Spaces:
Running
Running
Download benchmark.json from EnvLoop/Recursive-Play: direct link, hf CLI and curl.
- Browser
- Download file 14.4 kB
-
https://huggingface.co/spaces/EnvLoop/Recursive-Play/resolve/main/benchmark.json
- Command line
-
hf download hf://spaces/EnvLoop/Recursive-Play/benchmark.json
-
curl -L -o benchmark.json https://huggingface.co/spaces/EnvLoop/Recursive-Play/resolve/main/benchmark.json
14.4 kB
| { | |
| "models": [ | |
| { | |
| "name": "GPT-6 Astra", | |
| "id": "gpt-6-astra", | |
| "rank": 1, | |
| "full": 135, | |
| "levels": 848, | |
| "fullRate": 90.0, | |
| "levelRate": 94.22222222222223, | |
| "time": 6, | |
| "action": 9, | |
| "abandoned": 0, | |
| "depth": [ | |
| 2, | |
| 2, | |
| 4, | |
| 3, | |
| 1, | |
| 3, | |
| 135 | |
| ] | |
| }, | |
| { | |
| "name": "GPT-5.6 Sol", | |
| "id": "gpt-5.6-sol", | |
| "rank": 2, | |
| "full": 29, | |
| "levels": 357, | |
| "fullRate": 19.333333333333332, | |
| "levelRate": 39.666666666666664, | |
| "time": 73, | |
| "action": 47, | |
| "abandoned": 1, | |
| "depth": [ | |
| 50, | |
| 22, | |
| 16, | |
| 12, | |
| 12, | |
| 9, | |
| 29 | |
| ] | |
| }, | |
| { | |
| "name": "GPT-6 Sol", | |
| "id": "gpt-6-sol", | |
| "rank": 3, | |
| "full": 22, | |
| "levels": 369, | |
| "fullRate": 14.666666666666666, | |
| "levelRate": 41.0, | |
| "time": 122, | |
| "action": 6, | |
| "abandoned": 0, | |
| "depth": [ | |
| 32, | |
| 27, | |
| 27, | |
| 21, | |
| 12, | |
| 9, | |
| 22 | |
| ] | |
| }, | |
| { | |
| "name": "GPT-5.6 Terra", | |
| "id": "gpt-5.6-terra", | |
| "rank": 4, | |
| "full": 20, | |
| "levels": 282, | |
| "fullRate": 13.333333333333334, | |
| "levelRate": 31.333333333333332, | |
| "time": 69, | |
| "action": 59, | |
| "abandoned": 2, | |
| "depth": [ | |
| 68, | |
| 18, | |
| 15, | |
| 11, | |
| 9, | |
| 9, | |
| 20 | |
| ] | |
| }, | |
| { | |
| "name": "GPT-5.6 Luna", | |
| "id": "gpt-5.6-luna", | |
| "rank": 5, | |
| "full": 4, | |
| "levels": 160, | |
| "fullRate": 2.6666666666666665, | |
| "levelRate": 17.77777777777778, | |
| "time": 118, | |
| "action": 23, | |
| "abandoned": 5, | |
| "depth": [ | |
| 83, | |
| 22, | |
| 21, | |
| 12, | |
| 4, | |
| 4, | |
| 4 | |
| ] | |
| }, | |
| { | |
| "name": "Qwen 3.8 Flash", | |
| "id": "qwen3.8-flash", | |
| "rank": 6, | |
| "full": 2, | |
| "levels": 114, | |
| "fullRate": 1.3333333333333333, | |
| "levelRate": 12.666666666666666, | |
| "time": 125, | |
| "action": 0, | |
| "abandoned": 23, | |
| "depth": [ | |
| 95, | |
| 22, | |
| 18, | |
| 9, | |
| 3, | |
| 1, | |
| 2 | |
| ] | |
| }, | |
| { | |
| "name": "GPT-6 Luna", | |
| "id": "gpt-6-luna", | |
| "rank": 6, | |
| "full": 2, | |
| "levels": 89, | |
| "fullRate": 1.3333333333333333, | |
| "levelRate": 9.88888888888889, | |
| "time": 143, | |
| "action": 4, | |
| "abandoned": 1, | |
| "depth": [ | |
| 102, | |
| 27, | |
| 9, | |
| 9, | |
| 0, | |
| 1, | |
| 2 | |
| ] | |
| }, | |
| { | |
| "name": "Qwen 3.8 Max 0902", | |
| "id": "qwen3.8-max-0902", | |
| "rank": 8, | |
| "full": 1, | |
| "levels": 88, | |
| "fullRate": 0.6666666666666666, | |
| "levelRate": 9.777777777777779, | |
| "time": 149, | |
| "action": 0, | |
| "abandoned": 0, | |
| "depth": [ | |
| 100, | |
| 29, | |
| 10, | |
| 7, | |
| 3, | |
| 0, | |
| 1 | |
| ] | |
| }, | |
| { | |
| "name": "DeepSeek V4.1 Flash", | |
| "id": "deepseek-v4.1-flash", | |
| "rank": 9, | |
| "full": 0, | |
| "levels": 63, | |
| "fullRate": 0.0, | |
| "levelRate": 7.0, | |
| "time": 150, | |
| "action": 0, | |
| "abandoned": 0, | |
| "depth": [ | |
| 111, | |
| 26, | |
| 6, | |
| 4, | |
| 2, | |
| 1, | |
| 0 | |
| ] | |
| }, | |
| { | |
| "name": "Kimi K3", | |
| "id": "kimi-k3", | |
| "rank": 9, | |
| "full": 0, | |
| "levels": 38, | |
| "fullRate": 0.0, | |
| "levelRate": 4.222222222222222, | |
| "time": 150, | |
| "action": 0, | |
| "abandoned": 0, | |
| "depth": [ | |
| 126, | |
| 13, | |
| 9, | |
| 1, | |
| 1, | |
| 0, | |
| 0 | |
| ] | |
| }, | |
| { | |
| "name": "GLM 5.3 Flash", | |
| "id": "ZHIPU/GLM-5.3-Flash", | |
| "rank": 9, | |
| "full": 0, | |
| "levels": 28, | |
| "fullRate": 0.0, | |
| "levelRate": 3.111111111111111, | |
| "time": 150, | |
| "action": 0, | |
| "abandoned": 0, | |
| "depth": [ | |
| 128, | |
| 17, | |
| 4, | |
| 1, | |
| 0, | |
| 0, | |
| 0 | |
| ] | |
| } | |
| ], | |
| "cases": [ | |
| { | |
| "id": "a001", | |
| "seed": 503117, | |
| "initial": "a001-initial.png", | |
| "entry": "a001-level4-entry.png", | |
| "panels": [ | |
| { | |
| "model": "GPT-6 Astra", | |
| "file": "a001-astra-terminal.png", | |
| "levels": 6, | |
| "actions": 33, | |
| "seconds": 174.151, | |
| "end": "won", | |
| "levelShown": 6 | |
| }, | |
| { | |
| "model": "DeepSeek V4.1 Flash", | |
| "file": "a001-deepseek-terminal.png", | |
| "levels": 5, | |
| "actions": 38, | |
| "seconds": 719.989, | |
| "end": "time_budget", | |
| "levelShown": 6 | |
| }, | |
| { | |
| "model": "GPT-6 Luna", | |
| "file": "a001-luna-terminal.png", | |
| "levels": 3, | |
| "actions": 46, | |
| "seconds": 720.0, | |
| "end": "time_budget", | |
| "levelShown": 4 | |
| } | |
| ] | |
| }, | |
| { | |
| "id": "a005", | |
| "seed": 526874, | |
| "initial": "a005-initial.png", | |
| "panels": [ | |
| { | |
| "model": "GPT-6 Astra", | |
| "file": "a005-astra-terminal.png", | |
| "levels": 6, | |
| "actions": 30, | |
| "seconds": 158.739, | |
| "end": "won", | |
| "levelShown": 6 | |
| }, | |
| { | |
| "model": "Qwen 3.8 Flash", | |
| "file": "a005-qwenflash-terminal.png", | |
| "levels": 6, | |
| "actions": 39, | |
| "seconds": 717.969, | |
| "end": "won", | |
| "levelShown": 6 | |
| }, | |
| { | |
| "model": "GPT-6 Sol", | |
| "file": "a005-gpt6sol-terminal.png", | |
| "levels": 5, | |
| "actions": 154, | |
| "seconds": 720.002, | |
| "end": "time_budget", | |
| "levelShown": 6 | |
| }, | |
| { | |
| "model": "GPT-5.6 Sol", | |
| "file": "a005-gpt56sol-terminal.png", | |
| "levels": 1, | |
| "actions": 512, | |
| "seconds": 483.341, | |
| "end": "action_budget", | |
| "levelShown": 2 | |
| } | |
| ], | |
| "outcomes": [ | |
| { | |
| "actions": 30, | |
| "gameElapsedSeconds": 158.739, | |
| "levelsCompleted": 6, | |
| "model": "gpt-6-astra", | |
| "termination": "won" | |
| }, | |
| { | |
| "actions": 512, | |
| "gameElapsedSeconds": 483.341, | |
| "levelsCompleted": 1, | |
| "model": "gpt-5.6-sol", | |
| "termination": "action_budget" | |
| }, | |
| { | |
| "actions": 69, | |
| "gameElapsedSeconds": 719.997, | |
| "levelsCompleted": 5, | |
| "model": "gpt-5.6-luna", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 63, | |
| "gameElapsedSeconds": 553.16, | |
| "levelsCompleted": 6, | |
| "model": "gpt-5.6-terra", | |
| "termination": "won" | |
| }, | |
| { | |
| "actions": 39, | |
| "gameElapsedSeconds": 717.969, | |
| "levelsCompleted": 6, | |
| "model": "qwen3.8-flash", | |
| "termination": "won" | |
| }, | |
| { | |
| "actions": 6, | |
| "gameElapsedSeconds": 719.985, | |
| "levelsCompleted": 0, | |
| "model": "ZHIPU/GLM-5.3-Flash", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 36, | |
| "gameElapsedSeconds": 719.999, | |
| "levelsCompleted": 4, | |
| "model": "deepseek-v4.1-flash", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 10, | |
| "gameElapsedSeconds": 720.001, | |
| "levelsCompleted": 2, | |
| "model": "kimi-k3", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 35, | |
| "gameElapsedSeconds": 720.0, | |
| "levelsCompleted": 0, | |
| "model": "qwen3.8-max-0902", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 154, | |
| "gameElapsedSeconds": 720.002, | |
| "levelsCompleted": 5, | |
| "model": "gpt-6-sol", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 27, | |
| "gameElapsedSeconds": 720.001, | |
| "levelsCompleted": 3, | |
| "model": "gpt-6-luna", | |
| "termination": "time_budget" | |
| } | |
| ] | |
| }, | |
| { | |
| "id": "d009", | |
| "seed": 899067, | |
| "initial": "d009-initial.png", | |
| "panels": [ | |
| { | |
| "model": "GPT-6 Astra", | |
| "file": "d009-astra-terminal.png", | |
| "levels": 6, | |
| "actions": 96, | |
| "seconds": 135.827, | |
| "end": "won", | |
| "levelShown": 6 | |
| }, | |
| { | |
| "model": "GPT-5.6 Sol", | |
| "file": "d009-gpt56sol-terminal.png", | |
| "levels": 6, | |
| "actions": 115, | |
| "seconds": 661.809, | |
| "end": "won", | |
| "levelShown": 6 | |
| }, | |
| { | |
| "model": "GPT-6 Sol", | |
| "file": "d009-gpt6sol-terminal.png", | |
| "levels": 0, | |
| "actions": 45, | |
| "seconds": 720.002, | |
| "end": "time_budget", | |
| "levelShown": 1 | |
| }, | |
| { | |
| "model": "GPT-5.6 Terra", | |
| "file": "d009-terra-terminal.png", | |
| "levels": 0, | |
| "actions": 512, | |
| "seconds": 709.718, | |
| "end": "action_budget", | |
| "levelShown": 1 | |
| } | |
| ], | |
| "outcomes": [ | |
| { | |
| "actions": 96, | |
| "gameElapsedSeconds": 135.827, | |
| "levelsCompleted": 6, | |
| "model": "gpt-6-astra", | |
| "termination": "won" | |
| }, | |
| { | |
| "actions": 115, | |
| "gameElapsedSeconds": 661.809, | |
| "levelsCompleted": 6, | |
| "model": "gpt-5.6-sol", | |
| "termination": "won" | |
| }, | |
| { | |
| "actions": 512, | |
| "gameElapsedSeconds": 665.783, | |
| "levelsCompleted": 0, | |
| "model": "gpt-5.6-luna", | |
| "termination": "action_budget" | |
| }, | |
| { | |
| "actions": 512, | |
| "gameElapsedSeconds": 709.718, | |
| "levelsCompleted": 0, | |
| "model": "gpt-5.6-terra", | |
| "termination": "action_budget" | |
| }, | |
| { | |
| "actions": 39, | |
| "gameElapsedSeconds": 719.987, | |
| "levelsCompleted": 0, | |
| "model": "qwen3.8-flash", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 0, | |
| "gameElapsedSeconds": 719.986, | |
| "levelsCompleted": 0, | |
| "model": "ZHIPU/GLM-5.3-Flash", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 19, | |
| "gameElapsedSeconds": 720.001, | |
| "levelsCompleted": 0, | |
| "model": "deepseek-v4.1-flash", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 5, | |
| "gameElapsedSeconds": 720.003, | |
| "levelsCompleted": 0, | |
| "model": "kimi-k3", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 19, | |
| "gameElapsedSeconds": 720.006, | |
| "levelsCompleted": 0, | |
| "model": "qwen3.8-max-0902", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 45, | |
| "gameElapsedSeconds": 720.002, | |
| "levelsCompleted": 0, | |
| "model": "gpt-6-sol", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 15, | |
| "gameElapsedSeconds": 720.003, | |
| "levelsCompleted": 0, | |
| "model": "gpt-6-luna", | |
| "termination": "time_budget" | |
| } | |
| ] | |
| }, | |
| { | |
| "id": "e005", | |
| "seed": 978257, | |
| "initial": "e005-initial.png", | |
| "panels": [ | |
| { | |
| "model": "GPT-6 Astra", | |
| "file": "e005-astra-terminal.png", | |
| "levels": 6, | |
| "actions": 41, | |
| "seconds": 135.514, | |
| "end": "won", | |
| "levelShown": 6 | |
| }, | |
| { | |
| "model": "GPT-5.6 Sol", | |
| "file": "e005-gpt56sol-terminal.png", | |
| "levels": 6, | |
| "actions": 101, | |
| "seconds": 676.009, | |
| "end": "won", | |
| "levelShown": 6 | |
| }, | |
| { | |
| "model": "GPT-6 Sol", | |
| "file": "e005-gpt6sol-terminal.png", | |
| "levels": 2, | |
| "actions": 67, | |
| "seconds": 720.002, | |
| "end": "time_budget", | |
| "levelShown": 3 | |
| }, | |
| { | |
| "model": "GPT-6 Luna", | |
| "file": "e005-luna-terminal.png", | |
| "levels": 0, | |
| "actions": 9, | |
| "seconds": 720.003, | |
| "end": "time_budget", | |
| "levelShown": 1 | |
| } | |
| ], | |
| "outcomes": [ | |
| { | |
| "actions": 41, | |
| "gameElapsedSeconds": 135.514, | |
| "levelsCompleted": 6, | |
| "model": "gpt-6-astra", | |
| "termination": "won" | |
| }, | |
| { | |
| "actions": 101, | |
| "gameElapsedSeconds": 676.009, | |
| "levelsCompleted": 6, | |
| "model": "gpt-5.6-sol", | |
| "termination": "won" | |
| }, | |
| { | |
| "actions": 212, | |
| "gameElapsedSeconds": 719.985, | |
| "levelsCompleted": 2, | |
| "model": "gpt-5.6-luna", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 512, | |
| "gameElapsedSeconds": 389.674, | |
| "levelsCompleted": 1, | |
| "model": "gpt-5.6-terra", | |
| "termination": "action_budget" | |
| }, | |
| { | |
| "actions": 25, | |
| "gameElapsedSeconds": 719.985, | |
| "levelsCompleted": 1, | |
| "model": "qwen3.8-flash", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 0, | |
| "gameElapsedSeconds": 719.992, | |
| "levelsCompleted": 0, | |
| "model": "ZHIPU/GLM-5.3-Flash", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 7, | |
| "gameElapsedSeconds": 720.0, | |
| "levelsCompleted": 1, | |
| "model": "deepseek-v4.1-flash", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 5, | |
| "gameElapsedSeconds": 720.005, | |
| "levelsCompleted": 0, | |
| "model": "kimi-k3", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 11, | |
| "gameElapsedSeconds": 720.002, | |
| "levelsCompleted": 1, | |
| "model": "qwen3.8-max-0902", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 67, | |
| "gameElapsedSeconds": 720.002, | |
| "levelsCompleted": 2, | |
| "model": "gpt-6-sol", | |
| "termination": "time_budget" | |
| }, | |
| { | |
| "actions": 9, | |
| "gameElapsedSeconds": 720.003, | |
| "levelsCompleted": 0, | |
| "model": "gpt-6-luna", | |
| "termination": "time_budget" | |
| } | |
| ] | |
| } | |
| ] | |
| } | |