Human Frontier
83.6
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$4.81/M
Input Price
$1.75/M
Output Price
$14.00/M
Speed
109 tok/s
TTFT
43.01s
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2026-02-01:2026-03-01 · gpt-5.3-codex-xhigh · harness swe-rebench-react@tools · effort xhigh · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider gpt-5.3-codex-xhigh__tools · record gpt-5.3-codex-xhigh__tools:1769904000000:1772323200000
{
"passAt5": 70.17543859649122,
"developer": "openai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 1771027.652631579,
"modelReleaseDate": "2026-02-05",
"scoreStandardError": 0.8945648269461028,
"cachedTokenPercentage": 84.37114197273779,
"modelReleaseTimestamp": 1770249600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.8868153245614036,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1769904000000
},
"publishedTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1769904000000
}
}Evidence observed 2026-03-01
vcontinuous-leaderboard · tasks-created:2026-02-01:2026-03-01 · gpt-5.3-codex · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider gpt-5.3-codex__tools · record gpt-5.3-codex__tools:1769904000000:1772323200000
{
"passAt5": 62.5,
"developer": "openai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 680434.392857143,
"modelReleaseDate": "2026-02-05",
"scoreStandardError": 1.3363062095621214,
"cachedTokenPercentage": 79.09955471129729,
"modelReleaseTimestamp": 1770249600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.40443676999999995,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1769904000000
},
"publishedTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1769904000000
}
}Evidence observed 2026-03-01