Human Frontier
77.7
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$4.81/M
Input Price
$1.75/M
Output Price
$14.00/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2026-01-01:2026-03-01 · gpt-5.2-codex · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider gpt-5.2-codex__tools · record gpt-5.2-codex__tools:1767225600000:1772323200000
{
"passAt5": 59.61538461538461,
"developer": "openai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 661953.5403846154,
"modelReleaseDate": "2025-12-18",
"scoreStandardError": 1.2388556468004936,
"cachedTokenPercentage": 70.83085152655448,
"modelReleaseTimestamp": 1766016000000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.4398054520192307,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1767225600000
},
"publishedTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1767225600000
}
}Evidence observed 2026-03-01