Human Frontier
89.2
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:2025-09-01:2026-03-01 · Claude Sonnet 4.5 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Claude Sonnet 4.5__tools · record Claude Sonnet 4.5__tools:1756684800000:1772323200000
{
"passAt5": 64.54849498327759,
"developer": "anthropic",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 1995406.6802675587,
"modelReleaseDate": "2025-09-29",
"scoreStandardError": 0.8287298791547733,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1759104000000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.9791713679598661,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1756684800000
},
"publishedTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1756684800000
}
}Evidence observed 2026-03-01