Human Frontier
91.5
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
44 tok/s
TTFT
2.13s
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2026-03-01:2026-07-01 · MiMo V2.5 Pro · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider MiMo V2.5 Pro__tools · record MiMo V2.5 Pro__tools:1772323200000:1782864000000
{
"passAt5": 63.80090497737556,
"developer": "xiaomi",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 3642245.8018099545,
"modelReleaseDate": "2026-03-22",
"scoreStandardError": 0.5615236943887267,
"cachedTokenPercentage": 92.15941381888013,
"modelReleaseTimestamp": 1774137600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.11402410070009053,
"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 · MiMo V2.5 Pro · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider MiMo V2.5 Pro__tools · record MiMo V2.5 Pro__tools:1772323200000:1778803200000
{
"passAt5": 61.81818181818181,
"developer": "xiaomi",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2586997.812727273,
"modelReleaseDate": "2026-03-22",
"scoreStandardError": 0.8430562268632452,
"cachedTokenPercentage": 88.59134650558231,
"modelReleaseTimestamp": 1774137600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.12458069619927273,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1772323200000
},
"publishedTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1772323200000
}
}Evidence observed 2026-05-15