Human Frontier
77.1
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$6.00/M
Input Price
$3.00/M
Output Price
$15.00/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-08-01:2025-10-01 · Grok 4 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Grok 4__tools · record Grok 4__tools:1754006400000:1759276800000
{
"passAt5": 49.504950495049506,
"developer": "xai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 1177510.7816039603,
"modelReleaseDate": "2025-07-09",
"scoreStandardError": 1.8737570791350373,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1752019200000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 1.4612028114653466,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1759276800000,
"from": 1754006400000
},
"publishedTaskRangeTimestamp": {
"to": 1759276800000,
"from": 1754006400000
}
}Evidence observed 2025-10-01