, "leetcode": { "easy": { "unitTestPassRate": 92.61, "fullPass": 41, "partialPass": 4, "fail": 1, "noCode": 1, "codeQuality": 84.0, "invalidSyntax": 1, "inputTokens": 19895, "outputTokens": 252818 }, "medium": { "unitTestPassRate": 78.87, "fullPass": 61, "partialPass": 22, "fail": 12, "noCode": 2, "codeQuality": 72.6, "invalidSyntax": 6, "inputTokens": 49614, "outputTokens": 1251919 }, "hard": { "unitTestPassRate": 57.2, "fullPass": 22, "partialPass": 23, "fail": 11, "noCode": 8, "codeQuality": 56.3, "invalidSyntax": 5, "inputTokens": 31754, "outputTokens": 1147793 } } } }, { "name": "Deepseek V4 Flash", "provider": "DeepSeek", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash", "releaseDate": "2026-04-24", "size": 159609485896, "price": { "input": 0.098, "output": 0.24458 }, "scores": { "robloxqa": { "freeform": { "correct": 2153, "noAnswer": 0, "inputTokens": 216601, "outputTokens": 603615 }, "multipleChoice": { "correct": 2717, "noAnswer": 0, "inputTokens": 397210, "outputTokens": 1105987 }, "topics": { "classes": { "freeform": 780, "multipleChoice": 1019 }, "types": { "freeform": 231, "multipleChoice": 285 }, "luau": { "freeform": 72, "multipleChoice": 83 }, "scripting": { "freeform": 215, "multipleChoice": 265 }, "gameplay": { "freeform": 75, "multipleChoice": 108 }, "visuals": { "freeform": 79, "multipleChoice": 101 }, "art": { "freeform": 99, "multipleChoice": 149 }, "monetization": { "freeform": 119, "multipleChoice": 173 }, "studio": { "freeform": 130, "multipleChoice": 158 }, "learning": { "freeform": 353, "multipleChoice": 376 } } }, "leetcode": { "easy": { "unitTestPassRate": 90.69, "fullPass": 41, "partialPass": 3, "fail": 3, "noCode": 0, "codeQuality": 94.2, "invalidSyntax": 2, "inputTokens": 19950, "outputTokens": 59465 }, "medium": { "unitTestPassRate": 73.97, "fullPass": 58, "partialPass": 19, "fail": 20, "noCode": 0, "codeQuality": 82.0, "invalidSyntax": 9, "inputTokens": 49568, "outputTokens": 539899 }, "hard": { "unitTestPassRate": 42.11, "fullPass": 20, "partialPass": 11, "fail": 32, "noCode": 1, "codeQuality": 65.0, "invalidSyntax": 13, "inputTokens": 31666, "outputTokens": 687885 } } } }, { "name": "Gemini 2.5 Pro (Medium)", "provider": "Google", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro", "releaseDate": "2025-06-17", "size": null, "price": { "input": 1.25, "output": 10 }, "scores": { "robloxqa": { "freeform": { "correct": 2178, "noAnswer": 0, "inputTokens": 199629, "outputTokens": 2317472 }, "multipleChoice": { "correct": 2785, "noAnswer": 0, "inputTokens": 394248, "outputTokens": 3995205 }, "topics": { "classes": { "freeform": 804, "multipleChoice": 1048 }, "types": { "freeform": 222, "multipleChoice": 296 }, "luau": { "freeform": 72, "multipleChoice": 82 }, "scripting": { "freeform": 210, "multipleChoice": 264 }, "gameplay": { "freeform": 87, "multipleChoice": 115 }, "visuals": { "freeform": 80, "multipleChoice": 109 }, "art": { "freeform": 99, "multipleChoice": 152 }, "monetization": { "freeform": 122, "multipleChoice": 180 }, "studio": { "freeform": 135, "multipleChoice": 162 }, "learning": { "freeform": 347, "multipleChoice": 377 } } }, "leetcode": { "easy": { "unitTestPassRate": 94.95, "fullPass": 43, "partialPass": 3, "fail": 1, "noCode": 0, "codeQuality": 98.9, "invalidSyntax": 0, "inputTokens": 21524, "outputTokens": 232143 }, "medium": { "unitTestPassRate": 87.78, "fullPass": 64, "partialPass": 27, "fail": 6, "noCode": 0, "codeQuality": 88.1, "invalidSyntax": 4, "inputTokens": 53188, "outputTokens": 1065697 }, "hard": { "unitTestPassRate": 67.55, "fullPass": 29, "partialPass": 21, "fail": 14, "noCode": 0, "codeQuality": 78.9, "invalidSyntax": 7, "inputTokens": 34116, "outputTokens": 1135807 } } } }, { "name": "Gemini 3.1 Pro (Medium)", "provider": "Google", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview", "releaseDate": "2026-02-19", "size": null, "price": { "input": 2, "output": 12.01 }, "scores": { "robloxqa": { "freeform": { "correct": 2427, "noAnswer": 0, "inputTokens": 199629, "outputTokens": 1610007 }, "multipleChoice": { "correct": 2896, "noAnswer": 5, "inputTokens": 394248, "outputTokens": 5014795 }, "topics": { "classes": { "freeform": 919, "multipleChoice": 1106 }, "types": { "freeform": 250, "multipleChoice": 308 }, "luau": { "freeform": 79, "multipleChoice": 85 }, "scripting": { "freeform": 233, "multipleChoice": 277 }, "gameplay": { "freeform": 99, "multipleChoice": 118 }, "visuals": { "freeform": 93, "multipleChoice": 109 }, "art": { "freeform": 112, "multipleChoice": 156 }, "monetization": { "freeform": 142, "multipleChoice": 190 }, "studio": { "freeform": 141, "multipleChoice": 164 }, "learning": { "freeform": 359, "multipleChoice": 383 } } }, "leetcode": { "easy": { "unitTestPassRate": 95.05, "fullPass": 43, "partialPass": 4, "fail": 0, "noCode": 0, "codeQuality": 97.7, "invalidSyntax": 0, "inputTokens": 21524, "outputTokens": 72196 }, "medium": { "unitTestPassRate": 95.7, "fullPass": 79, "partialPass": 17, "fail": 1, "noCode": 0, "codeQuality": 84.2, "invalidSyntax": 1, "inputTokens": 53188, "outputTokens": 366555 }, "hard": { "unitTestPassRate": 93.59, "fullPass": 50, "partialPass": 11, "fail": 3, "noCode": 0, "codeQuality": 79.1, "invalidSyntax": 0, "inputTokens": 34116, "outputTokens": 414988 } } } }, { "name": "Gemma 3 27B", "provider": "Google", "url": "https://huggingface.co/google/gemma-3-27b-it", "releaseDate": "2025-03-12", "size": 54864813280, "price": { "input": 0.08, "output": 0.37514 }, "scores": { "robloxqa": { "freeform": { "correct": 1720, "noAnswer": 0, "inputTokens": 225213, "outputTokens": 219150 }, "multipleChoice": { "correct": 2536, "noAnswer": 0, "inputTokens": 420584, "outputTokens": 740270 }, "topics": { "classes": { "freeform": 594, "multipleChoice": 946 }, "types": { "freeform": 175, "multipleChoice": 256 }, "luau": { "freeform": 46, "multipleChoice": 72 }, "scripting": { "freeform": 178, "multipleChoice": 256 }, "gameplay": { "freeform": 59, "multipleChoice": 96 }, "visuals": { "freeform": 61, "multipleChoice": 98 }, "art": { "freeform": 80, "multipleChoice": 138 }, "monetization": { "freeform": 95, "multipleChoice": 159 }, "studio": { "freeform": 112, "multipleChoice": 156 }, "learning": { "freeform": 320, "multipleChoice": 359 } } }, "leetcode": { "easy": { "unitTestPassRate": 47.23, "fullPass": 15, "partialPass": 13, "fail": 19, "noCode": 0, "codeQuality": 87.0, "invalidSyntax": 4, "inputTokens": 21900, "outputTokens": 9501 }, "medium": { "unitTestPassRate": 25.38, "fullPass": 13, "partialPass": 30, "fail": 54, "noCode": 0, "codeQuality": 65.7, "invalidSyntax": 24, "inputTokens": 53968, "outputTokens": 36512 }, "hard": { "unitTestPassRate": 20.52, "fullPass": 6, "partialPass": 20, "fail": 38, "noCode": 0, "codeQuality": 58.6, "invalidSyntax": 22, "inputTokens": 34628, "outputTokens": 24815 } } } }, { "name": "Gemma 4 26B-A4B", "provider": "Google", "url": "https://huggingface.co/google/gemma-4-26B-A4B", "releaseDate": "2026-04-02", "size": 51611872412, "price": { "input": 0.12, "output": 0.3882 }, "scores": { "robloxqa": { "freeform": { "correct": 1996, "noAnswer": 0, "inputTokens": 268020, "outputTokens": 157880 }, "multipleChoice": { "correct": 2728, "noAnswer": 0, "inputTokens": 465984, "outputTokens": 1067741 }, "topics": { "classes": { "freeform": 717, "multipleChoice": 1022 }, "types": { "freeform": 201, "multipleChoice": 290 }, "luau": { "freeform": 62, "multipleChoice": 79 }, "scripting": { "freeform": 200, "multipleChoice": 261 }, "gameplay": { "freeform": 80, "multipleChoice": 114 }, "visuals": { "freeform": 78, "multipleChoice": 107 }, "art": { "freeform": 85, "multipleChoice": 148 }, "monetization": { "freeform": 100, "multipleChoice": 170 }, "studio": { "freeform": 124, "multipleChoice": 158 }, "learning": { "freeform": 349, "multipleChoice": 379 } } }, "leetcode": { "easy": { "unitTestPassRate": 61.75, "fullPass": 27, "partialPass": 4, "fail": 16, "noCode": 0, "codeQuality": 73.7, "invalidSyntax": 12, "inputTokens": 22873, "outputTokens": 37516 }, "medium": { "unitTestPassRate": 54.83, "fullPass": 44, "partialPass": 16, "fail": 36, "noCode": 1, "codeQuality": 86.0, "invalidSyntax": 5, "inputTokens": 55225, "outputTokens": 295668 }, "hard": { "unitTestPassRate": 27.63, "fullPass": 10, "partialPass": 14, "fail": 39, "noCode": 1, "codeQuality": 68.6, "invalidSyntax": 9, "inputTokens": 35820, "outputTokens": 351811 } } } }, { "name": "Gemma 4 31B", "provider": "Google", "url": "https://huggingface.co/google/gemma-4-31B", "releaseDate": "2026-04-02", "size": 62546177752, "price": { "input": 0.14, "output": 0.4256 }, "scores": { "robloxqa": { "freeform": { "correct": 2156, "noAnswer": 0, "inputTokens": 280989, "outputTokens": 142754 }, "multipleChoice": { "correct": 2777, "noAnswer": 0, "inputTokens": 471922, "outputTokens": 798907 }, "topics": { "classes": { "freeform": 795, "multipleChoice": 1056 }, "types": { "freeform": 220, "multipleChoice": 292 }, "luau": { "freeform": 66, "multipleChoice": 80 }, "scripting": { "freeform": 210, "multipleChoice": 261 }, "gameplay": { "freeform": 83, "multipleChoice": 114 }, "visuals": { "freeform": 81, "multipleChoice": 106 }, "art": { "freeform": 97, "multipleChoice": 152 }, "monetization": { "freeform": 118, "multipleChoice": 174 }, "studio": { "freeform": 129, "multipleChoice": 161 }, "learning": { "freeform": 357, "multipleChoice": 381 } } }, "leetcode": { "easy": { "unitTestPassRate": 82.99, "fullPass": 37, "partialPass": 5, "fail": 5, "noCode": 0, "codeQuality": 92.0, "invalidSyntax": 3, "inputTokens": 22895, "outputTokens": 20959 }, "medium": { "unitTestPassRate": 69.17, "fullPass": 52, "partialPass": 24, "fail": 21, "noCode": 0, "codeQuality": 80.9, "invalidSyntax": 9, "inputTokens": 56157, "outputTokens": 88193 }, "hard": { "unitTestPassRate": 61.61, "fullPass": 26, "partialPass": 24, "fail": 14, "noCode": 0, "codeQuality": 71.6, "invalidSyntax": 5, "inputTokens": 35864, "outputTokens": 101060 } } } }, { "name": "Llama 3.1 8B Instruct", "provider": "Meta", "url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "releaseDate": "2024-07-23", "size": 16060522496, "price": { "input": 0.05, "output": 0.071899 }, "scores": { "robloxqa": { "freeform": { "correct": 1443, "noAnswer": 0, "inputTokens": 304283, "outputTokens": 528316 }, "multipleChoice": { "correct": 2362, "noAnswer": 4, "inputTokens": 483150, "outputTokens": 1762943 }, "topics": { "classes": { "freeform": 523, "multipleChoice": 863 }, "types": { "freeform": 158, "multipleChoice": 259 }, "luau": { "freeform": 47, "multipleChoice": 65 }, "scripting": { "freeform": 145, "multipleChoice": 217 }, "gameplay": { "freeform": 36, "multipleChoice": 95 }, "visuals": { "freeform": 40, "multipleChoice": 91 }, "art": { "freeform": 56, "multipleChoice": 133 }, "monetization": { "freeform": 86, "multipleChoice": 142 }, "studio": { "freeform": 93, "multipleChoice": 148 }, "learning": { "freeform": 259, "multipleChoice": 349 } } }, "leetcode": { "easy": { "unitTestPassRate": 40.12, "fullPass": 11, "partialPass": 26, "fail": 8, "noCode": 2, "codeQuality": 80.0, "invalidSyntax": 0, "inputTokens": 21190, "outputTokens": 139618 }, "medium": { "unitTestPassRate": 18.94, "fullPass": 4, "partialPass": 52, "fail": 39, "noCode": 2, "codeQuality": 69.6, "invalidSyntax": 6, "inputTokens": 52215, "outputTokens": 163953 }, "hard": { "unitTestPassRate": 11.7, "fullPass": 2, "partialPass": 29, "fail": 32, "noCode": 1, "codeQuality": 69.1, "invalidSyntax": 4, "inputTokens": 33472, "outputTokens": 90364 } } } }, { "name": "Devstral Small 2507 (Q4_K_M)", "provider": "Mistral AI", "url": "https://huggingface.co/mistralai/Devstral-Small-2507", "releaseDate": "2025-07-10", "size": 16089785632, "price": { "electricity": 0.2 }, "scores": { "robloxqa": { "freeform": { "correct": 1652, "noAnswer": 0, "inputTokens": 216225, "outputTokens": 125508, "kilowattHour": 0.352 }, "multipleChoice": { "correct": 2510, "noAnswer": 0, "inputTokens": 398216, "outputTokens": 436601, "kilowattHour": 2.418 }, "topics": { "classes": { "freeform": 587, "multipleChoice": 939 }, "types": { "freeform": 178, "multipleChoice": 263 }, "luau": { "freeform": 50, "multipleChoice": 75 }, "scripting": { "freeform": 171, "multipleChoice": 245 }, "gameplay": { "freeform": 52, "multipleChoice": 96 }, "visuals": { "freeform": 60, "multipleChoice": 94 }, "art": { "freeform": 72, "multipleChoice": 135 }, "monetization": { "freeform": 82, "multipleChoice": 151 }, "studio": { "freeform": 97, "multipleChoice": 153 }, "learning": { "freeform": 303, "multipleChoice": 359 } } }, "leetcode": { "easy": { "unitTestPassRate": 65.51, "fullPass": 22, "partialPass": 16, "fail": 9, "noCode": 0, "codeQuality": 90.6, "invalidSyntax": 2, "inputTokens": 20716, "outputTokens": 16228, "kilowattHour": 0.192 }, "medium": { "unitTestPassRate": 34.15, "fullPass": 12, "partialPass": 55, "fail": 30, "noCode": 0, "codeQuality": 84.5, "invalidSyntax": 5, "inputTokens": 51222, "outputTokens": 56048, "kilowattHour": 0.662 }, "hard": { "unitTestPassRate": 21.85, "fullPass": 5, "partialPass": 29, "fail": 30, "noCode": 0, "codeQuality": 80.5, "invalidSyntax": 4, "inputTokens": 32878, "outputTokens": 39727, "kilowattHour": 0.469 } } } }, { "name": "Kimi K3 (High)", "provider": "Moonshot AI", "url": "https://www.kimi.com/blog/kimi-k3", "releaseDate": "2026-07-16", "size": 1560860324864, "price": { "input": 3, "output": 15 }, "scores": { "robloxqa": { "freeform": { "correct": 2426, "noAnswer": 0, "inputTokens": 488082, "outputTokens": 1229399 }, "multipleChoice": { "correct": 2894, "noAnswer": 0, "inputTokens": 669758, "outputTokens": 794432 }, "topics": { "classes": { "freeform": 907, "multipleChoice": 1108 }, "types": { "freeform": 258, "multipleChoice": 308 }, "luau": { "freeform": 76, "multipleChoice": 85 }, "scripting": { "freeform": 237, "multipleChoice": 274 }, "gameplay": { "freeform": 93, "multipleChoice": 119 }, "visuals": { "freeform": 97, "multipleChoice": 112 }, "art": { "freeform": 120, "multipleChoice": 156 }, "monetization": { "freeform": 135, "multipleChoice": 184 }, "studio": { "freeform": 140, "multipleChoice": 164 }, "learning": { "freeform": 363, "multipleChoice": 384 } } }, "leetcode": { "easy": { "unitTestPassRate": 96.57, "fullPass": 42, "partialPass": 5, "fail": 0, "noCode": 0, "codeQuality": 99.4, "invalidSyntax": 0, "inputTokens": 24300, "outputTokens": 30000 }, "medium": { "unitTestPassRate": 93.85, "fullPass": 75, "partialPass": 20, "fail": 2, "noCode": 0, "codeQuality": 97.1, "invalidSyntax": 0, "inputTokens": 58645, "outputTokens": 298404 }, "hard": { "unitTestPassRate": 91.69, "fullPass": 45, "partialPass": 16, "fail": 3, "noCode": 0, "codeQuality": 92.2, "invalidSyntax": 1, "inputTokens": 37711, "outputTokens": 515974 } } } }, { "name": "GPT 5 (Medium)", "provider": "OpenAI", "url": "https://developers.openai.com/api/docs/models/gpt-5", "releaseDate": "2025-08-07", "size": null, "price": { "input": 1.25, "output": 10 }, "scores": { "robloxqa": { "freeform": { "correct": 2364, "noAnswer": 0, "inputTokens": 225589, "outputTokens": 2416184 }, "multipleChoice": { "correct": 2831, "noAnswer": 0, "inputTokens": 404067, "outputTokens": 1886054 }, "topics": { "classes": { "freeform": 886, "multipleChoice": 1085 }, "types": { "freeform": 248, "multipleChoice": 294 }, "luau": { "freeform": 76, "multipleChoice": 81 }, "scripting": { "freeform": 227, "multipleChoice": 273 }, "gameplay": { "freeform": 94, "multipleChoice": 112 }, "visuals": { "freeform": 93, "multipleChoice": 111 }, "art": { "freeform": 121, "multipleChoice": 155 }, "monetization": { "freeform": 127, "multipleChoice": 180 }, "studio": { "freeform": 136, "multipleChoice": 162 }, "learning": { "freeform": 356, "multipleChoice": 378 } } }, "leetcode": { "easy": { "unitTestPassRate": 96.99, "fullPass": 44, "partialPass": 3, "fail": 0, "noCode": 0, "codeQuality": 98.4, "invalidSyntax": 0, "inputTokens": 20113, "outputTokens": 83604 }, "medium": { "unitTestPassRate": 96.47, "fullPass": 78, "partialPass": 18, "fail": 1, "noCode": 0, "codeQuality": 92.8, "invalidSyntax": 0, "inputTokens": 49965, "outputTokens": 521703 }, "hard": { "unitTestPassRate": 86.57, "fullPass": 42, "partialPass": 15, "fail": 7, "noCode": 0, "codeQuality": 81.0, "invalidSyntax": 4, "inputTokens": 32013, "outputTokens": 640520 } } } }, { "name": "GPT 5.4 nano (High)", "provider": "OpenAI", "url": "https://developers.openai.com/api/docs/models/gpt-5.4-nano", "releaseDate": "2026-03-17", "size": null, "price": { "input": 0.2, "output": 1.2471 }, "scores": { "robloxqa": { "freeform": { "correct": 2183, "noAnswer": 0, "inputTokens": 225589, "outputTokens": 882142 }, "multipleChoice": { "correct": 2670, "noAnswer": 0, "inputTokens": 404080, "outputTokens": 609487 }, "topics": { "classes": { "freeform": 809, "multipleChoice": 1005 }, "types": { "freeform": 231, "multipleChoice": 287 }, "luau": { "freeform": 73, "multipleChoice": 76 }, "scripting": { "freeform": 207, "multipleChoice": 257 }, "gameplay": { "freeform": 77, "multipleChoice": 109 }, "visuals": { "freeform": 78, "multipleChoice": 105 }, "art": { "freeform": 104, "multipleChoice": 146 }, "monetization": { "freeform": 129, "multipleChoice": 159 }, "studio": { "freeform": 129, "multipleChoice": 157 }, "learning": { "freeform": 346, "multipleChoice": 369 } } }, "leetcode": { "easy": { "unitTestPassRate": 89.85, "fullPass": 39, "partialPass": 5, "fail": 3, "noCode": 0, "codeQuality": 92.8, "invalidSyntax": 3, "inputTokens": 20935, "outputTokens": 73629 }, "medium": { "unitTestPassRate": 84.93, "fullPass": 64, "partialPass": 25, "fail": 8, "noCode": 0, "codeQuality": 85.9, "invalidSyntax": 6, "inputTokens": 53471, "outputTokens": 488158 }, "hard": { "unitTestPassRate": 65.54, "fullPass": 32, "partialPass": 14, "fail": 16, "noCode": 2, "codeQuality": 69.4, "invalidSyntax": 11, "inputTokens": 38485, "outputTokens": 854382 } } } }, { "name": "GPT 5.5 (Medium)", "provider": "OpenAI", "url": "https://developers.openai.com/api/docs/models/gpt-5.5", "releaseDate": "2026-04-23", "size": null, "price": { "input": 5, "output": 30 }, "scores": { "robloxqa": { "freeform": { "correct": 2598, "noAnswer": 0, "inputTokens": 225590, "outputTokens": 881130 }, "multipleChoice": { "correct": 2926, "noAnswer": 0, "inputTokens": 404089, "outputTokens": 550573 }, "topics": { "classes": { "freeform": 1007, "multipleChoice": 1124 }, "types": { "freeform": 279, "multipleChoice": 310 }, "luau": { "freeform": 78, "multipleChoice": 84 }, "scripting": { "freeform": 238, "multipleChoice": 278 }, "gameplay": { "freeform": 107, "multipleChoice": 123 }, "visuals": { "freeform": 104, "multipleChoice": 114 }, "art": { "freeform": 126, "multipleChoice": 157 }, "monetization": { "freeform": 150, "multipleChoice": 191 }, "studio": { "freeform": 141, "multipleChoice": 163 }, "learning": { "freeform": 368, "multipleChoice": 382 } } }, "leetcode": { "easy": { "unitTestPassRate": 97.06, "fullPass": 43, "partialPass": 4, "fail": 0, "noCode": 0, "codeQuality": 99.7, "invalidSyntax": 0, "inputTokens": 20113, "outputTokens": 18431 }, "medium": { "unitTestPassRate": 97.44, "fullPass": 82, "partialPass": 14, "fail": 1, "noCode": 0, "codeQuality": 97.9, "invalidSyntax": 0, "inputTokens": 49965, "outputTokens": 154490 }, "hard": { "unitTestPassRate": 93.01, "fullPass": 52, "partialPass": 9, "fail": 3, "noCode": 0, "codeQuality": 97.2, "invalidSyntax": 0, "inputTokens": 32013, "outputTokens": 233033 } } } }, { "name": "GPT 5.6 Luna (Medium)", "provider": "OpenAI", "url": "https://developers.openai.com/api/docs/models/gpt-5.6-luna", "releaseDate": "2026-07-09", "size": null, "price": { "input": 0.2, "output": 1.2 }, "scores": { "robloxqa": { "freeform": { "correct": 2397, "noAnswer": 0, "inputTokens": 225589, "outputTokens": 574988 }, "multipleChoice": { "correct": 2873, "noAnswer": 0, "inputTokens": 404067, "outputTokens": 349378 }, "topics": { "classes": { "freeform": 898, "multipleChoice": 1103 }, "types": { "freeform": 259, "multipleChoice": 296 }, "luau": { "freeform": 74, "multipleChoice": 84 }, "scripting": { "freeform": 222, "multipleChoice": 275 }, "gameplay": { "freeform": 100, "multipleChoice": 119 }, "visuals": { "freeform": 90, "multipleChoice": 111 }, "art": { "freeform": 116, "multipleChoice": 157 }, "monetization": { "freeform": 139, "multipleChoice": 180 }, "studio": { "freeform": 138, "multipleChoice": 165 }, "learning": { "freeform": 361, "multipleChoice": 383 } } }, "leetcode": { "easy": { "unitTestPassRate": 95.47, "fullPass": 44, "partialPass": 2, "fail": 1, "noCode": 0, "codeQuality": 99.5, "invalidSyntax": 0, "inputTokens": 20113, "outputTokens": 17787 }, "medium": { "unitTestPassRate": 88.98, "fullPass": 74, "partialPass": 16, "fail": 7, "noCode": 0, "codeQuality": 96.6, "invalidSyntax": 1, "inputTokens": 49965, "outputTokens": 117279 }, "hard": { "unitTestPassRate": 75.24, "fullPass": 33, "partialPass": 24, "fail": 7, "noCode": 0, "codeQuality": 88.0, "invalidSyntax": 3, "inputTokens": 32013, "outputTokens": 154252 } } } }, { "name": "GPT 5.6 Sol (Medium)", "provider": "OpenAI", "url": "https://developers.openai.com/api/docs/models/gpt-5.6-sol", "releaseDate": "2026-07-09", "size": null, "price": { "input": 5, "output": 30 }, "scores": { "robloxqa": { "freeform": { "correct": 2572, "noAnswer": 0, "inputTokens": 225589, "outputTokens": 581312 }, "multipleChoice": { "correct": 2938, "noAnswer": 0, "inputTokens": 404067, "outputTokens": 208018 }, "topics": { "classes": { "freeform": 988, "multipleChoice": 1135 }, "types": { "freeform": 280, "multipleChoice": 310 }, "luau": { "freeform": 78, "multipleChoice": 85 }, "scripting": { "freeform": 237, "multipleChoice": 277 }, "gameplay": { "freeform": 106, "multipleChoice": 121 }, "visuals": { "freeform": 100, "multipleChoice": 114 }, "art": { "freeform": 129, "multipleChoice": 159 }, "monetization": { "freeform": 149, "multipleChoice": 191 }, "studio": { "freeform": 148, "multipleChoice": 163 }, "learning": { "freeform": 357, "multipleChoice": 383 } } }, "leetcode": { "easy": { "unitTestPassRate": 97.0, "fullPass": 42, "partialPass": 5, "fail": 0, "noCode": 0, "codeQuality": 99.8, "invalidSyntax": 0, "inputTokens": 20113, "outputTokens": 10179 }, "medium": { "unitTestPassRate": 98.48, "fullPass": 81, "partialPass": 16, "fail": 0, "noCode": 0, "codeQuality": 98.1, "invalidSyntax": 0, "inputTokens": 50051, "outputTokens": 87592 }, "hard": { "unitTestPassRate": 92.28, "fullPass": 53, "partialPass": 8, "fail": 3, "noCode": 0, "codeQuality": 96.3, "invalidSyntax": 0, "inputTokens": 32013, "outputTokens": 128181 } } } }, { "name": "GPT 5.6 Terra (Medium)", "provider": "OpenAI", "url": "https://developers.openai.com/api/docs/models/gpt-5.6-terra", "releaseDate": "2026-07-09", "size": null, "price": { "input": 2, "output": 12 }, "scores": { "robloxqa": { "freeform": { "correct": 2378, "noAnswer": 0, "inputTokens": 225589, "outputTokens": 264017 }, "multipleChoice": { "correct": 2873, "noAnswer": 0, "inputTokens": 404067, "outputTokens": 261108 }, "topics": { "classes": { "freeform": 901, "multipleChoice": 1096 }, "types": { "freeform": 252, "multipleChoice": 304 }, "luau": { "freeform": 76, "multipleChoice": 84 }, "scripting": { "freeform": 225, "multipleChoice": 272 }, "gameplay": { "freeform": 97, "multipleChoice": 117 }, "visuals": { "freeform": 91, "multipleChoice": 107 }, "art": { "freeform": 113, "multipleChoice": 159 }, "monetization": { "freeform": 127, "multipleChoice": 186 }, "studio": { "freeform": 140, "multipleChoice": 165 }, "learning": { "freeform": 356, "multipleChoice": 383 } } }, "leetcode": { "easy": { "unitTestPassRate": 97.08, "fullPass": 44, "partialPass": 3, "fail": 0, "noCode": 0, "codeQuality": 99.1, "invalidSyntax": 0, "inputTokens": 20113, "outputTokens": 10682 }, "medium": { "unitTestPassRate": 93.89, "fullPass": 76, "partialPass": 17, "fail": 4, "noCode": 0, "codeQuality": 97.1, "invalidSyntax": 1, "inputTokens": 49965, "outputTokens": 88570 }, "hard": { "unitTestPassRate": 88.55, "fullPass": 49, "partialPass": 9, "fail": 6, "noCode": 0, "codeQuality": 93.2, "invalidSyntax": 2, "inputTokens": 32013, "outputTokens": 125400 } } } }, { "name": "GPT OSS 20B", "provider": "OpenAI", "url": "https://huggingface.co/openai/gpt-oss-20b", "releaseDate": "2025-08-05", "size": 13761264768, "price": { "input": 0.03, "output": 0.15499 }, "scores": { "robloxqa": { "freeform": { "correct": 1977, "noAnswer": 1, "inputTokens": 402625, "outputTokens": 1315332 }, "multipleChoice": { "correct": 2661, "noAnswer": 1, "inputTokens": 581019, "outputTokens": 853656 }, "topics": { "classes": { "freeform": 699, "multipleChoice": 992 }, "types": { "freeform": 212, "multipleChoice": 284 }, "luau": { "freeform": 71, "multipleChoice": 80 }, "scripting": { "freeform": 205, "multipleChoice": 257 }, "gameplay": { "freeform": 64, "multipleChoice": 99 }, "visuals": { "freeform": 72, "multipleChoice": 105 }, "art": { "freeform": 86, "multipleChoice": 144 }, "monetization": { "freeform": 114, "multipleChoice": 169 }, "studio": { "freeform": 123, "multipleChoice": 160 }, "learning": { "freeform": 331, "multipleChoice": 371 } } }, "leetcode": { "easy": { "unitTestPassRate": 86.43, "fullPass": 38, "partialPass": 5, "fail": 4, "noCode": 0, "codeQuality": 91.8, "invalidSyntax": 3, "inputTokens": 22886, "outputTokens": 58350 }, "medium": { "unitTestPassRate": 71.03, "fullPass": 54, "partialPass": 24, "fail": 17, "noCode": 2, "codeQuality": 80.8, "invalidSyntax": 10, "inputTokens": 55688, "outputTokens": 502154 }, "hard": { "unitTestPassRate": 41.2, "fullPass": 16, "partialPass": 15, "fail": 28, "noCode": 5, "codeQuality": 55.9, "invalidSyntax": 15, "inputTokens": 35789, "outputTokens": 618574 } } } }, { "name": "Luau Devstral 24B Instruct v0.2 (Q5_K_XL)", "provider": "Torpedo Software", "url": "https://huggingface.co/TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.2", "releaseDate": "2025-09-16", "size": 16788120384, "price": { "electricity": 0.2 }, "scores": { "robloxqa": { "freeform": { "correct": 1921, "noAnswer": 0, "inputTokens": 216225, "outputTokens": 121041, "kilowattHour": 0.42 }, "multipleChoice": { "correct": 2577, "noAnswer": 0, "inputTokens": 398216, "outputTokens": 304109, "kilowattHour": 0.934 }, "topics": { "classes": { "freeform": 687, "multipleChoice": 958 }, "types": { "freeform": 194, "multipleChoice": 271 }, "luau": { "freeform": 57, "multipleChoice": 76 }, "scripting": { "freeform": 196, "multipleChoice": 253 }, "gameplay": { "freeform": 72, "multipleChoice": 99 }, "visuals": { "freeform": 69, "multipleChoice": 95 }, "art": { "freeform": 91, "multipleChoice": 138 }, "monetization": { "freeform": 107, "multipleChoice": 160 }, "studio": { "freeform": 113, "multipleChoice": 155 }, "learning": { "freeform": 335, "multipleChoice": 372 } } }, "leetcode": { "easy": { "unitTestPassRate": 72.34, "fullPass": 26, "partialPass": 16, "fail": 5, "noCode": 0, "codeQuality": 96.0, "invalidSyntax": 0, "inputTokens": 20716, "outputTokens": 23893, "kilowattHour": 0.054 }, "medium": { "unitTestPassRate": 36.75, "fullPass": 15, "partialPass": 58, "fail": 24, "noCode": 0, "codeQuality": 95.8, "invalidSyntax": 0, "inputTokens": 51222, "outputTokens": 66540, "kilowattHour": 0.168 }, "hard": { "unitTestPassRate": 31.39, "fullPass": 8, "partialPass": 41, "fail": 15, "noCode": 0, "codeQuality": 93.7, "invalidSyntax": 0, "inputTokens": 32878, "outputTokens": 44250, "kilowattHour": 0.112 } } } }, { "name": "Luau Qwen3 4B FIM v0.1 (Q8_0)", "provider": "Torpedo Software", "url": "https://huggingface.co/TorpedoSoftware/Luau-Qwen3-4B-FIM-v0.1", "releaseDate": "2025-10-19", "size": 4280402464, "price": { "electricity": 0.2 }, "scores": { "robloxqa": { "freeform": { "correct": 1456, "noAnswer": 0, "inputTokens": 239246, "outputTokens": 132998, "kilowattHour": 0.103 }, "multipleChoice": { "correct": 2468, "noAnswer": 0, "inputTokens": 418468, "outputTokens": 500586, "kilowattHour": 0.402 }, "topics": { "classes": { "freeform": 543, "multipleChoice": 917 }, "types": { "freeform": 158, "multipleChoice": 264 }, "luau": { "freeform": 47, "multipleChoice": 75 }, "scripting": { "freeform": 140, "multipleChoice": 236 }, "gameplay": { "freeform": 42, "multipleChoice": 91 }, "visuals": { "freeform": 54, "multipleChoice": 91 }, "art": { "freeform": 54, "multipleChoice": 129 }, "monetization": { "freeform": 71, "multipleChoice": 158 }, "studio": { "freeform": 85, "multipleChoice": 148 }, "learning": { "freeform": 262, "multipleChoice": 359 } } }, "leetcode": { "easy": { "unitTestPassRate": 35.37, "fullPass": 13, "partialPass": 9, "fail": 9, "noCode": 16, "codeQuality": 45.9, "invalidSyntax": 5, "inputTokens": 20709, "outputTokens": 34978, "kilowattHour": 0.08 }, "medium": { "unitTestPassRate": 14.77, "fullPass": 6, "partialPass": 26, "fail": 27, "noCode": 38, "codeQuality": 35.8, "invalidSyntax": 15, "inputTokens": 51013, "outputTokens": 175066, "kilowattHour": 0.399 }, "hard": { "unitTestPassRate": 9.32, "fullPass": 2, "partialPass": 16, "fail": 21, "noCode": 25, "codeQuality": 31.3, "invalidSyntax": 9, "inputTokens": 32784, "outputTokens": 80208, "kilowattHour": 0.183 } } } }, { "name": "Grok 4.5 (Medium)", "provider": "xAI", "url": "https://docs.x.ai/developers/models/grok-4.5", "releaseDate": "2026-07-08", "size": null, "price": { "input": 2, "output": 6.4831 }, "scores": { "robloxqa": { "freeform": { "correct": 2441, "noAnswer": 0, "inputTokens": 827473, "outputTokens": 1723323 }, "multipleChoice": { "correct": 2887, "noAnswer": 0, "inputTokens": 1009787, "outputTokens": 1977283 }, "topics": { "classes": { "freeform": 934, "multipleChoice": 1113 }, "types": { "freeform": 267, "multipleChoice": 300 }, "luau": { "freeform": 81, "multipleChoice": 85 }, "scripting": { "freeform": 230, "multipleChoice": 276 }, "gameplay": { "freeform": 96, "multipleChoice": 119 }, "visuals": { "freeform": 94, "multipleChoice": 113 }, "art": { "freeform": 112, "multipleChoice": 155 }, "monetization": { "freeform": 132, "multipleChoice": 182 }, "studio": { "freeform": 138, "multipleChoice": 163 }, "learning": { "freeform": 357, "multipleChoice": 381 } } }, "leetcode": { "easy": { "unitTestPassRate": 97.58, "fullPass": 44, "partialPass": 3, "fail": 0, "noCode": 0, "codeQuality": 99.0, "invalidSyntax": 0, "inputTokens": 29842, "outputTokens": 60988 }, "medium": { "unitTestPassRate": 95.02, "fullPass": 79, "partialPass": 14, "fail": 4, "noCode": 0, "codeQuality": 96.2, "invalidSyntax": 1, "inputTokens": 70220, "outputTokens": 539460 }, "hard": { "unitTestPassRate": 83.88, "fullPass": 40, "partialPass": 17, "fail": 7, "noCode": 0, "codeQuality": 91.5, "invalidSyntax": 2, "inputTokens": 45378, "outputTokens": 824883 } } } }, { "name": "GLM 4.7 Flash", "provider": "Z.ai", "url": "https://huggingface.co/zai-org/GLM-4.7-Flash", "releaseDate": "2026-01-19", "size": 31221488576, "price": { "input": 0.06, "output": 0.4 }, "scores": { "robloxqa": { "freeform": { "correct": 1723, "noAnswer": 12, "inputTokens": 218150, "outputTokens": 2226246 }, "multipleChoice": { "correct": 2494, "noAnswer": 91, "inputTokens": 396863, "outputTokens": 7314366 }, "topics": { "classes": { "freeform": 617, "multipleChoice": 921 }, "types": { "freeform": 182, "multipleChoice": 262 }, "luau": { "freeform": 58, "multipleChoice": 71 }, "scripting": { "freeform": 182, "multipleChoice": 250 }, "gameplay": { "freeform": 52, "multipleChoice": 91 }, "visuals": { "freeform": 52, "multipleChoice": 94 }, "art": { "freeform": 74, "multipleChoice": 130 }, "monetization": { "freeform": 98, "multipleChoice": 154 }, "studio": { "freeform": 98, "multipleChoice": 154 }, "learning": { "freeform": 310, "multipleChoice": 367 } } }, "leetcode": { "easy": { "unitTestPassRate": 52.99, "fullPass": 20, "partialPass": 8, "fail": 12, "noCode": 7, "codeQuality": 77.8, "invalidSyntax": 0, "inputTokens": 19911, "outputTokens": 493838 }, "medium": { "unitTestPassRate": 20.44, "fullPass": 11, "partialPass": 19, "fail": 23, "noCode": 44, "codeQuality": 40.9, "invalidSyntax": 5, "inputTokens": 49306, "outputTokens": 2496010 }, "hard": { "unitTestPassRate": 6.75, "fullPass": 0, "partialPass": 9, "fail": 10, "noCode": 45, "codeQuality": 17.8, "invalidSyntax": 4, "inputTokens": 31479, "outputTokens": 2463034 } } } }, { "name": "GLM 5.2 (High)", "provider": "Z.ai", "url": "https://huggingface.co/zai-org/GLM-5.2", "releaseDate": "2026-06-16", "size": 1506659919872, "price": { "input": 0.826, "output": 3.5017 }, "scores": { "robloxqa": { "freeform": { "correct": 2230, "noAnswer": 87, "inputTokens": 239177, "outputTokens": 6894184 }, "multipleChoice": { "correct": 2670, "noAnswer": 180, "inputTokens": 417937, "outputTokens": 12567539 }, "topics": { "classes": { "freeform": 823, "multipleChoice": 997 }, "types": { "freeform": 230, "multipleChoice": 277 }, "luau": { "freeform": 74, "multipleChoice": 80 }, "scripting": { "freeform": 219, "multipleChoice": 257 }, "gameplay": { "freeform": 87, "multipleChoice": 107 }, "visuals": { "freeform": 88, "multipleChoice": 103 }, "art": { "freeform": 109, "multipleChoice": 145 }, "monetization": { "freeform": 116, "multipleChoice": 172 }, "studio": { "freeform": 133, "multipleChoice": 156 }, "learning": { "freeform": 351, "multipleChoice": 376 } } }, "leetcode": { "easy": { "unitTestPassRate": 94.95, "fullPass": 43, "partialPass": 3, "fail": 1, "noCode": 0, "codeQuality": 97.6, "invalidSyntax": 1, "inputTokens": 20240, "outputTokens": 51375 }, "medium": { "unitTestPassRate": 88.3, "fullPass": 76, "partialPass": 11, "fail": 8, "noCode": 2, "codeQuality": 91.6, "invalidSyntax": 3, "inputTokens": 50105, "outputTokens": 656574 }, "hard": { "unitTestPassRate": 67.04, "fullPass": 34, "partialPass": 13, "fail": 9, "noCode": 8, "codeQuality": 68.4, "invalidSyntax": 7, "inputTokens": 31999, "outputTokens": 1117629 } } } } ] }