Human Frontier
—
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$3.44/M
Input Price
$1.25/M
Output Price
$10.00/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-11-01:2026-02-01 · gpt-5.1-codex-max · harness swe-rebench-react@tools · effort max · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider gpt-5.1-codex-max__tools · record gpt-5.1-codex-max__tools:1761955200000:1769904000000
{
"passAt5": 66.43356643356644,
"developer": "openai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 1308803.2846055352,
"modelReleaseDate": "2025-11-19",
"scoreStandardError": 1.597583179363583,
"cachedTokenPercentage": 72.71792333880192,
"modelReleaseTimestamp": 1763510400000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.649101685235891,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1769904000000,
"from": 1761955200000
},
"publishedTaskRangeTimestamp": {
"to": 1769904000000,
"from": 1761955200000
}
}Evidence observed 2026-02-01