roadmodel 0.2.73__tar.gz → 0.2.75__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {roadmodel-0.2.73 → roadmodel-0.2.75}/PKG-INFO +1 -1
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/benchmarks.json +111 -49
- {roadmodel-0.2.73/roadmodel/data → roadmodel-0.2.75/docs}/catalog.json +119 -58
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/model-selector.txt +76 -56
- {roadmodel-0.2.73/roadmodel/data → roadmodel-0.2.75/docs}/model-tier-cost-scale.md +8 -4
- {roadmodel-0.2.73 → roadmodel-0.2.75}/pyproject.toml +1 -1
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/benchmarks.json +111 -49
- {roadmodel-0.2.73/docs → roadmodel-0.2.75/roadmodel/data}/catalog.json +119 -58
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/model-selector.txt +76 -56
- {roadmodel-0.2.73/docs → roadmodel-0.2.75/roadmodel/data}/model-tier-cost-scale.md +8 -4
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/__init__.py +1 -1
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/recommend.py +5 -1
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/scoring.py +68 -18
- {roadmodel-0.2.73 → roadmodel-0.2.75}/.gitignore +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/LICENSE +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/NOTICE +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/README.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/context-windows.json +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/settings-display.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/templates/phase-roadmap-template.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/templates/planning-kit-how-to-use.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/templates/project-roadmap-template.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/templates/prompt-phase-roadmap.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/templates/prompt-project-roadmap.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/docs/user-context.example.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/hatch_build.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/infra/README.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/infra/gcp-killswitch/README.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/infra/supabase/README.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/context-windows.json +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/phase-roadmap-template.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/planning-kit-how-to-use.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/project-roadmap-template.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/prompt-phase-roadmap.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/prompt-project-roadmap.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/settings-display.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/roadmodel/data/user-context.example.md +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/scripts/agent_context.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/scripts/agent_rules.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/scripts/update_projects.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/scripts/updater_lock.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/scripts/upgrade_fleet.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/scripts/worktree_memory.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/__main__.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/cli.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/config.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/cost.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/errors.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/mcp_server.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/providers/__init__.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/providers/anthropic.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/providers/google.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/providers/openai.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/providers/openai_compatible.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/providers/registry.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/usage.py +0 -0
- {roadmodel-0.2.73 → roadmodel-0.2.75}/src/roadmodel/user_context.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: roadmodel
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.75
|
|
4
4
|
Summary: BYO-key CLI that recommends the right AI model, platform, and settings for a prompt.
|
|
5
5
|
Project-URL: Homepage, https://roadmodel.ai
|
|
6
6
|
Project-URL: Repository, https://github.com/nathanramoscfa/roadmodel
|
|
@@ -6,8 +6,8 @@
|
|
|
6
6
|
"endpoint": "https://artificialanalysis.ai/api/v2/data/llms/models",
|
|
7
7
|
"attribution": "Benchmark data © Artificial Analysis, used under its API terms with attribution."
|
|
8
8
|
},
|
|
9
|
-
"generated_at_utc": "2026-10-
|
|
10
|
-
"model_count":
|
|
9
|
+
"generated_at_utc": "2026-10-07T22:56:43Z",
|
|
10
|
+
"model_count": 56,
|
|
11
11
|
"unmapped": [],
|
|
12
12
|
"missing_slugs": [],
|
|
13
13
|
"mismatched": [],
|
|
@@ -100,8 +100,8 @@
|
|
|
100
100
|
"tau2": null,
|
|
101
101
|
"tau_banking": 0.472164948453608
|
|
102
102
|
},
|
|
103
|
-
"median_output_tokens_per_second":
|
|
104
|
-
"median_time_to_first_token_seconds":
|
|
103
|
+
"median_output_tokens_per_second": 67.41,
|
|
104
|
+
"median_time_to_first_token_seconds": 145.247,
|
|
105
105
|
"aa_effort": "max",
|
|
106
106
|
"effort_variants": {
|
|
107
107
|
"low": {
|
|
@@ -292,8 +292,8 @@
|
|
|
292
292
|
"tau2": null,
|
|
293
293
|
"tau_banking": null
|
|
294
294
|
},
|
|
295
|
-
"median_output_tokens_per_second": 97.
|
|
296
|
-
"median_time_to_first_token_seconds":
|
|
295
|
+
"median_output_tokens_per_second": 97.16,
|
|
296
|
+
"median_time_to_first_token_seconds": 512.808,
|
|
297
297
|
"aa_effort": "max",
|
|
298
298
|
"effort_variants": {
|
|
299
299
|
"low": {
|
|
@@ -342,7 +342,7 @@
|
|
|
342
342
|
"lcr": 0.846666666666667,
|
|
343
343
|
"terminalbench_v4_0": 0.595959595959596
|
|
344
344
|
},
|
|
345
|
-
"median_output_tokens_per_second":
|
|
345
|
+
"median_output_tokens_per_second": 75.986
|
|
346
346
|
}
|
|
347
347
|
}
|
|
348
348
|
},
|
|
@@ -452,8 +452,8 @@
|
|
|
452
452
|
"tau2": null,
|
|
453
453
|
"tau_banking": null
|
|
454
454
|
},
|
|
455
|
-
"median_output_tokens_per_second":
|
|
456
|
-
"median_time_to_first_token_seconds":
|
|
455
|
+
"median_output_tokens_per_second": 133.893,
|
|
456
|
+
"median_time_to_first_token_seconds": 246.693,
|
|
457
457
|
"aa_effort": "max",
|
|
458
458
|
"effort_variants": {
|
|
459
459
|
"low": {
|
|
@@ -532,7 +532,7 @@
|
|
|
532
532
|
"tau2": null,
|
|
533
533
|
"tau_banking": null
|
|
534
534
|
},
|
|
535
|
-
"median_output_tokens_per_second":
|
|
535
|
+
"median_output_tokens_per_second": 215.593,
|
|
536
536
|
"median_time_to_first_token_seconds": 0.865,
|
|
537
537
|
"aa_effort": "max",
|
|
538
538
|
"effort_variants": {}
|
|
@@ -563,8 +563,8 @@
|
|
|
563
563
|
"tau2": null,
|
|
564
564
|
"tau_banking": 0.395876288659794
|
|
565
565
|
},
|
|
566
|
-
"median_output_tokens_per_second":
|
|
567
|
-
"median_time_to_first_token_seconds": 1.
|
|
566
|
+
"median_output_tokens_per_second": 94.966,
|
|
567
|
+
"median_time_to_first_token_seconds": 1.113,
|
|
568
568
|
"aa_effort": "max",
|
|
569
569
|
"effort_variants": {}
|
|
570
570
|
},
|
|
@@ -680,6 +680,37 @@
|
|
|
680
680
|
}
|
|
681
681
|
}
|
|
682
682
|
},
|
|
683
|
+
"gemini-3.1-flash-lite": {
|
|
684
|
+
"aa_id": "598190f8-dc9c-4fea-a7ea-4b81c402ab18",
|
|
685
|
+
"aa_slug": "gemini-3-1-flash-lite-preview",
|
|
686
|
+
"aa_name": "Gemini 3.1 Flash-Lite",
|
|
687
|
+
"aa_creator": "Google",
|
|
688
|
+
"release_date": "2026-03-03",
|
|
689
|
+
"evaluations": {
|
|
690
|
+
"artificial_analysis_intelligence_index": 15.6,
|
|
691
|
+
"artificial_analysis_coding_index": 34.7,
|
|
692
|
+
"artificial_analysis_math_index": null,
|
|
693
|
+
"mmlu_pro": null,
|
|
694
|
+
"gpqa": 0.822,
|
|
695
|
+
"hle": 0.172,
|
|
696
|
+
"livecodebench": null,
|
|
697
|
+
"scicode": 0.434,
|
|
698
|
+
"math_500": null,
|
|
699
|
+
"aime": null,
|
|
700
|
+
"aime_25": null,
|
|
701
|
+
"ifbench": 0.772108843537415,
|
|
702
|
+
"lcr": 0.743333333333333,
|
|
703
|
+
"terminalbench_hard": 0.242424242424242,
|
|
704
|
+
"terminalbench_v2_1": 0.310861423220974,
|
|
705
|
+
"terminalbench_v4_0": 0.00505050505050505,
|
|
706
|
+
"tau2": 0.312865497076023,
|
|
707
|
+
"tau_banking": 0.0969072164948454
|
|
708
|
+
},
|
|
709
|
+
"median_output_tokens_per_second": 0,
|
|
710
|
+
"median_time_to_first_token_seconds": 0,
|
|
711
|
+
"aa_effort": null,
|
|
712
|
+
"effort_variants": {}
|
|
713
|
+
},
|
|
683
714
|
"gemini-3.1-pro": {
|
|
684
715
|
"aa_id": "bbd93ebe-80da-4594-bb19-61e69d0331df",
|
|
685
716
|
"aa_slug": "gemini-3-1-pro-preview",
|
|
@@ -771,6 +802,37 @@
|
|
|
771
802
|
}
|
|
772
803
|
}
|
|
773
804
|
},
|
|
805
|
+
"gemini-3.5-flash-lite": {
|
|
806
|
+
"aa_id": "093b9df2-ebee-4309-943f-5a7e88360adf",
|
|
807
|
+
"aa_slug": "gemini-3-5-flash-lite",
|
|
808
|
+
"aa_name": "Gemini 3.5 Flash-Lite",
|
|
809
|
+
"aa_creator": "Google",
|
|
810
|
+
"release_date": "2026-07-21",
|
|
811
|
+
"evaluations": {
|
|
812
|
+
"artificial_analysis_intelligence_index": 22.2,
|
|
813
|
+
"artificial_analysis_coding_index": 49.3,
|
|
814
|
+
"artificial_analysis_math_index": null,
|
|
815
|
+
"mmlu_pro": null,
|
|
816
|
+
"gpqa": 0.838,
|
|
817
|
+
"hle": 0.188,
|
|
818
|
+
"livecodebench": null,
|
|
819
|
+
"scicode": 0.413,
|
|
820
|
+
"math_500": null,
|
|
821
|
+
"aime": null,
|
|
822
|
+
"aime_25": null,
|
|
823
|
+
"ifbench": null,
|
|
824
|
+
"lcr": 0.76,
|
|
825
|
+
"terminalbench_hard": null,
|
|
826
|
+
"terminalbench_v2_1": 0.535580524344569,
|
|
827
|
+
"terminalbench_v4_0": 0.0101010101010101,
|
|
828
|
+
"tau2": null,
|
|
829
|
+
"tau_banking": 0.175257731958763
|
|
830
|
+
},
|
|
831
|
+
"median_output_tokens_per_second": 329.536,
|
|
832
|
+
"median_time_to_first_token_seconds": 7.289,
|
|
833
|
+
"aa_effort": null,
|
|
834
|
+
"effort_variants": {}
|
|
835
|
+
},
|
|
774
836
|
"gemini-3.6-flash": {
|
|
775
837
|
"aa_id": "78332c88-fe60-42c8-af9d-3617e44cf1f5",
|
|
776
838
|
"aa_slug": "gemini-3-6-flash",
|
|
@@ -890,8 +952,8 @@
|
|
|
890
952
|
"tau2": null,
|
|
891
953
|
"tau_banking": 0.449484536082474
|
|
892
954
|
},
|
|
893
|
-
"median_output_tokens_per_second":
|
|
894
|
-
"median_time_to_first_token_seconds":
|
|
955
|
+
"median_output_tokens_per_second": 149.651,
|
|
956
|
+
"median_time_to_first_token_seconds": 14.293,
|
|
895
957
|
"aa_effort": "high",
|
|
896
958
|
"effort_variants": {
|
|
897
959
|
"low": {
|
|
@@ -1047,8 +1109,8 @@
|
|
|
1047
1109
|
"tau2": null,
|
|
1048
1110
|
"tau_banking": 0.503092783505155
|
|
1049
1111
|
},
|
|
1050
|
-
"median_output_tokens_per_second": 75.
|
|
1051
|
-
"median_time_to_first_token_seconds":
|
|
1112
|
+
"median_output_tokens_per_second": 75.43,
|
|
1113
|
+
"median_time_to_first_token_seconds": 2.91,
|
|
1052
1114
|
"aa_effort": "max",
|
|
1053
1115
|
"effort_variants": {
|
|
1054
1116
|
"low": {
|
|
@@ -1061,7 +1123,7 @@
|
|
|
1061
1123
|
"lcr": 0.726666666666667,
|
|
1062
1124
|
"terminalbench_v4_0": 0.348484848484849
|
|
1063
1125
|
},
|
|
1064
|
-
"median_output_tokens_per_second":
|
|
1126
|
+
"median_output_tokens_per_second": 76.317
|
|
1065
1127
|
}
|
|
1066
1128
|
}
|
|
1067
1129
|
},
|
|
@@ -1092,7 +1154,7 @@
|
|
|
1092
1154
|
"tau_banking": 0.472164948453608
|
|
1093
1155
|
},
|
|
1094
1156
|
"median_output_tokens_per_second": 49.499,
|
|
1095
|
-
"median_time_to_first_token_seconds": 2.
|
|
1157
|
+
"median_time_to_first_token_seconds": 2.806,
|
|
1096
1158
|
"aa_effort": null,
|
|
1097
1159
|
"effort_variants": {}
|
|
1098
1160
|
},
|
|
@@ -1423,8 +1485,8 @@
|
|
|
1423
1485
|
"tau2": 0.859649122807018,
|
|
1424
1486
|
"tau_banking": null
|
|
1425
1487
|
},
|
|
1426
|
-
"median_output_tokens_per_second":
|
|
1427
|
-
"median_time_to_first_token_seconds": 34.
|
|
1488
|
+
"median_output_tokens_per_second": 89.201,
|
|
1489
|
+
"median_time_to_first_token_seconds": 34.635,
|
|
1428
1490
|
"aa_effort": "xhigh",
|
|
1429
1491
|
"effort_variants": {}
|
|
1430
1492
|
},
|
|
@@ -1922,7 +1984,7 @@
|
|
|
1922
1984
|
"tau2": 0.728070175438596,
|
|
1923
1985
|
"tau_banking": 0.255670103092783
|
|
1924
1986
|
},
|
|
1925
|
-
"median_output_tokens_per_second":
|
|
1987
|
+
"median_output_tokens_per_second": 85.176
|
|
1926
1988
|
},
|
|
1927
1989
|
"high": {
|
|
1928
1990
|
"aa_slug": "gpt-5-6-terra-high",
|
|
@@ -1941,7 +2003,7 @@
|
|
|
1941
2003
|
"tau2": 0.783625730994152,
|
|
1942
2004
|
"tau_banking": 0.28659793814433
|
|
1943
2005
|
},
|
|
1944
|
-
"median_output_tokens_per_second":
|
|
2006
|
+
"median_output_tokens_per_second": 84.537
|
|
1945
2007
|
},
|
|
1946
2008
|
"xhigh": {
|
|
1947
2009
|
"aa_slug": "gpt-5-6-terra-xhigh",
|
|
@@ -1960,7 +2022,7 @@
|
|
|
1960
2022
|
"tau2": 0.804093567251462,
|
|
1961
2023
|
"tau_banking": 0.296907216494845
|
|
1962
2024
|
},
|
|
1963
|
-
"median_output_tokens_per_second":
|
|
2025
|
+
"median_output_tokens_per_second": 83.869
|
|
1964
2026
|
}
|
|
1965
2027
|
}
|
|
1966
2028
|
},
|
|
@@ -1990,8 +2052,8 @@
|
|
|
1990
2052
|
"tau2": null,
|
|
1991
2053
|
"tau_banking": 0.414432989690722
|
|
1992
2054
|
},
|
|
1993
|
-
"median_output_tokens_per_second":
|
|
1994
|
-
"median_time_to_first_token_seconds":
|
|
2055
|
+
"median_output_tokens_per_second": 48.042,
|
|
2056
|
+
"median_time_to_first_token_seconds": 229.496,
|
|
1995
2057
|
"aa_effort": "max",
|
|
1996
2058
|
"effort_variants": {
|
|
1997
2059
|
"low": {
|
|
@@ -2056,7 +2118,7 @@
|
|
|
2056
2118
|
"terminalbench_v4_0": 0.595959595959596,
|
|
2057
2119
|
"tau_banking": 0.430927835051546
|
|
2058
2120
|
},
|
|
2059
|
-
"median_output_tokens_per_second":
|
|
2121
|
+
"median_output_tokens_per_second": 51.703
|
|
2060
2122
|
}
|
|
2061
2123
|
}
|
|
2062
2124
|
},
|
|
@@ -2086,8 +2148,8 @@
|
|
|
2086
2148
|
"tau2": null,
|
|
2087
2149
|
"tau_banking": null
|
|
2088
2150
|
},
|
|
2089
|
-
"median_output_tokens_per_second":
|
|
2090
|
-
"median_time_to_first_token_seconds":
|
|
2151
|
+
"median_output_tokens_per_second": 127.196,
|
|
2152
|
+
"median_time_to_first_token_seconds": 61.062,
|
|
2091
2153
|
"aa_effort": "max",
|
|
2092
2154
|
"effort_variants": {
|
|
2093
2155
|
"low": {
|
|
@@ -2124,7 +2186,7 @@
|
|
|
2124
2186
|
"lcr": 0.793333333333333,
|
|
2125
2187
|
"terminalbench_v4_0": 0.0454545454545455
|
|
2126
2188
|
},
|
|
2127
|
-
"median_output_tokens_per_second":
|
|
2189
|
+
"median_output_tokens_per_second": 118.37
|
|
2128
2190
|
},
|
|
2129
2191
|
"xhigh": {
|
|
2130
2192
|
"aa_slug": "gpt-6-luna-xhigh",
|
|
@@ -2136,7 +2198,7 @@
|
|
|
2136
2198
|
"lcr": 0.8,
|
|
2137
2199
|
"terminalbench_v4_0": 0.0808080808080808
|
|
2138
2200
|
},
|
|
2139
|
-
"median_output_tokens_per_second":
|
|
2201
|
+
"median_output_tokens_per_second": 123.455
|
|
2140
2202
|
}
|
|
2141
2203
|
}
|
|
2142
2204
|
},
|
|
@@ -2296,7 +2358,7 @@
|
|
|
2296
2358
|
"lcr": 0.796666666666667,
|
|
2297
2359
|
"terminalbench_v4_0": 0.54040404040404
|
|
2298
2360
|
},
|
|
2299
|
-
"median_output_tokens_per_second":
|
|
2361
|
+
"median_output_tokens_per_second": 54.387
|
|
2300
2362
|
}
|
|
2301
2363
|
}
|
|
2302
2364
|
},
|
|
@@ -2326,8 +2388,8 @@
|
|
|
2326
2388
|
"tau2": 0.657894736842105,
|
|
2327
2389
|
"tau_banking": 0.127835051546392
|
|
2328
2390
|
},
|
|
2329
|
-
"median_output_tokens_per_second":
|
|
2330
|
-
"median_time_to_first_token_seconds": 0.
|
|
2391
|
+
"median_output_tokens_per_second": 183.019,
|
|
2392
|
+
"median_time_to_first_token_seconds": 0.502,
|
|
2331
2393
|
"aa_effort": "high",
|
|
2332
2394
|
"effort_variants": {
|
|
2333
2395
|
"low": {
|
|
@@ -2349,7 +2411,7 @@
|
|
|
2349
2411
|
"tau2": 0.450292397660819,
|
|
2350
2412
|
"tau_banking": 0.0288659793814433
|
|
2351
2413
|
},
|
|
2352
|
-
"median_output_tokens_per_second":
|
|
2414
|
+
"median_output_tokens_per_second": 191.359
|
|
2353
2415
|
}
|
|
2354
2416
|
}
|
|
2355
2417
|
},
|
|
@@ -2379,8 +2441,8 @@
|
|
|
2379
2441
|
"tau2": 0.60233918128655,
|
|
2380
2442
|
"tau_banking": 0.0701030927835052
|
|
2381
2443
|
},
|
|
2382
|
-
"median_output_tokens_per_second":
|
|
2383
|
-
"median_time_to_first_token_seconds": 0.
|
|
2444
|
+
"median_output_tokens_per_second": 206.106,
|
|
2445
|
+
"median_time_to_first_token_seconds": 0.427,
|
|
2384
2446
|
"aa_effort": "high",
|
|
2385
2447
|
"effort_variants": {
|
|
2386
2448
|
"low": {
|
|
@@ -2399,7 +2461,7 @@
|
|
|
2399
2461
|
"terminalbench_hard": 0.0454545454545455,
|
|
2400
2462
|
"tau2": 0.502923976608187
|
|
2401
2463
|
},
|
|
2402
|
-
"median_output_tokens_per_second":
|
|
2464
|
+
"median_output_tokens_per_second": 251.145
|
|
2403
2465
|
}
|
|
2404
2466
|
}
|
|
2405
2467
|
},
|
|
@@ -2569,7 +2631,7 @@
|
|
|
2569
2631
|
"tau2": null,
|
|
2570
2632
|
"tau_banking": null
|
|
2571
2633
|
},
|
|
2572
|
-
"median_output_tokens_per_second":
|
|
2634
|
+
"median_output_tokens_per_second": 61.072,
|
|
2573
2635
|
"median_time_to_first_token_seconds": 7.717,
|
|
2574
2636
|
"aa_effort": "xhigh",
|
|
2575
2637
|
"effort_variants": {
|
|
@@ -2583,7 +2645,7 @@
|
|
|
2583
2645
|
"lcr": 0.8,
|
|
2584
2646
|
"terminalbench_v4_0": 0.161616161616162
|
|
2585
2647
|
},
|
|
2586
|
-
"median_output_tokens_per_second":
|
|
2648
|
+
"median_output_tokens_per_second": 61.798
|
|
2587
2649
|
},
|
|
2588
2650
|
"high": {
|
|
2589
2651
|
"aa_slug": "grok-4-7-high",
|
|
@@ -2595,7 +2657,7 @@
|
|
|
2595
2657
|
"lcr": 0.77,
|
|
2596
2658
|
"terminalbench_v4_0": 0.247474747474747
|
|
2597
2659
|
},
|
|
2598
|
-
"median_output_tokens_per_second": 65.
|
|
2660
|
+
"median_output_tokens_per_second": 65.045
|
|
2599
2661
|
}
|
|
2600
2662
|
}
|
|
2601
2663
|
},
|
|
@@ -2625,8 +2687,8 @@
|
|
|
2625
2687
|
"tau2": 0.900584795321637,
|
|
2626
2688
|
"tau_banking": 0.202061855670103
|
|
2627
2689
|
},
|
|
2628
|
-
"median_output_tokens_per_second":
|
|
2629
|
-
"median_time_to_first_token_seconds": 1.
|
|
2690
|
+
"median_output_tokens_per_second": 83.137,
|
|
2691
|
+
"median_time_to_first_token_seconds": 1.154,
|
|
2630
2692
|
"aa_effort": null,
|
|
2631
2693
|
"effort_variants": {}
|
|
2632
2694
|
},
|
|
@@ -2656,8 +2718,8 @@
|
|
|
2656
2718
|
"tau2": null,
|
|
2657
2719
|
"tau_banking": 0.45979381443299
|
|
2658
2720
|
},
|
|
2659
|
-
"median_output_tokens_per_second":
|
|
2660
|
-
"median_time_to_first_token_seconds": 2.
|
|
2721
|
+
"median_output_tokens_per_second": 42.869,
|
|
2722
|
+
"median_time_to_first_token_seconds": 2.916,
|
|
2661
2723
|
"aa_effort": "max",
|
|
2662
2724
|
"effort_variants": {
|
|
2663
2725
|
"low": {
|
|
@@ -2704,8 +2766,8 @@
|
|
|
2704
2766
|
"tau2": 0.245614035087719,
|
|
2705
2767
|
"tau_banking": 0.0577319587628866
|
|
2706
2768
|
},
|
|
2707
|
-
"median_output_tokens_per_second": 77.
|
|
2708
|
-
"median_time_to_first_token_seconds": 0.
|
|
2769
|
+
"median_output_tokens_per_second": 77.616,
|
|
2770
|
+
"median_time_to_first_token_seconds": 0.692,
|
|
2709
2771
|
"aa_effort": null,
|
|
2710
2772
|
"effort_variants": {}
|
|
2711
2773
|
},
|
|
@@ -2766,8 +2828,8 @@
|
|
|
2766
2828
|
"tau2": 0.412280701754386,
|
|
2767
2829
|
"tau_banking": 0.0494845360824742
|
|
2768
2830
|
},
|
|
2769
|
-
"median_output_tokens_per_second": 163.
|
|
2770
|
-
"median_time_to_first_token_seconds": 0.
|
|
2831
|
+
"median_output_tokens_per_second": 163.75,
|
|
2832
|
+
"median_time_to_first_token_seconds": 0.555,
|
|
2771
2833
|
"aa_effort": null,
|
|
2772
2834
|
"effort_variants": {}
|
|
2773
2835
|
},
|
|
@@ -2815,7 +2877,7 @@
|
|
|
2815
2877
|
"terminalbench_v4_0": 0.166666666666667,
|
|
2816
2878
|
"tau_banking": 0.472164948453608
|
|
2817
2879
|
},
|
|
2818
|
-
"median_output_tokens_per_second":
|
|
2880
|
+
"median_output_tokens_per_second": 115.767
|
|
2819
2881
|
}
|
|
2820
2882
|
}
|
|
2821
2883
|
},
|