Spaces:
Running
Running
Publish codex SIMPLE seed-0 evaluation evidence
Browse files- comparison.json +85 -0
- data.json +1 -1
- manifest.json +2 -2
- publication-manifest.json +4 -4
comparison.json
CHANGED
|
@@ -3941,6 +3941,91 @@
|
|
| 3941 |
"unidentified_usage_records": 0
|
| 3942 |
}
|
| 3943 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3944 |
{
|
| 3945 |
"task_key": "task06/11",
|
| 3946 |
"kinex_success": true,
|
|
|
|
| 3941 |
"unidentified_usage_records": 0
|
| 3942 |
}
|
| 3943 |
},
|
| 3944 |
+
{
|
| 3945 |
+
"task_key": "task06/10",
|
| 3946 |
+
"kinex_success": true,
|
| 3947 |
+
"codex_success": true,
|
| 3948 |
+
"same_instruction": true,
|
| 3949 |
+
"same_budget": true,
|
| 3950 |
+
"same_roboenv_source": true,
|
| 3951 |
+
"kinex_steps": 6641,
|
| 3952 |
+
"codex_steps": 1710,
|
| 3953 |
+
"kinex_usage": {
|
| 3954 |
+
"input_tokens": 5852385,
|
| 3955 |
+
"output_tokens": 12793,
|
| 3956 |
+
"cached_input_tokens": 5652608,
|
| 3957 |
+
"cache_write_input_tokens": 0,
|
| 3958 |
+
"reasoning_output_tokens": 4543,
|
| 3959 |
+
"cache_reported_input_tokens": 5852385,
|
| 3960 |
+
"cache_write_reported_input_tokens": 5852385,
|
| 3961 |
+
"reasoning_reported_output_tokens": 12793,
|
| 3962 |
+
"schema": "rlebench/token-usage/1",
|
| 3963 |
+
"source": "Provider terminal response usage",
|
| 3964 |
+
"response_count": 130,
|
| 3965 |
+
"reported_responses": {
|
| 3966 |
+
"input_tokens": 130,
|
| 3967 |
+
"output_tokens": 130,
|
| 3968 |
+
"cached_input_tokens": 130,
|
| 3969 |
+
"cache_write_input_tokens": 130,
|
| 3970 |
+
"reasoning_output_tokens": 130,
|
| 3971 |
+
"cache_reported_input_tokens": 130,
|
| 3972 |
+
"cache_write_reported_input_tokens": 130,
|
| 3973 |
+
"reasoning_reported_output_tokens": 130
|
| 3974 |
+
},
|
| 3975 |
+
"known_cached_input_tokens": 5652608,
|
| 3976 |
+
"known_input_tokens": 5852385,
|
| 3977 |
+
"known_output_tokens": 12793,
|
| 3978 |
+
"known_cache_write_input_tokens": 0,
|
| 3979 |
+
"known_reasoning_output_tokens": 4543,
|
| 3980 |
+
"cache_hit_rate": 0.9658640024537005,
|
| 3981 |
+
"uncached_input_tokens": 199777,
|
| 3982 |
+
"cost_usd": null,
|
| 3983 |
+
"response_ids_complete": true,
|
| 3984 |
+
"accounting": "reported-responses",
|
| 3985 |
+
"usage_source": "provider-raw",
|
| 3986 |
+
"request_attempts": 130,
|
| 3987 |
+
"rejected_attempts": 0,
|
| 3988 |
+
"unresolved_attempts": [],
|
| 3989 |
+
"audit_complete": true
|
| 3990 |
+
},
|
| 3991 |
+
"codex_usage": {
|
| 3992 |
+
"accounting": "reported-responses",
|
| 3993 |
+
"audit_complete": true,
|
| 3994 |
+
"cache_hit_rate": 0.9782577578812951,
|
| 3995 |
+
"cache_reported_input_tokens": 2661777,
|
| 3996 |
+
"cache_write_input_tokens": 0,
|
| 3997 |
+
"cache_write_reported_input_tokens": 2661777,
|
| 3998 |
+
"cached_input_tokens": 2603904,
|
| 3999 |
+
"completed_turns": 1,
|
| 4000 |
+
"cost_usd": null,
|
| 4001 |
+
"failed_turns": 0,
|
| 4002 |
+
"input_tokens": 2661777,
|
| 4003 |
+
"known_cache_write_input_tokens": 0,
|
| 4004 |
+
"known_cached_input_tokens": 2603904,
|
| 4005 |
+
"known_input_tokens": 2661777,
|
| 4006 |
+
"known_output_tokens": 11612,
|
| 4007 |
+
"known_reasoning_output_tokens": 4313,
|
| 4008 |
+
"output_tokens": 11612,
|
| 4009 |
+
"reasoning_output_tokens": 4313,
|
| 4010 |
+
"reasoning_reported_output_tokens": 11612,
|
| 4011 |
+
"reported_responses": {
|
| 4012 |
+
"cache_reported_input_tokens": 62,
|
| 4013 |
+
"cache_write_input_tokens": 62,
|
| 4014 |
+
"cache_write_reported_input_tokens": 62,
|
| 4015 |
+
"cached_input_tokens": 62,
|
| 4016 |
+
"input_tokens": 62,
|
| 4017 |
+
"output_tokens": 62,
|
| 4018 |
+
"reasoning_output_tokens": 62,
|
| 4019 |
+
"reasoning_reported_output_tokens": 62
|
| 4020 |
+
},
|
| 4021 |
+
"response_count": 62,
|
| 4022 |
+
"response_ids_complete": true,
|
| 4023 |
+
"schema": "rlebench/token-usage/1",
|
| 4024 |
+
"source": "Codex token_usage_record per response",
|
| 4025 |
+
"uncached_input_tokens": 57873,
|
| 4026 |
+
"unidentified_usage_records": 0
|
| 4027 |
+
}
|
| 4028 |
+
},
|
| 4029 |
{
|
| 4030 |
"task_key": "task06/11",
|
| 4031 |
"kinex_success": true,
|
data.json
CHANGED
|
@@ -6,7 +6,7 @@
|
|
| 6 |
"benchmark_complete": true,
|
| 7 |
"edition": "codex-simple-astra-high-seed0",
|
| 8 |
"created_at": "2026-10-09T00:09:42.989838+00:00",
|
| 9 |
-
"updated_at": "2026-10-10T02:
|
| 10 |
"model": "gpt-6-astra",
|
| 11 |
"effort": "high",
|
| 12 |
"seed": 0,
|
|
|
|
| 6 |
"benchmark_complete": true,
|
| 7 |
"edition": "codex-simple-astra-high-seed0",
|
| 8 |
"created_at": "2026-10-09T00:09:42.989838+00:00",
|
| 9 |
+
"updated_at": "2026-10-10T02:50:00.958247+00:00",
|
| 10 |
"model": "gpt-6-astra",
|
| 11 |
"effort": "high",
|
| 12 |
"seed": 0,
|
manifest.json
CHANGED
|
@@ -18,8 +18,8 @@
|
|
| 18 |
"catalog/task06/10-open-faucet/task.yaml": "dcdd2228bfd8de298da36798856f5ff59b523c7104118103530eb7a641b52197",
|
| 19 |
"catalog/task06/11-push-office-chair/task.yaml": "0e2de1c50619b0c58fd939f58362dfc0630f34d4e19587fe4927a2c4e5c1d785",
|
| 20 |
"catalog/task06/12-open-trash-can/task.yaml": "e02833927892caa9c40ed193348aab1858e6ae6208c4c04892dec8eae4ad45f0",
|
| 21 |
-
"comparison.json": "
|
| 22 |
-
"data.json": "
|
| 23 |
"episodes.csv": "b5348f09433a027527df8df86037734f77393bef66f65b3eadacba143973bee5",
|
| 24 |
"episodes.json": "83441d4be35047527e34dd021c680b71f3b85e1a63d1b18e519deaf8b9fc4d0c",
|
| 25 |
"failure-reviews.json": "c66a997c9ecd6f7f43f130a8a33cd64c7a5b2049033e9ccde653ee30e4796f23",
|
|
|
|
| 18 |
"catalog/task06/10-open-faucet/task.yaml": "dcdd2228bfd8de298da36798856f5ff59b523c7104118103530eb7a641b52197",
|
| 19 |
"catalog/task06/11-push-office-chair/task.yaml": "0e2de1c50619b0c58fd939f58362dfc0630f34d4e19587fe4927a2c4e5c1d785",
|
| 20 |
"catalog/task06/12-open-trash-can/task.yaml": "e02833927892caa9c40ed193348aab1858e6ae6208c4c04892dec8eae4ad45f0",
|
| 21 |
+
"comparison.json": "ecd341ca400be6879fa870e61fc69a5685149e0607225c18f50cd27f7bf42d76",
|
| 22 |
+
"data.json": "ab7a1d36d95a2eaf4749ee2aa32935cc06a7c7f3f7fbd001dd6a04432e2034b2",
|
| 23 |
"episodes.csv": "b5348f09433a027527df8df86037734f77393bef66f65b3eadacba143973bee5",
|
| 24 |
"episodes.json": "83441d4be35047527e34dd021c680b71f3b85e1a63d1b18e519deaf8b9fc4d0c",
|
| 25 |
"failure-reviews.json": "c66a997c9ecd6f7f43f130a8a33cd64c7a5b2049033e9ccde653ee30e4796f23",
|
publication-manifest.json
CHANGED
|
@@ -78,11 +78,11 @@
|
|
| 78 |
"bytes": 338
|
| 79 |
},
|
| 80 |
"comparison.json": {
|
| 81 |
-
"sha256": "
|
| 82 |
-
"bytes":
|
| 83 |
},
|
| 84 |
"data.json": {
|
| 85 |
-
"sha256": "
|
| 86 |
"bytes": 1219597
|
| 87 |
},
|
| 88 |
"episodes.csv": {
|
|
@@ -142,7 +142,7 @@
|
|
| 142 |
"bytes": 234353
|
| 143 |
},
|
| 144 |
"manifest.json": {
|
| 145 |
-
"sha256": "
|
| 146 |
"bytes": 3481
|
| 147 |
}
|
| 148 |
}
|
|
|
|
| 78 |
"bytes": 338
|
| 79 |
},
|
| 80 |
"comparison.json": {
|
| 81 |
+
"sha256": "ecd341ca400be6879fa870e61fc69a5685149e0607225c18f50cd27f7bf42d76",
|
| 82 |
+
"bytes": 157815
|
| 83 |
},
|
| 84 |
"data.json": {
|
| 85 |
+
"sha256": "ab7a1d36d95a2eaf4749ee2aa32935cc06a7c7f3f7fbd001dd6a04432e2034b2",
|
| 86 |
"bytes": 1219597
|
| 87 |
},
|
| 88 |
"episodes.csv": {
|
|
|
|
| 142 |
"bytes": 234353
|
| 143 |
},
|
| 144 |
"manifest.json": {
|
| 145 |
+
"sha256": "ddc2fb39dccb0c5d05dc2da437fefcc9dee9a1d70e9990258a7263384aef9945",
|
| 146 |
"bytes": 3481
|
| 147 |
}
|
| 148 |
}
|