Human Frontier
88.6
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$30.00/M
Input Price
$15.00/M
Output Price
$75.00/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-09-01:2025-12-01 · Claude Opus 4.1 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Claude Opus 4.1__tools · record Claude Opus 4.1__tools:1756684800000:1764547200000
{
"passAt5": 54.421768707483,
"developer": "anthropic",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 1779063.1504892367,
"modelReleaseDate": "2025-08-05",
"scoreStandardError": 1.2909680970336588,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1754352000000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 4.251827704389153,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1764547200000,
"from": 1756684800000
},
"publishedTaskRangeTimestamp": {
"to": 1764547200000,
"from": 1756684800000
}
}Evidence observed 2025-12-01