Human Frontier
80.9
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$0.85/M
Input Price
$0.30/M
Output Price
$2.50/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-07-01:2025-11-01 · gemini-2.5-flash · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider gemini-2.5-flash__tools · record gemini-2.5-flash__tools:1751328000000:1761955200000
{
"passAt5": 35.16483516483517,
"developer": "google",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 0,
"modelReleaseDate": "2025-06-17",
"scoreStandardError": 0.41044547813716276,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1750118400000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1761955200000,
"from": 1751328000000
},
"publishedTaskRangeTimestamp": {
"to": 1761955200000,
"from": 1751328000000
}
}Evidence observed 2025-11-01