Ko-LongBench (LG)
K-EXAONE 2.0 89.6% leads since July 2026 Models answer questions over long Korean contexts. Tasks cover document QA, story and dialogue history understanding, in-context learning, structured QA and RAG.
LG AI Research built it in house and first described it in the EXAONE 4.0 technical report.
- Made by
- LG AI Research
- Released
- July 2025
- Kind
- Reasoning over long documents
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- Kept private
- Last in a launch post
- July 2026, dropped after it saturated
- Last model added
- August 2026
K-EXAONE 2.0 leads with 89.6% among models released by July 2026
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in July 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 K-EXAONE 2.0 89.6%
- 2 K-EXAONE 86.8%
- 3 EXAONE 4.0 32B 76.9%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | K-EXAONE 2.0 | 89.6% | Jul 2026 | Lab model card | |
| 2 | K-EXAONE | 86.8% | Dec 2025 | Lab model card | |
| 3 | EXAONE 4.0 32B | 76.9% | Jul 2025 | Lab model card |
3 models have held number one in labs’ own numbers since its release in July 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
LG AI Research’s own number for K-EXAONE passed 85% in December 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs headline it less often now, last in July 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Jul 31, 2026 | K-EXAONE 2.0 | 89.6 | Ko-LongBench (in-house) |
| Dec 31, 2025 | K-EXAONE | 86.8 | Ko-LongBench |
| Jul 15, 2025 | EXAONE 4.0 32B | 76.9 | Ko-LongBench (non-reasoning) |
3 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Aug 5, 2026 | K-EXAONE 2.0 technical report | 89.6 | Ko-LongBench (in-house) (Table 6, Reasoning mode) | Capabilities |
| Jan 5, 2026 | K-EXAONE technical report | 86.8 | Ko-LongBench (in-house) (Table 3, Reasoning mode). Non-reasoning 85.4 (Table 4) | Capabilities |
| Jul 15, 2025 | EXAONE 4.0 32B technical report | 76.9 | Ko-LongBench (KO), in-house, Non-reasoning only (Table 4) | Capabilities |
More in Long context
- MRCR v2 In use Multi-round coreference: retrieve the n-th of several similar requests hidden in a long synthetic conversation, up to 1M tokens.
Muse Spark 1.3 98.5% - LongBench v2 In use 503 multiple-choice questions over 8K-2M-word contexts (QA, dialogue, code repos, structured data). Accuracy.
Inkling 2 Small 70.6% - GraphWalks In use A graph is given as an edge list in long context. The model answers BFS or parent queries, scored by F1. Claude Fable 5 99.96%
- OpenAI MRCR v2 In use Models read a long synthetic chat that hides 2, 4 or 8 identical writing requests and must reproduce the response to the i-th one. Scored by mean string match ratio per context bin. Gemini 3.7 Flash 89%
- CL-bench In use Model must learn new knowledge from a supplied long context (rules, procedures, data) and solve tasks. Strict LLM-verified rubrics. GPT-5.4 27.9%
- AA-LCR 1.1 In use Models answer 100 questions that need reasoning across sets of real documents of about 100K tokens. An LLM equality checker with a fixed system prompt compares each answer with the key.
Step 5 Preview 88.3%