Human Frontier
86.9
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$0.53/M
Input Price
$0.30/M
Output Price
$1.20/M
Speed
78 tok/s
TTFT
1.63s
Axes
Filters
Providers
v2026.06 · official-100-task · MiniMax M3 (adaptive) · harness mini-swe-agent · effort adaptive · 1 attempt · pass@1 · harbor:snorkel-ai/senior-swe-bench-v2026.06 · provider openai/minimax/minimax-m3 · record minimax-m3-mini-swe · run 40e12d37c11a5700209734f0cd22d3e42aae26b7d6ae1c19d13dd547769acb3b
{
"taskCount": 100,
"agentGroup": "mini-swe-agent:minimax-m3",
"basicPassAt1": 41.05263157894737,
"basicPassAt3": 50.526315789473685,
"datasetPackage": "snorkel-ai/senior-swe-bench-v2026.06",
"publicTaskCount": 50,
"tastefulPassAt1": 21.052631578947366,
"tastefulPassAt3": 28.421052631578945,
"agentDescription": "MiniMax M3 via mini-swe (Portkey->OpenRouter), adaptive thinking",
"privateTaskCount": 50,
"upstreamProvider": "minimax",
"upstreamRunCount": 50,
"averageAgentSteps": 335.33684210526314,
"averageOutputTokens": 75786.57894736843,
"averageTotalCostUsd": 1.2684179555368422,
"averageOutputCostUsd": 0.09094389473684211,
"basicAllThreePassRate": 21.052631578947366,
"tastefulAllThreePassRate": 8.421052631578947
}Evidence observed 2026-07-30
v2026.06 · official-100-task · MiniMax M3 (adaptive) · harness mini-swe-agent · effort adaptive · 1 attempt · pass@1 · harbor:snorkel-ai/senior-swe-bench-v2026.06 · provider openai/minimax/minimax-m3 · record minimax-m3-mini-swe · run ef8d583a4b3f6b6e11e0d4f03933e933f5d1e6e0bce960327f709628d888eee3
{
"taskCount": 100,
"agentGroup": "mini-swe-agent:minimax-m3",
"basicPassAt1": 35.63218390804598,
"datasetPackage": "snorkel-ai/senior-swe-bench-v2026.06",
"publicTaskCount": 50,
"tastefulPassAt1": 13.793103448275861,
"agentDescription": "MiniMax M3 via mini-swe (Portkey->OpenRouter), adaptive thinking",
"privateTaskCount": 50,
"upstreamProvider": "minimax",
"upstreamRunCount": 50,
"averageAgentSteps": 369.57954545454544,
"averageOutputTokens": 85256.39772727272,
"averageTotalCostUsd": 1.513936438090909,
"averageOutputCostUsd": 0.10230767727272727
}Evidence observed 2026-07-22
vcontinuous-leaderboard · tasks-created:2026-03-01:2026-07-01 · MiniMax M3 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider MiniMax M3__tools · record MiniMax M3__tools:1772323200000:1782864000000
{
"passAt5": 68.32579185520362,
"developer": "minimax",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 10393438.660633486,
"modelReleaseDate": "2026-05-31",
"scoreStandardError": 0.9117394425162844,
"cachedTokenPercentage": 95.2765881633983,
"modelReleaseTimestamp": 1780185600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 1.0094569537194573,
"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 · MiniMax M3 · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider MiniMax M3__tools · record MiniMax M3__tools:1772323200000:1778803200000
{
"passAt5": 67.27272727272727,
"developer": "minimax",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 6885817.818181818,
"modelReleaseDate": "2026-05-31",
"scoreStandardError": 1.2662171161076474,
"cachedTokenPercentage": 93.51696897271863,
"modelReleaseTimestamp": 1780185600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 1.0648923078545454,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1772323200000
},
"publishedTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1772323200000
}
}Evidence observed 2026-05-15