K-EXAONE 2.0
As of 16 Nov 2026, K-EXAONE 2.0 by LG AI Research scores 42.4 on the BenchLeader Index (608 ranked configurations), with its best results in long context (54) and weakest in coding (29). Released 12 Aug 2026.
Key facts (as of 16 Nov 2026)
- K-EXAONE 2.0 was released on 12 Aug 2026 (LG AI Research).
In detail. K-EXAONE 2.0 is a LG AI Research open-weights reasoning model, released 12 Aug 2026. Its best configuration ranks #494 of 608 on the BenchLeader Index at 42.4 ±6.8, in the lower half. The ± is the point: 234 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in long context (54) and lowest in coding (29). Last measured 12 Aug 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 262k
- via Artificial Analysis
- Cost per task
- –
- Tokens per task
- 55k
- 41% of it reasoning
- Released
- 12 Aug 2026
- Overall index42
- Reasoning32
- Coding29
- Agents & tools39
- Knowledge39
- Long context54
Embed this rank
More badge styles[](https://www.benchleader.com/models/k-exaone-2-0)Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.
Versions
LG AI Research has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| K-EXAONE 2.0this page | 12 Aug 2026 | 42.4 | #494 |
| K-EXAONEno reasoning | 31 Dec 2025 | – | – |
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Metadata
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Openness Indexnot in index | 44.4#97 | Artificial Analysis |
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 82.9%#166 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 18.6%#246 | Artificial Analysis | |
| HLE-Diamond (AA) | 5.7%#142 | Artificial Analysis | |
| CritPtnot in index | 0.9%#256 | Artificial Analysis | |
| CritPt v2 hard subset (AA) | 4.0%#116 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode (AA)not in index | 42.0%#180 | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#186 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 40.5%#141 | Artificial Analysis | |
| FrontierCode 2.0 (AA) | 0.8%#121 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GDPval-AA v2.1, normalised scorenot in index | 15.4%#104 | Artificial Analysis | |
| GDPval-AA v2.1not in index | 816#208 | Artificial Analysis | |
| τ³-Banking (AA) | 11.6%#141 | Artificial Analysis | |
| AutomationBenchnot in index | 3.9%#205 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 4.2%#203 | Artificial Analysis | |
| AA-Briefcase v1.1not in index | 651#207 | Artificial Analysis | |
| Terminal-Bench-Science 0.1 (AA)not in index | 0.0%#115 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience v1.1 | -11.5#110 | Artificial Analysis | |
| AA-Omniscience v1.1: accuracynot in index | 14.5%#135 | Artificial Analysis | |
| AA-Omniscience v1.1: non-hallucinationnot in index | 69.6%#37 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR v1.1 | 60.0%#301 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v5.0.1not in index | 7.6#116 | Artificial Analysis | |
| AA Intelligence Index v4.3.2not in index | 19.7#248 | Artificial Analysis | |
| AA Progress Index v1not in index | 253.3#256 | Artificial Analysis |
More from LG AI Research
See also
Embed or cite
Show where K-EXAONE 2.0 ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.
[](https://www.benchleader.com/models/k-exaone-2-0)Cite this
The ranking changes daily, so a reference carries the data date. APA style:
BenchLeader. (2026, November 16). K-EXAONE 2.0 on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 16, 2026, from https://www.benchleader.com/models/k-exaone-2-0
BibTeX:
@misc{benchleader_k_exaone_2_0_20261116,
author = {{BenchLeader}},
title = {{K-EXAONE 2.0 on the BenchLeader Index (method v1.4)}},
year = {2026},
month = nov,
howpublished = {\url{https://www.benchleader.com/models/k-exaone-2-0}},
note = {Data as of 2026-11-16}
}Every badge style, the embeddable top-10 widget and how to cite the Index
Questions people ask
- What are K-EXAONE 2.0's benchmark scores?
- As of 16 Nov 2026, K-EXAONE 2.0 scores 42.4 ±6.8 on the BenchLeader Index, strongest in long context (54) and weakest in coding (29). That rests on independent benchmark results only, and every score on this page links to its publisher.
- How does K-EXAONE 2.0 rank?
- K-EXAONE 2.0 is #494 of 608 ranked configurations on 16 Nov 2026. 234 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 72.7.
- When was K-EXAONE 2.0 released?
- LG AI Research released K-EXAONE 2.0 on 12 Aug 2026.
Data as of 16 Nov 2026. Compare with another model.
Cite as: BenchLeader, “K-EXAONE 2.0: benchmarks, pricing, speed and rank”, data as of 16 Nov 2026, https://www.benchleader.com/models/k-exaone-2-0.