intelligence-radar/catalog/reviewed-2026-09-13.json
tegwick 29ceb77938 Build reproducible capability advisor and scheduled source capture
Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a09c77-b1a9-7eb3-b501-6cb24b458c97
2026-09-13 23:07:41 +02:00

185 lines
5.5 KiB
JSON

{
"synthetic": false,
"benchmarks": [
{
"id": "swe-bench-verified",
"version": "pending-verification",
"constructs": [
"coding"
],
"health": {
"ecological_validity": 0.5,
"measurement_reliability": 0.5,
"discriminative_power": 0.5,
"freshness": 0.5,
"execution_profile_similarity": 0.5,
"reproducibility": 0.5,
"contamination_resistance": 0.5
},
"scale": {
"minimum": 0,
"maximum": 100
},
"limitations": "Candidate instrument only. Exact benchmark version, health and profile-matched result need review. Health values are neutral curator placeholders."
},
{
"id": "terminal-bench",
"version": "pending-verification",
"constructs": [
"coding",
"tool_use"
],
"health": {
"ecological_validity": 0.5,
"measurement_reliability": 0.5,
"discriminative_power": 0.5,
"freshness": 0.5,
"execution_profile_similarity": 0.5,
"reproducibility": 0.5,
"contamination_resistance": 0.5
},
"scale": {
"minimum": 0,
"maximum": 100
},
"limitations": "Candidate instrument only. Exact benchmark version, health and profile-matched result need review. Health values are neutral curator placeholders."
},
{
"id": "bfcl",
"version": "pending-verification",
"constructs": [
"tool_use"
],
"health": {
"ecological_validity": 0.5,
"measurement_reliability": 0.5,
"discriminative_power": 0.5,
"freshness": 0.5,
"execution_profile_similarity": 0.5,
"reproducibility": 0.5,
"contamination_resistance": 0.5
},
"scale": {
"minimum": 0,
"maximum": 100
},
"limitations": "Candidate instrument only. Exact benchmark version, health and profile-matched result need review. Health values are neutral curator placeholders."
},
{
"id": "browsecomp",
"version": "pending-verification",
"constructs": [
"web_research"
],
"health": {
"ecological_validity": 0.5,
"measurement_reliability": 0.5,
"discriminative_power": 0.5,
"freshness": 0.5,
"execution_profile_similarity": 0.5,
"reproducibility": 0.5,
"contamination_resistance": 0.5
},
"scale": {
"minimum": 0,
"maximum": 100
},
"limitations": "Candidate instrument only. Exact benchmark version, health and profile-matched result need review. Health values are neutral curator placeholders."
},
{
"id": "scicode",
"version": "pending-verification",
"constructs": [
"coding",
"reasoning"
],
"health": {
"ecological_validity": 0.5,
"measurement_reliability": 0.5,
"discriminative_power": 0.5,
"freshness": 0.5,
"execution_profile_similarity": 0.5,
"reproducibility": 0.5,
"contamination_resistance": 0.5
},
"scale": {
"minimum": 0,
"maximum": 100
},
"limitations": "Candidate instrument only. Exact benchmark version, health and profile-matched result need review. Health values are neutral curator placeholders."
}
],
"profiles": [
{
"id": "claude-sonnet-5-api-default",
"model": "claude-sonnet-5",
"harness": "direct-api-no-tools",
"effort": "provider-default-unspecified",
"provider": "Anthropic",
"deployment": "Claude Platform/global/standard",
"attributes": {
"requester_access": false
},
"availability": {
"observed_at": "2026-09-13T20:49:30.828142+00:00",
"capture_id": "74b6b3868ee49b78e44df9ab1c088042ad36bb45627edf3079c81a8942370dda",
"review_status": "reviewed",
"reviewer": "codex",
"available": true
}
},
{
"id": "claude-haiku-4-5-api-default",
"model": "claude-haiku-4-5",
"harness": "direct-api-no-tools",
"effort": "provider-default-unspecified",
"provider": "Anthropic",
"deployment": "Claude Platform/global/standard",
"attributes": {
"requester_access": false
},
"availability": {
"observed_at": "2026-09-13T20:49:30.528597+00:00",
"capture_id": "42c09fd59fada0dd8b1e77dde13e5a33d0ae696a8675d39af691941bd8c8028e",
"review_status": "reviewed",
"reviewer": "codex",
"available": true
}
}
],
"results": [],
"prices": [
{
"observed_at": "2026-09-13T20:49:30.528597+00:00",
"capture_id": "42c09fd59fada0dd8b1e77dde13e5a33d0ae696a8675d39af691941bd8c8028e",
"review_status": "reviewed",
"reviewer": "codex",
"profile_id": "claude-sonnet-5-api-default",
"currency": "USD",
"valid_from": "2026-09-13",
"valid_until": "2026-09-13",
"usd_per_million": {
"input": 2,
"output": 10,
"cached_input": 0.2,
"cache_write": 2.5
}
},
{
"observed_at": "2026-09-13T20:49:30.528597+00:00",
"capture_id": "42c09fd59fada0dd8b1e77dde13e5a33d0ae696a8675d39af691941bd8c8028e",
"review_status": "reviewed",
"reviewer": "codex",
"profile_id": "claude-haiku-4-5-api-default",
"currency": "USD",
"valid_from": "2026-09-13",
"valid_until": "2026-09-13",
"usd_per_million": {
"input": 1,
"output": 5,
"cached_input": 0.1,
"cache_write": 1.25
}
}
]
}