Human Frontier
78.8
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$0.26/M
Input Price
$0.15/M
Output Price
$0.60/M
Speed
194 tok/s
TTFT
0.54s
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-08-01:2026-03-01 · gpt-oss-120b · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider gpt-oss-120b__tools · record gpt-oss-120b__tools:1754006400000:1772323200000
{
"passAt5": 41.76136363636363,
"developer": "openai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 984778.178873115,
"modelReleaseDate": "2025-07-13",
"scoreStandardError": 0.43015859883713925,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1752364800000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.0863527183021023,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1754006400000
},
"publishedTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1754006400000
}
}Evidence observed 2026-03-01
vcontinuous-leaderboard · tasks-created:2025-12-01:2026-01-01 · gpt-oss-120b-high · harness swe-rebench-react@tools · effort high · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider gpt-oss-120b-high__tools · record gpt-oss-120b-high__tools:1764547200000:1767225600000
{
"passAt5": 62.5,
"developer": "openai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 1673240.5163120567,
"modelReleaseDate": "2025-08-05",
"scoreStandardError": 3.5338440713801917,
"cachedTokenPercentage": 91.39581727953724,
"modelReleaseTimestamp": 1754352000000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.2624850758909575,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1767225600000,
"from": 1764547200000
},
"publishedTaskRangeTimestamp": {
"to": 1767225600000,
"from": 1764547200000
}
}Evidence observed 2026-01-01