Human Frontier
84.7
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
Free/M
Input Price
Free/M
Output Price
Free/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-07-01:2026-02-01 · DeepSeek-R1-0528 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider DeepSeek-R1-0528__tools · record DeepSeek-R1-0528__tools:1751328000000:1769904000000
{
"passAt5": 38.2716049382716,
"developer": "deepseek",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 0,
"modelReleaseDate": "2025-05-28",
"scoreStandardError": 1.0699905998080443,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1748390400000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1769904000000,
"from": 1751328000000
},
"publishedTaskRangeTimestamp": {
"to": 1769904000000,
"from": 1751328000000
}
}Evidence observed 2026-02-01