Human Frontier
80.6
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$0.82/M
Input Price
$0.30/M
Output Price
$2.40/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2026-02-01:2026-03-01 · Qwen3.5-27B · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Qwen3.5-27B__tools · record Qwen3.5-27B__tools:1769904000000:1772323200000
{
"passAt5": 64.91228070175438,
"developer": "alibaba",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2617752.270175439,
"modelReleaseDate": "2026-02-15",
"scoreStandardError": 0.7017543859649119,
"cachedTokenPercentage": 94.91762941099825,
"modelReleaseTimestamp": 1771113600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.5309000963157895,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1769904000000
},
"publishedTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1769904000000
}
}Evidence observed 2026-03-01