Update evaluation: official Qwen3-Reranker and KaLM-Reranker-V1-Large-R2 added, seq-cls variants and ettin removed

README.md

@@ -119,21 +119,22 @@ Evaluation was conducted using the [reranker-simple-benchmark](https://github.co
 
 <img src="./assets/pps_vs_ndcg9.png" width="700" alt="Reranking performance (mean nDCG@10) vs. throughput (mean PPS)">
 
-The figure plots mean nDCG@10 against mean PPS across the nine Korean benchmarks, including MLDR. Dot color marks model size. PPS uses each model's own input limit and its best measured batch size, so it measures neither speed at equal token lengths nor end-to-end retrieval latency.
+The figure plots mean nDCG@10 against mean PPS across the nine Korean benchmarks, including MLDR. Dot color marks model size. PPS uses each model's own input limit and its best measured batch size, so it measures neither speed at equal token lengths nor end-to-end retrieval latency. The x-axis is a non-uniform log scale that stretches 20–26 and compresses 26–50 pairs/s so that nearby points stay readable.
 
 ### Results — MTEB-ko-retrieval (9 subsets)
 <!-- **공식 9개 subset 을 모두 평가한 모델**의 9-subset mean NDCG@10, PPS -->
 | Model | Params | Mean NDCG@10 | Mean PPS |
 |---|---|---|---|
-| tomaarsen/Qwen3-Reranker-8B-seq-cls | 7.6B | 0.9004 | 15.1 |
-| tomaarsen/Qwen3-Reranker-4B-seq-cls | 4.0B | 0.8956 | 24.3 |
+| Qwen/Qwen3-Reranker-8B | 8.2B | 0.9030 | 15.2 |
+| KaLM-Embedding/KaLM-Reranker-V1-Large-R2 | 7.5B | 0.8960 | 25.3 |
+| Qwen/Qwen3-Reranker-4B | 4.0B | 0.8957 | 24.3 |
 | **nlpai-lab/KURE-Reranker-base** | 1.7B | 0.8849 | 55.1 |
 | **nlpai-lab/KURE-Reranker-nano** | 149M | 0.8808 | 473.7 |
 | zeroentropy/zerank-2-reranker | 4.0B | 0.8695 | 29.4 |
 | lightonai/LightOn-rerank-PW-4B | 4.5B | 0.8664 | 15.0 |
 | mixedbread-ai/mxbai-rerank-large-v2 | 1.5B | 0.8661 | 65.2 |
 | BAAI/bge-reranker-v2-m3 | 568M | 0.8586 | 404.1 |
-| tomaarsen/Qwen3-Reranker-0.6B-seq-cls | 596M | 0.8585 | 99.6 |
+| Qwen/Qwen3-Reranker-0.6B | 596M | 0.8577 | 100.2 |
 | nvidia/llama-nemotron-rerank-1b-v2 | 1.2B | 0.8522 | 127.3 |
 | nlpai-lab/LAMAR-600m | 568M | 0.8406 | 408.8 |
 | dragonkue/bge-reranker-v2-m3-ko | 568M | 0.8263 | 401.5 |
@@ -141,9 +142,8 @@ The figure plots mean nDCG@10 against mean PPS across the nine Korean benchmarks
 | upskyy/ko-reranker-8k | 568M | 0.8085 | 404.0 |
 | Dongjin-kr/ko-reranker | 560M | 0.7950 | 482.8 |
 | telepix/PIXIE-Spell-Reranker-Preview-0.6B | 596M | 0.7806 | 99.6 |
-| cross-encoder/ettin-reranker-1b-v1 | 1.0B | 0.6901 | 49.7 |
 
-PPS is measured on a single NVIDIA RTX A6000 48GB per model and averaged over the nine benchmarks. Inputs are length-sorted and dynamically padded within each batch.
+PPS is measured on a single NVIDIA RTX A6000 48GB per model and averaged over the nine benchmarks. For each benchmark, every model is timed on the same ~550 sampled query–document pairs (whole queries, fixed seed). Inputs are length-sorted and dynamically padded within each batch. Models run in bf16 with flash_attention_2, except `KaLM-Embedding/KaLM-Reranker-V1-Large-R2`, which uses sdpa because transformers does not support flash_attention_2 for T5Gemma2.
 
 `jinaai/jina-reranker-v3` and `jinaai/jina-reranker-v3.5` are listwise rerankers that cannot be compared under the same 8,192-token condition on MLDR, so they are excluded from the 9-subset table and their MLDR cells are left blank below.
 
@@ -151,8 +151,9 @@ PPS is measured on a single NVIDIA RTX A6000 48GB per model and averaged over th
 
 | Model | Params | Ko-StrategyQA | AutoRAGRetrieval | PublicHealthQA | BelebeleRetrieval | MIRACLRetrieval | MrTidyRetrieval | MultiLongDocRetrieval | SQuADKorV1Retrieval | LawIRKo |
 |---|---|---|---|---|---|---|---|---|---|---|
-| tomaarsen/Qwen3-Reranker-8B-seq-cls | 7.6B | 0.8679 | 0.9546 | 0.8893 | 0.9907 | 0.8490 | 0.8409 | 0.8220 | 0.9880 | 0.9014 |
-| tomaarsen/Qwen3-Reranker-4B-seq-cls | 4.0B | 0.8733 | 0.9707 | 0.8685 | 0.9906 | 0.8533 | 0.8321 | 0.8105 | 0.9861 | 0.8752 |
+| Qwen/Qwen3-Reranker-8B | 8.2B | 0.8720 | 0.9653 | 0.8899 | 0.9908 | 0.8513 | 0.8416 | 0.8255 | 0.9897 | 0.9013 |
+| KaLM-Embedding/KaLM-Reranker-V1-Large-R2 | 7.5B | 0.8796 | 0.9415 | 0.8956 | 0.9936 | 0.8382 | 0.8500 | 0.7970 | 0.9863 | 0.8824 |
+| Qwen/Qwen3-Reranker-4B | 4.0B | 0.8733 | 0.9630 | 0.8702 | 0.9904 | 0.8559 | 0.8298 | 0.8161 | 0.9861 | 0.8766 |
 | **nlpai-lab/KURE-Reranker-base** | 1.7B | 0.8548 | 0.9762 | 0.8716 | 0.9880 | 0.8371 | 0.7970 | 0.8163 | 0.9891 | 0.8343 |
 | **nlpai-lab/KURE-Reranker-nano** | 149M | 0.8582 | 0.9741 | 0.8475 | 0.9830 | 0.8400 | 0.8011 | 0.7966 | 0.9895 | 0.8368 |
 | jinaai/jina-reranker-v3.5 | 597M | 0.8539 | 0.9838 | 0.8094 | 0.9733 | 0.8565 | 0.8194 | — | 0.9887 | 0.8545 |
@@ -161,7 +162,7 @@ PPS is measured on a single NVIDIA RTX A6000 48GB per model and averaged over th
 | lightonai/LightOn-rerank-PW-4B | 4.5B | 0.8567 | 0.9321 | 0.8693 | 0.9882 | 0.8072 | 0.8091 | 0.7609 | 0.9803 | 0.7938 |
 | mixedbread-ai/mxbai-rerank-large-v2 | 1.5B | 0.8563 | 0.9531 | 0.8772 | 0.9778 | 0.7939 | 0.8771 | 0.6787 | 0.9681 | 0.8130 |
 | BAAI/bge-reranker-v2-m3 | 568M | 0.8487 | 0.9663 | 0.8475 | 0.9853 | 0.8129 | 0.8222 | 0.6690 | 0.9853 | 0.7906 |
-| tomaarsen/Qwen3-Reranker-0.6B-seq-cls | 596M | 0.8336 | 0.9308 | 0.8489 | 0.9779 | 0.8507 | 0.7359 | 0.7813 | 0.9808 | 0.7867 |
+| Qwen/Qwen3-Reranker-0.6B | 596M | 0.8336 | 0.9321 | 0.8477 | 0.9779 | 0.8470 | 0.7325 | 0.7819 | 0.9804 | 0.7865 |
 | nvidia/llama-nemotron-rerank-1b-v2 | 1.2B | 0.8536 | 0.9480 | 0.8491 | 0.9883 | 0.8182 | 0.8026 | 0.6719 | 0.9858 | 0.7527 |
 | nlpai-lab/LAMAR-600m | 568M | 0.8461 | 0.9591 | 0.8225 | 0.9835 | 0.8214 | 0.7975 | 0.5679 | 0.9850 | 0.7822 |
 | dragonkue/bge-reranker-v2-m3-ko | 568M | 0.8232 | 0.9684 | 0.8708 | 0.9769 | 0.7573 | 0.6776 | 0.7061 | 0.9846 | 0.6721 |
@@ -169,14 +170,14 @@ PPS is measured on a single NVIDIA RTX A6000 48GB per model and averaged over th
 | upskyy/ko-reranker-8k | 568M | 0.8143 | 0.9230 | 0.8388 | 0.9291 | 0.7249 | 0.6998 | 0.5975 | 0.9718 | 0.7770 |
 | Dongjin-kr/ko-reranker | 560M | 0.8468 | 0.9014 | 0.7675 | 0.9759 | 0.8017 | 0.7772 | 0.3721 | 0.9785 | 0.7343 |
 | telepix/PIXIE-Spell-Reranker-Preview-0.6B | 596M | 0.8329 | 0.9794 | 0.8534 | 0.9777 | 0.8449 | 0.7650 | 0.1829 | 0.9850 | 0.6042 |
-| cross-encoder/ettin-reranker-1b-v1 | 1.0B | 0.6624 | 0.8901 | 0.7461 | 0.6914 | 0.7004 | 0.6659 | 0.3651 | 0.9590 | 0.5306 |
 
 ### Per-dataset PPS
 
 | Model | Params | Ko-StrategyQA | AutoRAGRetrieval | PublicHealthQA | BelebeleRetrieval | MIRACLRetrieval | MrTidyRetrieval | MultiLongDocRetrieval | SQuADKorV1Retrieval | LawIRKo |
 |---|---|---|---|---|---|---|---|---|---|---|
-| tomaarsen/Qwen3-Reranker-8B-seq-cls | 7.6B | 16.6 | 7.3 | 17.5 | 19.4 | 24.9 | 26.5 | 0.7 | 10.6 | 12.3 |
-| tomaarsen/Qwen3-Reranker-4B-seq-cls | 4.0B | 26.1 | 11.8 | 28.4 | 31.5 | 40.0 | 42.4 | 1.1 | 17.2 | 20.0 |
+| Qwen/Qwen3-Reranker-8B | 8.2B | 16.5 | 7.4 | 17.6 | 19.4 | 25.0 | 26.6 | 0.7 | 10.8 | 12.4 |
+| KaLM-Embedding/KaLM-Reranker-V1-Large-R2 | 7.5B | 28.6 | 12.4 | 28.5 | 33.7 | 39.6 | 43.8 | 0.8 | 18.7 | 21.4 |
+| Qwen/Qwen3-Reranker-4B | 4.0B | 26.2 | 11.8 | 28.2 | 31.1 | 40.1 | 42.8 | 1.1 | 17.1 | 19.9 |
 | **nlpai-lab/KURE-Reranker-base** | 1.7B | 59.2 | 27.3 | 64.6 | 71.1 | 89.1 | 97.1 | 2.6 | 39.1 | 45.7 |
 | **nlpai-lab/KURE-Reranker-nano** | 149M | 475.4 | 233.2 | 569.7 | 630.9 | 765.8 | 855.2 | 16.5 | 330.8 | 386.0 |
 | jinaai/jina-reranker-v3.5 | 597M | 141.0 | 38.6 | 148.6 | 174.6 | 277.3 | 295.7 | — | 68.4 | 86.7 |
@@ -185,7 +186,7 @@ PPS is measured on a single NVIDIA RTX A6000 48GB per model and averaged over th
 | lightonai/LightOn-rerank-PW-4B | 4.5B | 16.2 | 7.3 | 18.6 | 19.5 | 23.4 | 26.1 | 0.7 | 10.7 | 12.4 |
 | mixedbread-ai/mxbai-rerank-large-v2 | 1.5B | 70.0 | 32.9 | 76.8 | 84.1 | 104.2 | 113.6 | 3.2 | 47.0 | 54.7 |
 | BAAI/bge-reranker-v2-m3 | 568M | 420.7 | 195.6 | 471.3 | 545.3 | 653.2 | 724.8 | 9.3 | 271.6 | 345.5 |
-| tomaarsen/Qwen3-Reranker-0.6B-seq-cls | 596M | 107.1 | 49.6 | 118.0 | 129.3 | 159.5 | 173.9 | 4.2 | 71.8 | 82.9 |
+| Qwen/Qwen3-Reranker-0.6B | 596M | 105.9 | 49.4 | 117.9 | 130.3 | 162.6 | 177.4 | 4.3 | 70.8 | 83.6 |
 | nvidia/llama-nemotron-rerank-1b-v2 | 1.2B | 133.7 | 54.4 | 146.9 | 163.0 | 220.0 | 243.1 | 3.9 | 84.9 | 95.9 |
 | nlpai-lab/LAMAR-600m | 568M | 418.0 | 196.5 | 480.5 | 557.2 | 656.7 | 742.5 | 9.2 | 275.0 | 343.8 |
 | dragonkue/bge-reranker-v2-m3-ko | 568M | 416.9 | 195.1 | 467.2 | 540.7 | 653.4 | 716.7 | 9.2 | 271.9 | 342.7 |
@@ -193,7 +194,6 @@ PPS is measured on a single NVIDIA RTX A6000 48GB per model and averaged over th
 | upskyy/ko-reranker-8k | 568M | 411.8 | 195.6 | 474.3 | 551.4 | 649.3 | 726.0 | 9.2 | 275.1 | 342.8 |
 | Dongjin-kr/ko-reranker | 560M | 520.8 | 258.0 | 510.1 | 554.8 | 747.6 | 765.2 | 272.7 | 334.4 | 381.2 |
 | telepix/PIXIE-Spell-Reranker-Preview-0.6B | 596M | 104.6 | 49.4 | 117.8 | 129.8 | 160.5 | 175.6 | 4.3 | 72.1 | 82.6 |
-| cross-encoder/ettin-reranker-1b-v1 | 1.0B | 52.4 | 19.9 | 51.4 | 65.6 | 92.7 | 97.2 | 3.8 | 31.2 | 33.4 |
 
 Batch size starts at 8 and doubles until an out-of-memory error. Samples are repeated to fill complete batches. After warmup, three full passes are timed with CUDA events. Throughput is the total number of processed pairs divided by the accumulated GPU forward time. The highest-throughput successful batch is reported. Tokenization, data loading, and CPU preprocessing are excluded. The batch-search approach is informed by the [Ettin reranker speed benchmark](https://huggingface.co/blog/ettin-reranker#speed).