Sync model card
Browse files- MODEL_CARD.md +1 -1
MODEL_CARD.md
CHANGED
|
@@ -117,7 +117,7 @@ The Typed Decisions result is the full 2,000-decision test split. The
|
|
| 117 |
DecisionBench result is the 1,565-row matched subset used for every model in the
|
| 118 |
table: ≤16 candidates and ≤2,048-token prompts, not the full 23,900-row suite.
|
| 119 |
Bosun, Pluto-2, d1-2B, and d1-3B were all run locally on the same rows and
|
| 120 |
-
scored with the same code. Raw summaries are in
|
| 121 |
|
| 122 |
---
|
| 123 |
|
|
|
|
| 117 |
DecisionBench result is the 1,565-row matched subset used for every model in the
|
| 118 |
table: ≤16 candidates and ≤2,048-token prompts, not the full 23,900-row suite.
|
| 119 |
Bosun, Pluto-2, d1-2B, and d1-3B were all run locally on the same rows and
|
| 120 |
+
scored with the same code. Raw summaries are in benchmarks/. The full DecisionBench suite is not claimed.
|
| 121 |
|
| 122 |
---
|
| 123 |
|