Human Frontier
84.6
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$4.81/M
Input Price
$1.75/M
Output Price
$14.00/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-12-01:2026-02-01 · gpt-5.2-2025-12-11-xhigh · harness swe-rebench-react@tools · effort xhigh · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider gpt-5.2-2025-12-11-xhigh__tools · record gpt-5.2-2025-12-11-xhigh__tools:1764547200000:1769904000000
{
"passAt5": 64.58333333333334,
"developer": "openai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 1909938.5220175437,
"modelReleaseDate": "2025-12-11",
"scoreStandardError": 0.3045917639386849,
"cachedTokenPercentage": 74.35348070732941,
"modelReleaseTimestamp": 1765411200000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 1.371884737654605,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1769904000000,
"from": 1764547200000
},
"publishedTaskRangeTimestamp": {
"to": 1769904000000,
"from": 1764547200000
}
}Evidence observed 2026-02-01