Human Frontier
79.8
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:2025-05-01:2025-09-01 · Claude Sonnet 3.5 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Claude Sonnet 3.5__tools · record Claude Sonnet 3.5__tools:1746057600000:1756684800000
{
"passAt5": 45.67901234567901,
"developer": "anthropic",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 0,
"modelReleaseDate": "2024-10-22",
"scoreStandardError": 0.4117907322904589,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1729555200000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1756684800000,
"from": 1746057600000
},
"publishedTaskRangeTimestamp": {
"to": 1756684800000,
"from": 1746057600000
}
}Evidence observed 2025-09-01