Ko-LongBench (LG)
K-EXAONE 2.0 89.6% leads since Jul 2026 Fading 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.
- Level
- University Undergraduates and entry-level professionals
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Short answer A number, word or short string matched to a key.
K-EXAONE 2.0 leads with 89.6% among models released by Jul 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 Jul 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 K-EXAONE 2.0 89.6%
- 2 K-EXAONE 86.8%
- 3 EXAONE 4.0 32B 76.9%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | K-EXAONE 2.0 | 89.6% | Jul 2026 | Model card | |
| 2 | K-EXAONE | 86.8% | Dec 2025 | Model card | |
| 3 | EXAONE 4.0 32B | 76.9% | Jul 2025 | Model card |
3 models have held number one since its release in Jul 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
The best score passed 85% in Dec 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs headline it less often now, last in Jul 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 |
|---|---|---|---|
| 31 Jul 2026 | K-EXAONE 2.0 | 89.6 | Ko-LongBench (in-house) |
| 31 Dec 2025 | K-EXAONE | 86.8 | Ko-LongBench |
| 15 Jul 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 |
|---|---|---|---|---|
| 5 Aug 2026 | K-EXAONE 2.0 technical report | 89.6 | Ko-LongBench (in-house) (Table 6, Reasoning mode) | Capabilities |
| 5 Jan 2026 | K-EXAONE technical report | 86.8 | Ko-LongBench (in-house) (Table 3, Reasoning mode). Non-reasoning 85.4 (Table 4) | Capabilities |
| 15 Jul 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. Beam 1.0 66.9%
- 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 5 100%
- 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. K-EXAONE 2.0 94.4%
- 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%