Human Frontier
84.3
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$0.86/M
Input Price
$0.59/M
Output Price
$1.69/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-08-01:2025-11-01 · DeepSeek-V3.1 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider DeepSeek-V3.1__tools · record DeepSeek-V3.1__tools:1754006400000:1761955200000
{
"passAt5": 43.42105263157895,
"developer": "deepseek",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 1324465.7343549435,
"modelReleaseDate": "2025-08-21",
"scoreStandardError": 0.8037911714492743,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1755734400000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.36237847216816893,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1761955200000,
"from": 1754006400000
},
"publishedTaskRangeTimestamp": {
"to": 1761955200000,
"from": 1754006400000
}
}Evidence observed 2025-11-01