{
 "mmmu": {
  "n": 900,
  "ok": 704,
  "trunc": 1,
  "errors": 0,
  "tokens": 1044906,
  "acc": 78.22,
  "total": 900,
  "minutes": 11.3
 },
 "toolcall": {
  "n": 800,
  "ok": 623,
  "trunc": 1,
  "errors": 0,
  "tokens": 149727,
  "name_ok": 667,
  "acc": 77.88,
  "total": 800,
  "minutes": 12.4
 },
 "gpqa": {
  "n": 198,
  "ok": 150,
  "trunc": 3,
  "errors": 0,
  "tokens": 812122,
  "acc": 75.76,
  "total": 198,
  "minutes": 25.8
 },
 "ceval": {
  "n": 1346,
  "ok": 1211,
  "trunc": 0,
  "errors": 0,
  "tokens": 917558,
  "acc": 89.97,
  "total": 1346,
  "minutes": 26.9
 },
 "aime26": {
  "n": 120,
  "ok": 114,
  "trunc": 6,
  "errors": 0,
  "tokens": 2338742,
  "acc": 95.0,
  "total": 120,
  "minutes": 54.1
 },
 "humaneval": {
  "n": 164,
  "ok": 162,
  "trunc": 0,
  "errors": 0,
  "tokens": 110345,
  "acc": 98.78,
  "total": 164,
  "minutes": 79.3
 },
 "mmlu": {
  "n": 14042,
  "ok": 12269,
  "trunc": 8,
  "errors": 0,
  "tokens": 9486427,
  "acc": 87.37,
  "total": 14042,
  "minutes": 81.0
 }
}