Human Frontier
83.7
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$1.00/M
Input Price
$0.57/M
Output Price
$2.30/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-08-01:2026-02-01 · Kimi K2 Instruct 0905 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Kimi K2 Instruct 0905__tools · record Kimi K2 Instruct 0905__tools:1754006400000:1769904000000
{
"passAt5": 51.52542372881356,
"developer": "moonshot",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 1723548.7501902613,
"modelReleaseDate": "2025-09-05",
"scoreStandardError": 0.6755293464631847,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1757030400000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.6897268324772987,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1769904000000,
"from": 1754006400000
},
"publishedTaskRangeTimestamp": {
"to": 1769904000000,
"from": 1754006400000
}
}Evidence observed 2026-02-01
vcontinuous-leaderboard · tasks-created:2025-08-01:2025-09-01 · Kimi K2 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Kimi K2__tools · record Kimi K2__tools:1754006400000:1756684800000
{
"passAt5": 51.92307692307693,
"developer": "moonshot",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 892937.2192307692,
"modelReleaseDate": "2025-07-11",
"scoreStandardError": 0.8600261451922262,
"cachedTokenPercentage": null,
"modelReleaseTimestamp": 1752192000000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.45749332730769227,
"potentialContamination": false,
"aggregateTaskRangeTimestamp": {
"to": 1756684800000,
"from": 1754006400000
},
"publishedTaskRangeTimestamp": {
"to": 1756684800000,
"from": 1754006400000
}
}Evidence observed 2025-09-01