Human Frontier
75.9
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$0.10/M
Input Price
$0.070/M
Output Price
$0.20/M
Speed
186 tok/s
TTFT
0.59s
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-08-01:2025-09-01 · gpt-oss-20b · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider gpt-oss-20b__tools · record gpt-oss-20b__tools:1754006400000:1756684800000
{
"passAt5": 23.076923076923077,
"developer": "openai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 0,
"modelReleaseDate": "2025-07-13",
"scoreStandardError": 1.1213369028548656,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1752364800000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1756684800000,
"from": 1754006400000
},
"publishedTaskRangeTimestamp": {
"to": 1756684800000,
"from": 1754006400000
}
}Evidence observed 2025-09-01