{ "date": "2026-10-03", "edition": "0.2.1", "metric": "official_raw_score", "code_revision": "87d4650b42b377c0291a89c1f1a879f9b31082bf", "source_url": "https://github.com/apolinario/decision-index/tree/87d4650b42b377c0291a89c1f1a879f9b31082bf", "jev_reference_url": "https://github.com/apolinario/decision-index/blob/87d4650b42b377c0291a89c1f1a879f9b31082bf/tests/fixtures/board-0.2.1.json", "results": { "gsm8k": { "catalog_id": 30, "title": "GSM8K", "metric": "mean track accuracy", "total": 2638, "models": { "qwen35_2b_base": { "raw": 0.304, "skill": 0.1609, "coverage": 1.0, "answered": 2638, "native_score": 0.30401819560272936, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.40788476118271416, "skill": 0.21051301491028554, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.2001516300227445, "skill": 0.11127958891416054, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation" }, "qev_2b": { "raw": 0.3776, "skill": 0.2531, "coverage": 1.0, "answered": 2638, "native_score": 0.3775587566338135, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.5026535253980288, "skill": 0.3368713671973717, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.25246398786959817, "skill": 0.16940443096622018, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation" }, "qwen35_4b_base": { "raw": 0.37, "skill": 0.2381, "coverage": 1.0, "answered": 2638, "native_score": 0.36997725549658833, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.44275966641395, "skill": 0.2570128885519333, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.2971948445792267, "skill": 0.2191053828658074, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation" }, "qev_4b": { "raw": 0.5459, "skill": 0.4585, "coverage": 1.0, "answered": 2638, "native_score": 0.5458680818802123, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.6679302501895376, "skill": 0.5572403335860501, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.42380591357088704, "skill": 0.3597843484120967, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation" }, "qwen35_9b_base": { "raw": 0.5553, "skill": 0.4642, "coverage": 1.0, "answered": 2638, "native_score": 0.5553449583017438, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.624715693707354, "skill": 0.4996209249431387, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.48597422289613346, "skill": 0.4288602476623705, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation" }, "qev_9b": { "raw": 0.6175, "skill": 0.5442, "coverage": 1.0, "answered": 2638, "native_score": 0.6175132676269901, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.7225170583775588, "skill": 0.6300227445034117, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.5125094768764216, "skill": 0.458343863196024, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation", "model_revision": "v0.3.0" }, "kev_9b": { "raw": 0.4636, "skill": 0.357, "coverage": 1.0, "answered": 2638, "native_score": 0.4636087945413192, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.5769522365428355, "skill": 0.43593631539044725, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.3502653525398029, "skill": 0.2780726139331143, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation" }, "kev_4b": { "raw": 0.5849, "skill": 0.5003, "coverage": 1.0, "answered": 2638, "native_score": 0.5849128127369219, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.6535253980288097, "skill": 0.5380338640384129, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.5163002274450341, "skill": 0.46255580827226017, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation" }, "jevany_4b_pointer": { "raw": 0.4761, "skill": 0.3736, "coverage": 1.0, "answered": 2638, "native_score": 0.4761182714177407, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.601213040181956, "skill": 0.46828405357594133, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.3510235026535254, "skill": 0.2789150029483615, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation" }, "jevany_4b_direct": { "raw": 0.4503, "skill": 0.3407, "coverage": 1.0, "answered": 2638, "native_score": 0.45034116755117515, "tracks": [ { "track": "GSM8K-4choice", "raw": 0.5625473843821076, "skill": 0.41672984584281014, "random": 0.25, "coverage": 1 }, { "track": "GSM8K-10choice", "raw": 0.33813495072024263, "skill": 0.2645943896891585, "random": 0.1, "coverage": 1 } ], "source": "local_evaluation" }, "jev": { "raw": 0.7987, "skill": 0.7565, "coverage": 1, "source": "published_leaderboard", "version": "Jev 1.13.0" } } }, "chessbench": { "catalog_id": 31, "title": "ChessBench", "metric": "best-move accuracy, accepting tied optima", "total": 5000, "models": { "qwen35_2b_base": { "raw": 0.0884, "skill": 0.0071, "coverage": 1.0, "answered": 5000, "native_score": 0.0884, "tracks": [ { "track": "all", "raw": 0.0884, "skill": 0.00712784287150035, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation" }, "qev_2b": { "raw": 0.1098, "skill": 0.0304, "coverage": 1.0, "answered": 5000, "native_score": 0.1098, "tracks": [ { "track": "all", "raw": 0.1098, "skill": 0.03043572369922071, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation" }, "qwen35_4b_base": { "raw": 0.1178, "skill": 0.0391, "coverage": 1.0, "answered": 5000, "native_score": 0.1178, "tracks": [ { "track": "all", "raw": 0.1178, "skill": 0.0391489501768732, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation" }, "qev_4b": { "raw": 0.1242, "skill": 0.0461, "coverage": 1.0, "answered": 5000, "native_score": 0.1242, "tracks": [ { "track": "all", "raw": 0.1242, "skill": 0.04611953135899518, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation" }, "qwen35_9b_base": { "raw": 0.1322, "skill": 0.0548, "coverage": 1.0, "answered": 5000, "native_score": 0.1322, "tracks": [ { "track": "all", "raw": 0.1322, "skill": 0.054832757836647664, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation" }, "qev_9b": { "raw": 0.1034, "skill": 0.0235, "coverage": 1.0, "answered": 5000, "native_score": 0.1034, "tracks": [ { "track": "all", "raw": 0.1034, "skill": 0.023465142517098744, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation", "model_revision": "v0.3.0" }, "kev_9b": { "raw": 0.1176, "skill": 0.0389, "coverage": 1.0, "answered": 5000, "native_score": 0.1176, "tracks": [ { "track": "all", "raw": 0.1176, "skill": 0.038931119514931875, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation" }, "kev_4b": { "raw": 0.088, "skill": 0.0067, "coverage": 1.0, "answered": 5000, "native_score": 0.088, "tracks": [ { "track": "all", "raw": 0.088, "skill": 0.0066921815476177135, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation" }, "jevany_4b_pointer": { "raw": 0.1132, "skill": 0.0341, "coverage": 1.0, "answered": 5000, "native_score": 0.1132, "tracks": [ { "track": "all", "raw": 0.1132, "skill": 0.03413884495222302, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation" }, "jevany_4b_direct": { "raw": 0.1172, "skill": 0.0385, "coverage": 1.0, "answered": 5000, "native_score": 0.1172, "tracks": [ { "track": "all", "raw": 0.1172, "skill": 0.038495458191049256, "random": 0.0818556110623024, "coverage": 1 } ], "source": "local_evaluation" }, "jev": { "raw": 0.1722, "skill": 0.0984, "coverage": 1, "source": "published_leaderboard", "version": "Jev 1.13.0" } } }, "esci": { "catalog_id": 37, "title": "Amazon ESCI", "metric": "macro-F1", "total": 5000, "models": { "qwen35_2b_base": { "raw": 0.281, "skill": 0.0982, "coverage": 1.0, "answered": 5000, "native_score": 0.281041285029981, "tracks": [ { "track": "all", "raw": 0.281041285029981, "skill": 0.09821544691532137, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation" }, "qev_2b": { "raw": 0.3634, "skill": 0.2015, "coverage": 1.0, "answered": 5000, "native_score": 0.3634004876980141, "tracks": [ { "track": "all", "raw": 0.3634004876980141, "skill": 0.2015179804599628, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation" }, "qwen35_4b_base": { "raw": 0.2918, "skill": 0.1117, "coverage": 1.0, "answered": 5000, "native_score": 0.2918028420723953, "tracks": [ { "track": "all", "raw": 0.2918028420723953, "skill": 0.11171358763734261, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation" }, "qev_4b": { "raw": 0.4249, "skill": 0.2786, "coverage": 1.0, "answered": 5000, "native_score": 0.4248617285215504, "tracks": [ { "track": "all", "raw": 0.4248617285215504, "skill": 0.2786083563522611, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation" }, "qwen35_9b_base": { "raw": 0.3056, "skill": 0.129, "coverage": 1.0, "answered": 5000, "native_score": 0.3055619197954184, "tracks": [ { "track": "all", "raw": 0.3055619197954184, "skill": 0.12897149618892217, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation" }, "qev_9b": { "raw": 0.4708, "skill": 0.3363, "coverage": 1.0, "answered": 5000, "native_score": 0.4708360372719961, "tracks": [ { "track": "all", "raw": 0.4708360372719961, "skill": 0.336273588870691, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation", "model_revision": "v0.3.0" }, "kev_9b": { "raw": 0.4809, "skill": 0.3489, "coverage": 1.0, "answered": 5000, "native_score": 0.4809184305561307, "tracks": [ { "track": "all", "raw": 0.4809184305561307, "skill": 0.3489198595569521, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation" }, "kev_4b": { "raw": 0.3956, "skill": 0.2419, "coverage": 1.0, "answered": 5000, "native_score": 0.39561788161121436, "tracks": [ { "track": "all", "raw": 0.39561788161121436, "skill": 0.24192801731830993, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation" }, "jevany_4b_pointer": { "raw": 0.5494, "skill": 0.4348, "coverage": 1.0, "answered": 5000, "native_score": 0.5493592773788667, "tracks": [ { "track": "all", "raw": 0.5493592773788667, "skill": 0.4347647031893874, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation" }, "jevany_4b_direct": { "raw": 0.5425, "skill": 0.4262, "coverage": 1.0, "answered": 5000, "native_score": 0.5424928991743364, "tracks": [ { "track": "all", "raw": 0.5424928991743364, "skill": 0.42615225622747677, "random": 0.20273782411694521, "coverage": 1 } ], "source": "local_evaluation" }, "jev": { "raw": 0.5521, "skill": 0.4382, "coverage": 1, "source": "published_leaderboard", "version": "Jev 1.13.0" } } }, "bpomp": { "catalog_id": 20, "title": "BPoMP", "metric": "mean accuracy across poem variants", "total": 5000, "models": { "qwen35_2b_base": { "raw": 0.505, "skill": 0.0101, "coverage": 1.0, "answered": 5000, "native_score": 0.5026, "tracks": [ { "track": "all", "raw": 0.5050301177080375, "skill": 0.010060235416075036, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation" }, "qev_2b": { "raw": 0.7381, "skill": 0.4763, "coverage": 1.0, "answered": 5000, "native_score": 0.7346, "tracks": [ { "track": "all", "raw": 0.7381339972176438, "skill": 0.47626799443528767, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation" }, "qwen35_4b_base": { "raw": 0.6895, "skill": 0.3791, "coverage": 1.0, "answered": 5000, "native_score": 0.6942, "tracks": [ { "track": "all", "raw": 0.689541386353874, "skill": 0.37908277270774793, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation" }, "qev_4b": { "raw": 0.7819, "skill": 0.5638, "coverage": 1.0, "answered": 5000, "native_score": 0.779, "tracks": [ { "track": "all", "raw": 0.7818951793165829, "skill": 0.5637903586331658, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation" }, "qwen35_9b_base": { "raw": 0.5939, "skill": 0.1877, "coverage": 1.0, "answered": 5000, "native_score": 0.5954, "tracks": [ { "track": "all", "raw": 0.593868528281851, "skill": 0.187737056563702, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation" }, "qev_9b": { "raw": 0.8103, "skill": 0.6205, "coverage": 1.0, "answered": 5000, "native_score": 0.8068, "tracks": [ { "track": "all", "raw": 0.8102618917009247, "skill": 0.6205237834018493, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation", "model_revision": "v0.3.0" }, "kev_9b": { "raw": 0.6693, "skill": 0.3387, "coverage": 1.0, "answered": 5000, "native_score": 0.6688, "tracks": [ { "track": "all", "raw": 0.6693391049629296, "skill": 0.3386782099258592, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation" }, "kev_4b": { "raw": 0.6528, "skill": 0.3056, "coverage": 1.0, "answered": 5000, "native_score": 0.6502, "tracks": [ { "track": "all", "raw": 0.6528226564034934, "skill": 0.3056453128069867, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation" }, "jevany_4b_pointer": { "raw": 0.7387, "skill": 0.4773, "coverage": 1.0, "answered": 5000, "native_score": 0.731, "tracks": [ { "track": "all", "raw": 0.7386594480630367, "skill": 0.4773188961260735, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation" }, "jevany_4b_direct": { "raw": 0.8129, "skill": 0.6258, "coverage": 1.0, "answered": 5000, "native_score": 0.8142, "tracks": [ { "track": "all", "raw": 0.8128861556266215, "skill": 0.625772311253243, "random": 0.5, "coverage": 1 } ], "source": "local_evaluation" }, "jev": { "raw": 0.9092, "skill": 0.8184, "coverage": 1, "source": "published_leaderboard", "version": "Jev 1.13.0" } } } } }