Human Frontier
80.9
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$3.00/M
Input Price
$1.50/M
Output Price
$7.50/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-07-01:2026-03-01 · Qwen3-Coder-480B-A35B-Instruct · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Qwen3-Coder-480B-A35B-Instruct__tools · record Qwen3-Coder-480B-A35B-Instruct__tools:1751328000000:1772323200000
{
"passAt5": 50,
"developer": "alibaba",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 0,
"modelReleaseDate": "2025-07-22",
"scoreStandardError": 0.6240184559572816,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1753142400000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1751328000000
},
"publishedTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1751328000000
}
}Evidence observed 2026-03-01