Human Frontier
—
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$0.56/M
Input Price
$0.25/M
Output Price
$1.49/M
Speed
134 tok/s
TTFT
1.31s
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2026-03-01:2026-07-01 · Qwen3.6-35B-A3B · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Qwen3.6-35B-A3B__tools · record Qwen3.6-35B-A3B__tools:1772323200000:1782864000000
{
"passAt5": 48.86877828054298,
"developer": "alibaba",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2981378.1049773754,
"modelReleaseDate": "2026-03-14",
"scoreStandardError": 0.5079172923222539,
"cachedTokenPercentage": 82.96985287501887,
"modelReleaseTimestamp": 1773446400000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.22538132466968328,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1772323200000
},
"publishedTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1772323200000
}
}Evidence observed 2026-07-01
vcontinuous-leaderboard · tasks-created:2026-03-01:2026-05-15 · Qwen3.6-35B-A3B · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Qwen3.6-35B-A3B__tools · record Qwen3.6-35B-A3B__tools:1772323200000:1778803200000
{
"passAt5": 54.54545454545454,
"developer": "alibaba",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2229925.44,
"modelReleaseDate": "2026-03-14",
"scoreStandardError": 0.9270944570168703,
"cachedTokenPercentage": 78.39277993598903,
"modelReleaseTimestamp": 1773446400000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.1817398307636364,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1772323200000
},
"publishedTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1772323200000
}
}Evidence observed 2026-05-15