Human Frontier
90.7
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$0.54/M
Input Price
$0.43/M
Output Price
$0.87/M
Speed
55 tok/s
TTFT
1.04s
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2026-03-01:2026-07-01 · DeepSeek-V4 Pro [high] · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider DeepSeek-V4 Pro [high]__tools · record DeepSeek-V4 Pro [high]__tools:1772323200000:1782864000000
{
"passAt5": 62.89592760180995,
"developer": "deepseek",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 3106736.0740800425,
"modelReleaseDate": "2026-04-24",
"scoreStandardError": 0.9533075696834811,
"cachedTokenPercentage": 84.12624744672245,
"modelReleaseTimestamp": 1776988800000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.18284101939597103,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1772323200000
},
"publishedTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1772323200000
}
}Evidence observed 2026-07-01
vcontinuous-leaderboard · tasks-created:2026-03-01:2026-07-01 · DeepSeek-V4 Pro [high] · harness swe-rebench-react@tools · effort high · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider DeepSeek-V4 Pro [high]__tools · record DeepSeek-V4 Pro [high]__tools:1772323200000:1782864000000
{
"passAt5": 62.89592760180995,
"developer": "deepseek",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 3106736.0740800425,
"modelReleaseDate": "2026-04-24",
"scoreStandardError": 0.9533075696834811,
"cachedTokenPercentage": 84.12624744672245,
"modelReleaseTimestamp": 1776988800000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.18284101939597103,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1772323200000
},
"publishedTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1772323200000
}
}Evidence observed 2026-07-01