Update README.md

README.md

@@ -54,15 +54,16 @@ Nearly every setting above matches v1 on purpose. The point of v2 was to isolate
 
 ## Benchmarks
 
-Benchmarks were run with a custom harness this time. We won't put İvme-Conversate-v2 to leaderboards for now until we verify our benchmark produces real results.
+Benchmarks were run with lm-evaluation-harness via a custom model adapter (previous numbers from an internal script have been superseded by these).
 
 | Benchmark | v1 | v2 |
 |---|---|---|
-| WikiText-2 (byte perplexity) ↓ | 2.96 | **2.50** |
-| BLiMP (macro-average) ↑ | 61.40% | **73.19%** |
-| ARC-Easy ↑ | 30.85% | **43.14%** |
+| WikiText-2 (byte perplexity) ↓ | 2.96 | **2.2250** |
+| BLiMP (macro-average, 68 paradigms) ↑ | 61.40% | **75.09%** |
+| ARC-Easy (acc_norm) ↑ | 30.85% | **39.98%** |
+| ARC-Easy (acc) ↑ | — | **43.56%** |
 
-Every metric improved, and the ARC-Easy jump in particular is bigger than you would expect from data and training changes alone at this parameter count.
+Every metric improved. The ARC-Easy acc_norm gain (30.85% → 39.98%) is more modest than the raw acc numbers alone suggest, but still a real improvement over v1.
 
 ### BLiMP paradigm breakdown
 
@@ -70,22 +71,22 @@ Strong on core agreement paradigms:
 
 | Paradigm | Accuracy |
 |---|---|
-| existential_there_quantifiers_1 | 99.10% |
-| anaphor_number_agreement | 98.30% |
-| sentential_negation_npi_licensor_present | 98.10% |
-| determiner_noun_agreement_1 | 96.60% |
-| determiner_noun_agreement_2 | 95.40% |
-| anaphor_gender_agreement | 90.70% |
+| blimp_principle_A_case_1 | 100.00% |
+| blimp_existential_there_quantifiers_1 | 99.40% |
+| blimp_anaphor_number_agreement | 98.00% |
+| blimp_sentential_negation_npi_licensor_present | 97.30% |
+| blimp_determiner_noun_agreement_1 | 96.90% |
+| blimp_principle_A_domain_1 | 95.40% |
 
 Weaker on long-distance dependencies and island constraints, a known hard case for small models:
 
 | Paradigm | Accuracy |
 |---|---|
-| existential_there_quantifiers_2 | 18.90% |
-| left_branch_island_echo_question | 27.80% |
-| sentential_subject_island | 33.80% |
-| only_npi_scope | 42.60% |
-| complex_NP_island | 50.30% |
+| blimp_wh_vs_that_with_gap_long_distance | 17.20% |
+| blimp_existential_there_quantifiers_2 | 30.20% |
+| blimp_left_branch_island_echo_question | 31.40% |
+| blimp_superlative_quantifiers_2 | 33.20% |
+| blimp_principle_A_reconstruction | 36.10% |
 
 This pattern, strong local agreement paired with weaker long-distance syntax, is typical for models at this scale.