Human Frontier
78.2
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$1.93/M
Input Price
$1.10/M
Output Price
$4.40/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-07-01:2025-12-01 · o4-mini-2025-04-16 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider o4-mini-2025-04-16__tools · record o4-mini-2025-04-16__tools:1751328000000:1764547200000
{
"passAt5": 41.04803493449782,
"developer": "openai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 0,
"modelReleaseDate": "2025-04-16",
"scoreStandardError": 0.6019235262921496,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1744761600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1764547200000,
"from": 1751328000000
},
"publishedTaskRangeTimestamp": {
"to": 1764547200000,
"from": 1751328000000
}
}Evidence observed 2025-12-01