Buckets:
| { | |
| "ours": { | |
| "base": { | |
| "model": "Qwen/Qwen3.5-4B", | |
| "temps": { | |
| "choice": 1.707683209388825, | |
| "noul": 2.4105066990845945, | |
| "score": 1.2847580560947693 | |
| }, | |
| "raw": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 48.05492263372704, | |
| "ci": [ | |
| 37.76904082341696, | |
| 57.150183634721955 | |
| ], | |
| "accuracy": 0.8066666666666666, | |
| "ece_10_bin": 0.06460862585758344, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": 2.049999831140492, | |
| "ci": [ | |
| -9.799345465028715, | |
| 13.108881184556378 | |
| ], | |
| "accuracy": 0.4033333333333333, | |
| "ece_10_bin": 0.15123322991920435, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 56.173306098208656, | |
| "ci": [ | |
| 49.27693100059662, | |
| 63.141876285290685 | |
| ], | |
| "accuracy": 0.7186666666666667, | |
| "ece_10_bin": 0.14011876588219976, | |
| "T": 1.0, | |
| "n": 300 | |
| } | |
| }, | |
| "calibrated": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 36.371473995104964, | |
| "ci": [ | |
| 29.35952403100504, | |
| 42.77706939107353 | |
| ], | |
| "accuracy": 0.8066666666666666, | |
| "ece_10_bin": 0.15700328478531872, | |
| "T": 2.4105066990845945, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": 4.103423043229137, | |
| "ci": [ | |
| -6.389453722683416, | |
| 13.956330811232187 | |
| ], | |
| "accuracy": 0.4033333333333333, | |
| "ece_10_bin": 0.08902712405177117, | |
| "T": 1.2847580560947693, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 59.3453919929658, | |
| "ci": [ | |
| 53.69828564607293, | |
| 64.93884389399817 | |
| ], | |
| "accuracy": 0.7186666666666667, | |
| "ece_10_bin": 0.04315345334218913, | |
| "T": 1.707683209388825, | |
| "n": 300 | |
| } | |
| } | |
| }, | |
| "rl60": { | |
| "model": "runs/v2/checkpoints/rl60_merged", | |
| "temps": { | |
| "choice": 1.1599743376333564, | |
| "noul": 0.7983784191901301, | |
| "score": 0.7276446912498098 | |
| }, | |
| "raw": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 58.72560050503446, | |
| "ci": [ | |
| 48.25519209655997, | |
| 67.9986456840194 | |
| ], | |
| "accuracy": 0.8633333333333333, | |
| "ece_10_bin": 0.026845709305701414, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": 6.037515788606118, | |
| "ci": [ | |
| -2.400834157155406, | |
| 14.35084224020631 | |
| ], | |
| "accuracy": 0.43666666666666665, | |
| "ece_10_bin": 0.095953934239622, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 60.955089258193006, | |
| "ci": [ | |
| 54.66931758063293, | |
| 67.32577013719438 | |
| ], | |
| "accuracy": 0.7313333333333333, | |
| "ece_10_bin": 0.05904332938166834, | |
| "T": 1.0, | |
| "n": 300 | |
| } | |
| }, | |
| "calibrated": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 58.614060949612615, | |
| "ci": [ | |
| 47.33820737643784, | |
| 68.84278523729319 | |
| ], | |
| "accuracy": 0.8633333333333333, | |
| "ece_10_bin": 0.03571861771195042, | |
| "T": 0.7983784191901301, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": 2.368980700043777, | |
| "ci": [ | |
| -7.2405524866967275, | |
| 11.746115459613257 | |
| ], | |
| "accuracy": 0.43666666666666665, | |
| "ece_10_bin": 0.1303236520061676, | |
| "T": 0.7276446912498098, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 61.33904164009218, | |
| "ci": [ | |
| 55.52009100804195, | |
| 67.34968363963038 | |
| ], | |
| "accuracy": 0.7313333333333333, | |
| "ece_10_bin": 0.027606077031200056, | |
| "T": 1.1599743376333564, | |
| "n": 300 | |
| } | |
| } | |
| }, | |
| "rl60_think": { | |
| "model": "runs/v2/checkpoints/rl60_merged", | |
| "temps": { | |
| "choice": 2.145082715273473, | |
| "noul": 1.9352338162597778, | |
| "score": 1.8069801445316314 | |
| }, | |
| "raw": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 58.936313009275274, | |
| "ci": [ | |
| 44.39233287434623, | |
| 72.34563008669913 | |
| ], | |
| "accuracy": 0.9, | |
| "ece_10_bin": 0.09364023899498322, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": -42.99011458744382, | |
| "ci": [ | |
| -61.37940857090847, | |
| -24.665619976798016 | |
| ], | |
| "accuracy": 0.41333333333333333, | |
| "ece_10_bin": 0.519184866453263, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 49.48519474863158, | |
| "ci": [ | |
| 40.343495405677444, | |
| 58.75819407518067 | |
| ], | |
| "accuracy": 0.7333333333333333, | |
| "ece_10_bin": 0.24588454845319418, | |
| "T": 1.0, | |
| "n": 300 | |
| } | |
| }, | |
| "calibrated": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 63.46531221234828, | |
| "ci": [ | |
| 51.2282704267052, | |
| 74.80118608216338 | |
| ], | |
| "accuracy": 0.9, | |
| "ece_10_bin": 0.045119675748778995, | |
| "T": 1.9352338162597778, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": -20.13990146885871, | |
| "ci": [ | |
| -35.33533731665648, | |
| -4.939007706671506 | |
| ], | |
| "accuracy": 0.41333333333333333, | |
| "ece_10_bin": 0.37806488700901164, | |
| "T": 1.8069801445316314, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 59.27752355436782, | |
| "ci": [ | |
| 53.606719794836316, | |
| 64.93246211545883 | |
| ], | |
| "accuracy": 0.7333333333333333, | |
| "ece_10_bin": 0.13413758897367453, | |
| "T": 2.145082715273473, | |
| "n": 300 | |
| } | |
| } | |
| }, | |
| "v1_joint": { | |
| "model": "checkpoints/joint_merged", | |
| "temps": { | |
| "choice": 1.2843740495491411, | |
| "noul": 1.1776347713530488, | |
| "score": 1.0535480782391846 | |
| }, | |
| "raw": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 49.206682779012525, | |
| "ci": [ | |
| 36.65442701300594, | |
| 59.903266381066885 | |
| ], | |
| "accuracy": 0.8233333333333334, | |
| "ece_10_bin": 0.06969906794374832, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": 6.7772824916263685, | |
| "ci": [ | |
| -2.2223595409748595, | |
| 16.175846550495578 | |
| ], | |
| "accuracy": 0.3933333333333333, | |
| "ece_10_bin": 0.17954795337837168, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 60.61334399242887, | |
| "ci": [ | |
| 54.24958965660347, | |
| 66.93369679868799 | |
| ], | |
| "accuracy": 0.7326666666666667, | |
| "ece_10_bin": 0.07895850726459176, | |
| "T": 1.0, | |
| "n": 300 | |
| } | |
| }, | |
| "calibrated": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 50.30267194300714, | |
| "ci": [ | |
| 38.78645963769695, | |
| 60.216646199918934 | |
| ], | |
| "accuracy": 0.8233333333333334, | |
| "ece_10_bin": 0.06609612462236357, | |
| "T": 1.1776347713530488, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": 7.5280862119676435, | |
| "ci": [ | |
| -1.2187682680666836, | |
| 16.69347049625058 | |
| ], | |
| "accuracy": 0.3933333333333333, | |
| "ece_10_bin": 0.16808161152147194, | |
| "T": 1.0535480782391846, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 61.483220852549046, | |
| "ci": [ | |
| 55.919259043009745, | |
| 67.11049272666077 | |
| ], | |
| "accuracy": 0.7326666666666667, | |
| "ece_10_bin": 0.05006183740765189, | |
| "T": 1.2843740495491411, | |
| "n": 300 | |
| } | |
| } | |
| }, | |
| "v2_joint": { | |
| "model": "runs/v2/checkpoints/v2_joint_merged", | |
| "temps": { | |
| "choice": 1.1592816013856364, | |
| "noul": 0.8031824332990728, | |
| "score": 0.716891860990727 | |
| }, | |
| "raw": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 57.9754923387608, | |
| "ci": [ | |
| 47.474841970587384, | |
| 67.33647236474492 | |
| ], | |
| "accuracy": 0.8566666666666667, | |
| "ece_10_bin": 0.024792356261037377, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": 6.072330512589563, | |
| "ci": [ | |
| -2.447039948281713, | |
| 14.421161550147108 | |
| ], | |
| "accuracy": 0.43, | |
| "ece_10_bin": 0.0758746614948931, | |
| "T": 1.0, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 60.90446514198684, | |
| "ci": [ | |
| 54.643973597052714, | |
| 67.26811195597078 | |
| ], | |
| "accuracy": 0.734, | |
| "ece_10_bin": 0.05840767711375198, | |
| "T": 1.0, | |
| "n": 300 | |
| } | |
| }, | |
| "calibrated": { | |
| "pubmedqa": { | |
| "primitive": "noul", | |
| "ds": 57.786338685636565, | |
| "ci": [ | |
| 46.39802375142668, | |
| 68.04438733775511 | |
| ], | |
| "accuracy": 0.8566666666666667, | |
| "ece_10_bin": 0.033081921946533914, | |
| "T": 0.8031824332990728, | |
| "n": 300 | |
| }, | |
| "helpsteer2": { | |
| "primitive": "score", | |
| "ds": 2.314214972593698, | |
| "ci": [ | |
| -7.267135153938562, | |
| 11.84096549506603 | |
| ], | |
| "accuracy": 0.43, | |
| "ece_10_bin": 0.1364261756101774, | |
| "T": 0.716891860990727, | |
| "n": 300 | |
| }, | |
| "banking77": { | |
| "primitive": "choice", | |
| "ds": 61.31478198739936, | |
| "ci": [ | |
| 55.423784855833, | |
| 67.28099088659312 | |
| ], | |
| "accuracy": 0.734, | |
| "ece_10_bin": 0.02052732067327072, | |
| "T": 1.1592816013856364, | |
| "n": 300 | |
| } | |
| } | |
| } | |
| }, | |
| "board": [ | |
| { | |
| "board": "banking77", | |
| "name": "Gemini 3.8 Flash", | |
| "ds": 74.107, | |
| "ci": [ | |
| 68.4397, | |
| 79.7893 | |
| ], | |
| "accuracy": 0.846, | |
| "ece": 0.0319, | |
| "p95_ms": 3938, | |
| "cost_per_1k": 1.367931, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "banking77", | |
| "name": "Jev", | |
| "ds": 67.7806, | |
| "ci": [ | |
| 61.3393, | |
| 74.4909 | |
| ], | |
| "accuracy": 0.7967, | |
| "ece": 0.0981, | |
| "p95_ms": 693, | |
| "cost_per_1k": 0.043276, | |
| "interface": "native" | |
| }, | |
| { | |
| "board": "banking77", | |
| "name": "GLM-5.3", | |
| "ds": 66.8264, | |
| "ci": [ | |
| 61.9567, | |
| 71.7196 | |
| ], | |
| "accuracy": 0.7887, | |
| "ece": 0.0616, | |
| "p95_ms": 3186, | |
| "cost_per_1k": 0.718505, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "banking77", | |
| "name": "DeepSeek V4.1 Flash", | |
| "ds": 63.9292, | |
| "ci": [ | |
| 58.5065, | |
| 69.6119 | |
| ], | |
| "accuracy": 0.7587, | |
| "ece": 0.0276, | |
| "p95_ms": 1309, | |
| "cost_per_1k": 0.138384, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "banking77", | |
| "name": "Qwen3.8 Flash", | |
| "ds": 62.4389, | |
| "ci": [ | |
| 55.9178, | |
| 68.8961 | |
| ], | |
| "accuracy": 0.768, | |
| "ece": 0.0951, | |
| "p95_ms": 3105, | |
| "cost_per_1k": 0.122064, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "banking77", | |
| "name": "Mistral Medium 3.5", | |
| "ds": 59.4547, | |
| "ci": [ | |
| 54.2695, | |
| 64.8301 | |
| ], | |
| "accuracy": 0.7447, | |
| "ece": 0.0807, | |
| "p95_ms": 1444, | |
| "cost_per_1k": 1.515244, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "banking77", | |
| "name": "Mercury 2.5", | |
| "ds": 54.0395, | |
| "ci": [ | |
| 47.8178, | |
| 60.6156 | |
| ], | |
| "accuracy": 0.7033, | |
| "ece": 0.1044, | |
| "p95_ms": 1478, | |
| "cost_per_1k": 0.03606, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "banking77", | |
| "name": "Label prior", | |
| "ds": 0, | |
| "ci": [ | |
| 0, | |
| 0 | |
| ], | |
| "accuracy": 0.0133, | |
| "ece": 0, | |
| "p95_ms": null, | |
| "cost_per_1k": 0, | |
| "interface": "baseline" | |
| }, | |
| { | |
| "board": "helpsteer2", | |
| "name": "Jev", | |
| "ds": 9.2034, | |
| "ci": [ | |
| -4.365, | |
| 20.9655 | |
| ], | |
| "accuracy": 0.4127, | |
| "ece": 0.1966, | |
| "p95_ms": 670, | |
| "cost_per_1k": 0.036285, | |
| "interface": "native" | |
| }, | |
| { | |
| "board": "helpsteer2", | |
| "name": "GLM-5.3", | |
| "ds": 7.7828, | |
| "ci": [ | |
| -4.5884, | |
| 18.5647 | |
| ], | |
| "accuracy": 0.43, | |
| "ece": 0.1287, | |
| "p95_ms": 3631, | |
| "cost_per_1k": 0.784848, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "helpsteer2", | |
| "name": "Gemini 3.8 Flash", | |
| "ds": 4.5909, | |
| "ci": [ | |
| -12.2314, | |
| 18.9838 | |
| ], | |
| "accuracy": 0.424, | |
| "ece": 0.2259, | |
| "p95_ms": 3979, | |
| "cost_per_1k": 1.269273, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "helpsteer2", | |
| "name": "Label prior", | |
| "ds": 0, | |
| "ci": [ | |
| 0, | |
| 0 | |
| ], | |
| "accuracy": 0.4167, | |
| "ece": 0, | |
| "p95_ms": null, | |
| "cost_per_1k": 0, | |
| "interface": "baseline" | |
| }, | |
| { | |
| "board": "helpsteer2", | |
| "name": "Qwen3.8 Flash", | |
| "ds": -1.3701, | |
| "ci": [ | |
| -15.4058, | |
| 11.5108 | |
| ], | |
| "accuracy": 0.3607, | |
| "ece": 0.2577, | |
| "p95_ms": 2638, | |
| "cost_per_1k": 0.125698, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "helpsteer2", | |
| "name": "Mercury 2.5", | |
| "ds": -5.5457, | |
| "ci": [ | |
| -16.2223, | |
| 3.9934 | |
| ], | |
| "accuracy": 0.4173, | |
| "ece": 0.3148, | |
| "p95_ms": 1165, | |
| "cost_per_1k": 0.034331, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "helpsteer2", | |
| "name": "Mistral Medium 3.5", | |
| "ds": -13.7288, | |
| "ci": [ | |
| -28.2641, | |
| -0.1455 | |
| ], | |
| "accuracy": 0.4387, | |
| "ece": 0.3361, | |
| "p95_ms": 1178, | |
| "cost_per_1k": 1.325036, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "helpsteer2", | |
| "name": "DeepSeek V4.1 Flash", | |
| "ds": -18.9946, | |
| "ci": [ | |
| -36.0158, | |
| -3.3185 | |
| ], | |
| "accuracy": 0.3467, | |
| "ece": 0.3348, | |
| "p95_ms": 1203, | |
| "cost_per_1k": 0.125297, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "pubmedqa", | |
| "name": "Gemini 3.8 Flash", | |
| "ds": 72.983, | |
| "ci": [ | |
| 62.0659, | |
| 82.2398 | |
| ], | |
| "accuracy": 0.9253, | |
| "ece": 0.0198, | |
| "p95_ms": 5538, | |
| "cost_per_1k": 0.803439, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "pubmedqa", | |
| "name": "Jev", | |
| "ds": 69.0274, | |
| "ci": [ | |
| 59.7741, | |
| 76.5459 | |
| ], | |
| "accuracy": 0.9127, | |
| "ece": 0.0504, | |
| "p95_ms": 653, | |
| "cost_per_1k": 0.028535, | |
| "interface": "native" | |
| }, | |
| { | |
| "board": "pubmedqa", | |
| "name": "Qwen3.8 Flash", | |
| "ds": 62.4422, | |
| "ci": [ | |
| 50.905, | |
| 72.5479 | |
| ], | |
| "accuracy": 0.8967, | |
| "ece": 0.0255, | |
| "p95_ms": 3515, | |
| "cost_per_1k": 0.08613, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "pubmedqa", | |
| "name": "GLM-5.3", | |
| "ds": 60.6328, | |
| "ci": [ | |
| 49.9596, | |
| 69.8189 | |
| ], | |
| "accuracy": 0.8867, | |
| "ece": 0.0202, | |
| "p95_ms": 2879, | |
| "cost_per_1k": 0.512414, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "pubmedqa", | |
| "name": "Mistral Medium 3.5", | |
| "ds": 58.0327, | |
| "ci": [ | |
| 45.3414, | |
| 69.8002 | |
| ], | |
| "accuracy": 0.888, | |
| "ece": 0.0523, | |
| "p95_ms": 917, | |
| "cost_per_1k": 0.874716, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "pubmedqa", | |
| "name": "Mercury 2.5", | |
| "ds": 55.6583, | |
| "ci": [ | |
| 44.8114, | |
| 65.4167 | |
| ], | |
| "accuracy": 0.8713, | |
| "ece": 0.0468, | |
| "p95_ms": 1036, | |
| "cost_per_1k": 0.022595, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "pubmedqa", | |
| "name": "DeepSeek V4.1 Flash", | |
| "ds": 47.5001, | |
| "ci": [ | |
| 34.7497, | |
| 59.0847 | |
| ], | |
| "accuracy": 0.8367, | |
| "ece": 0.0616, | |
| "p95_ms": 1123, | |
| "cost_per_1k": 0.078411, | |
| "interface": "adapter" | |
| }, | |
| { | |
| "board": "pubmedqa", | |
| "name": "Label prior", | |
| "ds": 0, | |
| "ci": [ | |
| 0, | |
| 0 | |
| ], | |
| "accuracy": 0.62, | |
| "ece": 0, | |
| "p95_ms": null, | |
| "cost_per_1k": 0, | |
| "interface": "baseline" | |
| } | |
| ], | |
| "release": "2026-09-18", | |
| "suite": "0.1.0" | |
| } |
Xet Storage Details
- Size:
- 14.7 kB
- Xet hash:
- 7e183a0962c9bca1f5223fecde8625dad32cf3cb5c3ce2921463894e697436c0
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.