Human Frontier
84.5
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$1.35/M
Input Price
$0.60/M
Output Price
$3.60/M
Speed
64 tok/s
TTFT
1.59s
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2026-02-01:2026-03-01 · Qwen3.5-397B-A17B · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Qwen3.5-397B-A17B__tools · record Qwen3.5-397B-A17B__tools:1769904000000:1772323200000
{
"passAt5": 71.9298245614035,
"developer": "alibaba",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2957222.26660401,
"modelReleaseDate": "2026-02-15",
"scoreStandardError": 1.6354943798653636,
"cachedTokenPercentage": 91.38288729053994,
"modelReleaseTimestamp": 1771113600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 1.1845025964473685,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1769904000000
},
"publishedTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1769904000000
}
}Evidence observed 2026-03-01