Human Frontier
89.1
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$1.00/M
Input Price
$0.60/M
Output Price
$2.20/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-12-01:2026-05-15 · GLM-4.7 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider GLM-4.7__tools · record GLM-4.7__tools:1764547200000:1778803200000
{
"passAt5": 62.3574144486692,
"developer": "zhipu",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2173658.1844774047,
"modelReleaseDate": "2025-12-22",
"scoreStandardError": 0.4234518845167259,
"cachedTokenPercentage": 88.14456273319895,
"modelReleaseTimestamp": 1766361600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.36561502261834977,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1764547200000
},
"publishedTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1764547200000
}
}Evidence observed 2026-05-15