mzwin9870 commited on
Commit
4e2ac00
·
verified ·
1 Parent(s): 2b8d01d

exam-v1 Claude/Grok 26/76 Codex 19/76 Trace 74/76

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -128,10 +128,12 @@ Same 76 files. Same grader. Frontier seats are naked JSON. Trace is the product
128
  | Qwen 2.5 7B | 0.00 (0/76) | 0.12 | 0.00 |
129
  | Qwen + dated RAG | 0.16 (12/76) | 0.04 | 0.70 |
130
  | Qwen + RAG + tools | 0.20 (15/76) | 0.03 | 0.71 |
 
131
  | Codex | 0.25 (19/76) | 0 | 0.89 |
 
132
  | **Trace** | **0.97 (74/76)** | **0** | **1.00** |
133
 
134
- Codex occupancy 8/8; pass family 0/20 (labels `needs_facts`, not a false kill). Trace affiliation 6/8; every other family 8/8 or 20/20. Claude and Grok exam still running. `verified: false`.
135
 
136
  ## Quickstart
137
 
 
128
  | Qwen 2.5 7B | 0.00 (0/76) | 0.12 | 0.00 |
129
  | Qwen + dated RAG | 0.16 (12/76) | 0.04 | 0.70 |
130
  | Qwen + RAG + tools | 0.20 (15/76) | 0.03 | 0.71 |
131
+ | Claude | 0.34 (26/76) | 0.05 | 0.66 |
132
  | Codex | 0.25 (19/76) | 0 | 0.89 |
133
+ | Grok | 0.34 (26/76) | 0.09 | 1.00 |
134
  | **Trace** | **0.97 (74/76)** | **0** | **1.00** |
135
 
136
+ Codex occupancy 8/8; pass family 0/20. Grok size 7/8; occupancy 0/8. Claude SOP 8.1 leak on 26 files. Trace affiliation 6/8; every other family 8/8 or 20/20. No frontier clears v0 0.85. `verified: false`.
137
 
138
  ## Quickstart
139