add solar open technical report. add benchmark results.

.gitattributes

@@ -17,6 +17,7 @@
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
+*.pdf filter=lfs diff=lfs merge=lfs -text
 *.pickle filter=lfs diff=lfs merge=lfs -text
 *.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -28,7 +28,7 @@ tags:
 ## Model Overview
 
 * **Model Name:** Solar Open 100B
-* **Hugging Face ID:** Upstage/Solar-Open-100B
+* **Hugging Face ID:** `Upstage/Solar-Open-100B`
 * **Architecture:** Mixture-of-Experts (MoE)
     * **Total Parameters:** 102.6B
     * **Active Parameters:** 12B (per token)
@@ -36,10 +36,12 @@ tags:
 * **Pre-training Tokens:** 19.7 Trillion
 * **Context Length:** 128k
 * **Training Hardware:** NVIDIA B200 GPUs
-* **License:** **Solar-Apache License 2.0** (See [LICENSE](./LICENSE))
+* **License:** **Solar-Apache License 2.0** (See [LICENSE](#license))
 * **Hardware Requirements:**
     * **Minimum:** 4x NVIDIA A100 (80GB)
 
+For more details, please refer to [Solar Open Technical Report](solar-open-technical-report.pdf).
+
 ## License
 This repository contains both model weights and code,
 which are licensed under different terms:
@@ -54,7 +56,46 @@ which are licensed under different terms:
 
 ## Performance
 
-TBA
+### Korean Benchmarks
+
+| Category | Benchmarks | Model Name (102B) | gpt-oss-120b (117B, high) | gpt-oss-120b (117B, medium) | GLM-4.5-Air (110B) |
+| :--- | :--- | :---: | :---: | :---: | :---: |
+| **General** | KMMLU | 73.0 | 72.7 | 70.3 | 70.2 |
+| | KMMLU-Pro | 64.0 | 62.6 | 60.5 | 60.7 |
+| | CLIcK | 78.9 | 77.2 | 72.9 | 48.3 |
+| | HAE-RAE v1.1 | 73.3 | 70.8 | 69.6 | 42.6 |
+| | KoBALT | 44.3 | 52.6 | 45.0 | 40.3 |
+| **Finance** | KBankMMLU (in-house) | 65.5 | 62.5 | 61.5 | 64.7 |
+| **Law** | KBL | 65.5 | 62.8 | 60.1 | 60.6 |
+| **Medical** | KorMedMCQA | 84.4 | 75.8 | 76.3 | 80.5 |
+| **Math** | Ko-AIME 2024 (in-house) | 80.3 | 90.0 | 76.7 | 80.0 |
+| | Ko-AIME 2025 (in-house) | 80.0 | 90.0 | 70.0 | 83.3 |
+| | HRM8K | 87.6 | 89.5 | 84.8 | 86.0 |
+| **IF** | Ko-IFEval | 87.5 | 93.2 | 86.7 | 79.5 |
+| **Preference** | Ko Arena Hard v2 (in-house) | 79.9 | 79.5 | 73.8 | 60.4 |
+
+
+### English Benchmarks
+
+| Category | Benchmarks | Model Name (102B) | gpt-oss-120b (117B, high) | gpt-oss-120b (117B, medium) | GLM-4.5-Air (110B) |
+| :--- | :--- | :---: | :---: | :---: | :---: |
+| **General** | MMLU | 88.2 | 88.6 | 87.9 | 83.3 |
+| | MMLU-Pro | 80.4 | 80.4 | 78.6 | 81.4 |
+| | GPQA-Diamond | 68.1 | 78.0 | 69.4 | 75.8 |
+| | HLE (text only) | 10.5 | 18.4 | 7.23 | 10.8 |
+| **Math** | AIME 2024 | 91.7 | 94.3 | 77.7 | 88.7 |
+| | AIME 2025 | 84.3 | 91.7 | 75.0 | 82.7 |
+| | HMMT 2025 (Feb) | 73.3 | 80.0 | 63.3 | 66.7 |
+| | HMMT 2025 (Nov) | 80.0 | 73.3 | 66.7 | 70.0 |
+| **Code** | LiveCodeBench (v1–v6 cumul) | 74.2 | 89.9 | 82.8 | 71.9 |
+| **IF** | IFBench | 53.7 | 70.8 | 61.2 | 37.8 |
+| | IFEval | 88.0 | 91.4 | 86.5 | 86.5 |
+| **Preference** | Arena Hard v2 | 74.8 | 79.6 | 72.7 | 62.5 |
+| | Writing Bench | 7.51 | 6.61 | 6.55 | 7.40 |
+| **Agent** | Tau² Airline | 52.4 | 56.0 | 52.8 | 60.8 |
+| | Tau² Telecom | 55.6 | 57.7 | 47.4 | 28.1 |
+| | Tau² Retail | 59.3 | 76.5 | 68.4 | 71.9 |
+| **Long** | AA-LCR | 35.0 | 48.3 | 45.0 | 37.3 |
 
 ## Inference Quickstart
 

solar-open-technical-report.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d6664d644f12a4eff2deaa1d061e377aa11fce81e679c2837a8bfdecf509cd
+size 366668