guanning's picture
Upload eval
5208c5c verified
Raw History Blame Contribute Delete
15.9 kB
label,set,questions,samples_per_q,all_idk_frac,S,E,F,qi,C,J0.01,J0.02,J0.05,acc1,tok1,acc2,tok2,acc4,tok4,acc8,tok8,s,trunc,len_S,len_E,len_F
base,aime_combined,89,64,0.0,0.06179775280898876,0.37447331460674155,0.5637289325842697,0.08713128404899269,8.424772248329658,0.0028835615656961104,-0.08136416091760046,-0.33410732836749024,0.06179775280898876,2.3349731390449437,0.07588658707865169,3.6180276619557588,0.08279340856530693,5.083389791231477,0.08556556042560053,6.501928038127102,2.3349731390449437,0.05301966292134831,2260.237385833665,2505.826928078681,2369.6217151897417
base,amc,124,64,0.0,0.30758568548387094,0.3709677419354839,0.3214465725806452,0.3601895612820918,5.208138272432804,0.30810817855776373,0.25602679583343574,0.0997826476604516,0.30758568548387094,2.101507308467742,0.3365754158266129,2.8677396023658015,0.3495140537138908,3.630136941898734,0.355581050567699,4.3098858252592915,2.101507308467742,0.04196068548387097,1966.6669251860278,2355.831623039757,2443.375878705359
base,beyondaime,100,64,0.01,0.01140625,0.42734375,0.56125,0.023227607666749476,9.077362402649984,-0.06754601635975037,-0.1583196403862502,-0.43064051246574986,0.01140625,2.1329056250000002,0.016142578125,3.313380908203125,0.019796788692474365,4.657279804267883,0.021777490199726655,5.986273473816413,2.1329056250000002,0.02953125,2297.315625,2254.5453824746114,2140.5088888051723
base,bigmath,198,64,0.0,0.6820549242424242,0.2316919191919192,0.08625315656565656,0.7079106332804069,1.5514722549911275,0.6923959107304957,0.6768811881805843,0.6303370205308504,0.6820549242424242,1.1856796085858587,0.7008327907986112,1.3651013035629735,0.7064299749003516,1.4813623474180095,0.7076704678868133,1.5359449835024546,1.1856796085858587,0.017282196969696968,1100.6746589927388,1672.3256904952077,2032.1911191451823
base,dapo_heldout,1536,64,0.0013020833333333333,0.2584431966145833,0.4146830240885417,0.326873779296875,0.3041394015819584,5.082312333561067,0.2533162782463477,0.20249315491073705,0.05002378490390505,0.2584431966145833,2.234050313313802,0.28537829717000324,3.031351373990377,0.2975577486601348,3.7537371489960543,0.3020156941737313,4.302705125987834,2.234050313313802,0.049387613932291664,2087.648879646779,2391.2460168739635,2514.9111039437466
base,math500,496,64,0.0,0.7069052419354839,0.18491683467741934,0.10817792338709678,0.7427198416955781,1.9871966535763483,0.7228478751598147,0.7029759086240512,0.6433600090167608,0.7069052419354839,1.3558794102822578,0.7301842474168346,1.6061235696115803,0.7386970445513725,1.7936932263941534,0.741580641370912,1.9076443524461923,1.3558794102822578,0.016286542338709676,1233.062532664265,1814.168367490857,2311.5586325354925
base_rep,aime_combined,89,64,0.0,0.06724016853932584,0.3674508426966292,0.5653089887640449,0.09342187555742239,9.466250522614489,-0.0012406296687224858,-0.09590313489486736,-0.3798906505733019,0.06724016853932584,2.3310395014044945,0.08241803458567416,3.6213861344583913,0.09019738301802217,5.124165186273248,0.0926744242279725,6.647909320280686,2.3310395014044945,0.05179073033707865,2270.9109044844345,2529.5332476849135,2345.249921623075
base_rep,amc,124,64,0.0,0.3092237903225806,0.37247983870967744,0.31829637096774194,0.36124755479771103,4.976596225813714,0.31148159253957397,0.2617156302814368,0.1124177435070254,0.3092237903225806,2.09127986391129,0.33808751260080644,2.8491499240013862,0.3508922275035612,3.589532794624086,0.3568645201486477,4.222857995024212,2.09127986391129,0.04170866935483871,1969.2275905473005,2316.306878656033,2450.391220612172
base_rep,beyondaime,100,64,0.0,0.01125,0.43015625,0.55859375,0.0252192603877903,8.753037874682848,-0.06231111835903819,-0.14984149710586667,-0.41243263334635216,0.01125,2.12098484375,0.0166162109375,3.2869481225585946,0.021449354887008668,4.615499240199923,0.024220356545531486,5.9164143251957855,2.12098484375,0.0284375,2264.1708904521406,2253.268591187088,2113.855986382421
base_rep,bigmath,198,64,0.0,0.6818970959595959,0.22971906565656566,0.08838383838383838,0.7097800750941647,1.568352375818714,0.6940965513359777,0.6784130275777907,0.6313624563032291,0.6818970959595959,1.1761803977272727,0.7025430082070707,1.3574745847143308,0.7084523186539159,1.4763136770701168,0.7096305245347493,1.539689167351378,1.1761803977272727,0.014835858585858586,1080.5343170383912,1597.3066797444822,1950.9548924725157
base_rep,dapo_heldout,1536,64,0.0006510416666666666,0.259063720703125,0.4165140787760417,0.3244222005208333,0.30443782123201957,5.09081380168648,0.25352968321515473,0.20262154519828995,0.04989713114769553,0.259063720703125,2.231237009684245,0.2859673500061035,3.0217351044019067,0.29820460760189843,3.736920519058709,0.302578474877131,4.281518611819041,2.231237009684245,0.047882080078125,2084.470288403445,2387.492547779297,2507.6318179360005
base_rep,math500,496,64,0.0,0.7064012096774194,0.18762600806451613,0.10597278225806452,0.7412972724902764,1.9705751199334183,0.7215915212909423,0.7018857700916081,0.6427685164936057,0.7064012096774194,1.3549856665826612,0.7302812145602319,1.5993460530927104,0.7380974438161619,1.7790803407931761,0.7403607455952244,1.890452980301428,1.3549856665826612,0.017231602822580645,1249.6919073910376,1808.9840127350099,2341.197557336638
l01_s200,dapo_heldout,1536,32,0.0006510416666666666,0.26959228515625,0.5280965169270834,0.20231119791666666,0.3061345634657531,3.1133743208296836,0.27500082025745615,0.24386707704915936,0.15046584742426886,0.26959228515625,2.0572323201497396,0.2933540344238281,2.5301779918670655,0.30249473825097084,2.8376298973045,0.3051542750125158,3.0058684754855896,2.0572323201497396,0.018168131510416668,1942.0833199847962,2165.2451677483027,2316.818398120044
l01_s200,math500,496,32,0.0,0.7183089717741935,0.2048891129032258,0.07680191532258064,0.7483980094705293,1.625596040292991,0.7321420490675992,0.7158860886646694,0.6671182074558796,0.7183089717741935,1.3044112903225809,0.7397835023941532,1.4691319836032006,0.7464497916160091,1.5591525710686562,0.7481333054780066,1.5969585901139451,1.3044112903225809,0.008694556451612902,1194.9675256165672,1761.4190691743531,2131.843321460958
l01_s440,aime_combined,89,64,0.0,0.06320224719101124,0.6839887640449438,0.25280898876404495,0.08354750884089238,3.0160769452917786,0.0533867393879746,0.023225969935056812,-0.06725633842369654,0.06320224719101124,1.892083040730337,0.07610055301966293,2.407290927844101,0.08158715387408653,2.7278047607480804,0.08314769917991063,2.897680763332636,1.892083040730337,0.01211376404494382,1939.0813994812127,1898.9120715910954,2036.3371372266975
l01_s440,amc,124,64,0.0,0.3103578629032258,0.4915574596774194,0.19808467741935484,0.35139712384017485,2.452100768473201,0.32687611615544293,0.3023551084707108,0.2287920854165148,0.3103578629032258,1.7047035030241935,0.3380402595766129,2.10230223624937,0.3485141982955317,2.3311629870173425,0.35102233335362315,2.42293766744233,1.7047035030241935,0.0073084677419354835,1585.17100179892,1793.3616646501368,2108.277758940531
l01_s440,beyondaime,100,64,0.0,0.01921875,0.8021875,0.17859375,0.024173796420110243,2.396776471474013,0.00020603170537010994,-0.023761733009370026,-0.09566502715359043,0.01921875,1.7333849999999997,0.02240478515625,2.0815856201171874,0.02383386194705963,2.2527961769604685,0.024155616576634068,2.327494499770067,1.7333849999999997,0.00640625,1742.9600189393939,1718.3320848900441,1912.191438748368
l01_s440,bigmath,198,64,0.0,0.6861584595959596,0.24329229797979798,0.07054924242424243,0.7125313375312874,1.19696229895162,0.7005617145417713,0.6885920915522549,0.6526832225837064,0.6861584595959596,0.9872153566919194,0.7057143702651515,1.1094926733151833,0.7110818142842765,1.1723476902806398,0.7123521081395299,1.1937827282326454,0.9872153566919194,0.0025252525252525255,900.0750792625037,1328.5880582353466,1704.953847309321
l01_s440,dapo_heldout,1536,64,0.0,0.2726338704427083,0.5341796875,0.19318644205729166,0.30947812535417607,2.772443737083254,0.28175368798334355,0.254029250612511,0.17085593850001335,0.2726338704427083,1.8128171793619794,0.29677629470825195,2.22244832722346,0.30599598202388734,2.4746792468132526,0.3087543344313583,2.600491170590564,1.8128171793619794,0.009979248046875,1717.0645385324262,1883.5923847195793,2155.805425830957
l01_s440,math500,496,64,0.0,0.7156943044354839,0.2015814012096774,0.0827242943548387,0.7459788781898946,1.4324851192391916,0.7316540269975027,0.7173291758051108,0.674354622227935,0.7156943044354839,1.1240273752520162,0.7371068154611895,1.2839210195233743,0.7438174820234699,1.3777749923558966,0.745615138891821,1.4181866805317649,1.1240273752520162,0.0032132056451612905,1012.3570005750983,1553.7524995767558,1953.1570218883326
l01_s500,dapo_heldout,128,8,0.0,0.228515625,0.7509765625,0.0205078125,0.2299107142857143,3.405048130580357,0.19586023297991068,0.16180975167410716,0.05965830775669641,0.228515625,3.3227587890625,0.229736328125,3.3925201416015627,0.22990798950195312,3.404642210006714,0.22991071362048388,3.40504700525431,3.3227587890625,0.62109375,2735.4873393801963,3608.6346311475413,2593.2631578947367
l01_s720,dapo_heldout,1536,32,0.0013020833333333333,0.22721354166666666,0.3708902994791667,0.4018961588541667,0.3052150755351194,2.7606422484164823,0.2776086530509546,0.2500022305667898,0.1671829631142953,0.22721354166666666,1.117145711263021,0.2683404286702474,1.5886887664794924,0.2910034091522296,2.036101954672486,0.30082109169389365,2.3856715764529497,1.117145711263021,0.0024820963541666665,1153.0329398908937,1167.5063950336355,1154.0152001575736
l01_s720,math500,496,32,0.0,0.6588961693548387,0.16834677419354838,0.1727570564516129,0.7254923485934464,1.329148244165764,0.7122008661517887,0.698909383710131,0.6590349363851581,0.6588961693548387,0.7467963079637097,0.698088615171371,0.9298383454353578,0.7151586509520008,1.0896782570019845,0.721729772849508,1.2100656112420864,0.7467963079637097,0.0008190524193548387,709.8389371555136,934.6050149992577,1045.5045968182988
l02_s200,dapo_heldout,1536,32,0.0006510416666666666,0.24570719401041666,0.470458984375,0.2838338216145833,0.2911492887504674,2.9823987508835788,0.2613253012416316,0.23150131373279578,0.14202935120628846,0.24570719401041666,1.6704244588216148,0.274383544921875,2.1818346799214683,0.28607600679000217,2.555568710145851,0.2896755731950762,2.7775667160738915,1.6704244588216148,0.053853352864583336,1606.3469918147848,1835.3828374898183,1663.5421850368148
l02_s200,math500,496,32,0.0,0.678679435483871,0.20936239919354838,0.11195816532258064,0.7207394575390914,1.56788068587272,0.7050606506803639,0.6893818438216368,0.6423454232454553,0.678679435483871,1.1340843623991936,0.7066256615423387,1.3243775004725302,0.7163630185588714,1.4474755592807649,0.7195228810909824,1.5167576973415098,1.1340843623991936,0.032069052419354836,1048.226919383251,1568.2608410508903,1585.3081627034069
l02_s300,aime_combined,89,64,0.0,0.047928370786516857,0.8525280898876404,0.0995435393258427,0.05140064930659711,1.8396906533579331,0.033003742773017784,0.014606836239438446,-0.04058388336129954,0.047928370786516857,1.6171490519662919,0.050986986481741575,1.7857070367363062,0.051389018471321365,1.8286560010066193,0.05140062133622436,1.8382204869091745,1.6171490519662919,0.009655898876404494,1615.1741782374831,1627.2672755836995,1764.65797112346
l02_s300,amc,124,64,0.0,0.29322076612903225,0.6145413306451613,0.09223790322580645,0.3096916837872989,1.7856867788279454,0.29183481599901934,0.2739779482107399,0.2204073448459016,0.29322076612903225,1.542094632056452,0.3063905777469758,1.7083048587922127,0.3093974422062597,1.766820227174509,0.30968562470528443,1.7830885094872704,1.542094632056452,0.011214717741935484,1330.6846721407233,1626.316750282869,1869.4188728234583
l02_s300,beyondaime,100,64,0.0,0.0171875,0.885,0.0978125,0.018990912166519328,1.859550273074258,0.0003954094357767502,-0.018200093294965837,-0.07398660148719358,0.0171875,1.6151182812500002,0.01864501953125,1.7919006152343753,0.01896075189113617,1.8485942380285263,0.01899043682684205,1.8588266272180431,1.6151182812500002,0.01015625,1731.3634286323227,1604.9874021278256,1809.3439539442393
l02_s300,bigmath,198,64,0.0,0.6678503787878788,0.2833017676767677,0.048847853535353536,0.6860215913302595,1.0694024124820554,0.675327567205439,0.6646335430806183,0.6325514707061567,0.6678503787878788,0.9619777462121213,0.6821695963541666,1.0397095922604955,0.6855580430440228,1.0653126813284677,0.6860069718992816,1.0692541036389707,0.9619777462121213,0.006549873737373737,859.6431019268025,1316.3652235296904,1649.513261255127
l02_s300,dapo_heldout,1536,64,0.0,0.2563273111979167,0.6549072265625,0.08876546223958333,0.2695216198766565,1.8846835583471948,0.2506747842931845,0.2318279487097126,0.17528744195929677,0.2563273111979167,1.614471211751302,0.2669103940327962,1.7849697642326354,0.2691049999169384,1.8494610630942432,0.26946555063593336,1.8726281112214727,1.614471211751302,0.010772705078125,1506.9088209133074,1690.6338108561786,1927.808367043741
l02_s300,math500,496,64,0.0,0.6860824092741935,0.2651524697580645,0.04876512096774194,0.7033372234054517,1.1995433861488747,0.6913417895439629,0.679346355682474,0.6433600540980078,0.6860824092741935,1.0558516885080647,0.6991828180128529,1.1430292082755797,0.7023845174379887,1.1801112995484184,0.7031770005540092,1.194887448137511,1.0558516885080647,0.006016885080645161,946.7254809790259,1508.3692557100385,1776.494175651665
l02_s620,dapo_heldout,1536,32,0.0,0.2516072591145833,0.55340576171875,0.19498697916666666,0.2871861480494822,1.6351267930678592,0.2708348801188036,0.25448361218812504,0.20542980839608924,0.2516072591145833,1.1131680908203123,0.2745920817057292,1.352218149185181,0.2835189787050088,1.4961723360860102,0.2863045198097171,1.5711288857614392,1.1131680908203123,0.00323486328125,1133.1879039991952,1138.5331507136866,1181.963577281424
l02_s620,math500,496,32,0.0,0.6681577620967742,0.24313256048387097,0.08870967741935484,0.6996456118104375,0.9263327622253416,0.690382284188184,0.6811189565659306,0.6533289736991704,0.6681577620967742,0.7511783644153226,0.6905025359122984,0.8462522799584172,0.697487759974695,0.8956999298757122,0.6991516311484376,0.9168431599287818,0.7511783644153226,0.0008820564516129032,706.3848004331862,901.182829788156,1042.280811153476
l02_s80,dapo_heldout,1536,32,0.0,0.2790730794270833,0.6872355143229166,0.03369140625,0.28343181285436797,2.0964245813109956,0.262467567041258,0.24150332122814802,0.1786105837888182,0.2790730794270833,1.9901888834635415,0.2828318277994792,2.0730800336201987,0.28337712213397026,2.092625321343541,0.28342845484994567,2.0961076369828984,1.9901888834635415,0.022216796875,1838.525725423963,2092.7249213849295,2534.9835835398935
l02_s80,math500,496,32,0.0,0.7190020161290323,0.2677041330645161,0.013293850806451613,0.7234814017868219,1.2857961293463933,0.7106234404933578,0.697765479199894,0.6591915953195021,0.7190020161290323,1.247682837701613,0.7227645381804435,1.2783379142515119,0.7234272014710211,1.2850987240499065,0.7234807966153088,1.2857840670778122,1.247682837701613,0.01171875,1135.585305295336,1737.1490632635766,2517.3736639376884
l05_s120,dapo_heldout,1536,32,0.0,0.2737630208333333,0.71783447265625,0.008402506510416666,0.27506554942848044,1.4488778895797474,0.26057677053268297,0.24608799163688552,0.2026216549494931,0.2737630208333333,1.4324976806640624,0.2749481201171875,1.447258112589518,0.2750575542449951,1.448774483890583,0.2750653459467003,1.4488755079431572,1.4324976806640624,0.002685546875,1396.7885092045149,1484.9278935745401,1926.635330593179
l05_s120,math500,496,32,0.0,0.7130166330645161,0.28295110887096775,0.004032258064516129,0.714944073422496,0.9441416778816089,0.70550265664368,0.6960612398648637,0.6677369895284154,0.7130166330645161,0.9378976814516129,0.7147984658518145,0.9435205845986644,0.7149410497757697,0.9441253060237053,0.7149440691519214,0.9441416508982949,0.9378976814516129,0.0008820564516129032,879.259199272134,1217.027857544945,1507.2673992673992