K-EXAONE-236B-A23B: benchmark scores, price and ranking
K-EXAONE-236B-A23B from LGAI-EXAONE ranks #84 of 743 LLMs on the LLMs Tiger aggregate benchmark score (52.0), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- LGAI-EXAONE
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #84 of 743 (score 52.0)
Across the 2 benchmarks where at least ten models are scored, K-EXAONE-236B-A23B is in the top 10% on 0 and in the top half on 2.
K-EXAONE-236B-A23B benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| MMLU-Pro | 83.8% | #18 of 136 | HuggingFace MMLU-Pro leaderboard | 2026-10-13 |
| GPQA Diamond | 79.1% | #110 of 275 | HuggingFace GPQA Diamond leaderboard | 2026-10-13 |
About K-EXAONE-236B-A23B
K-EXAONE-236B-A23B is an open-weight model that can run on your own hardware from LGAI-EXAONE. No API price is listed for it yet. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.
Where K-EXAONE-236B-A23B stands
On our aggregate score, K-EXAONE-236B-A23B is #84 of 743 ranked models, in the top quarter. Its score is 52.0; the scale is centred on 50, so it sits 2.0 points above the typical model. That beats 89% of the ranked field. Among the 5 ranked LGAI-EXAONE models it is #2. The next one up is EXAONE-4.5-33B at 52.1. The next one down is EXAONE-3.5-32B-Instruct at 48.4.
K-EXAONE-236B-A23B, benchmark by benchmark
MMLU-Pro puts K-EXAONE-236B-A23B at 83.8%, #18 of 136. That beats 87% of the models tested, but 4.3 points short of Darwin-180B-RSI (88.1%). The results either side are DeepSeek-R1 (84.0%) and NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (83.7%). It covers 57-subject knowledge + reasoning. The board median is 55.3%, so K-EXAONE-236B-A23B is 28.5 points above it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.
On GPQA Diamond, K-EXAONE-236B-A23B reaches 79.1%. It ranks #110 of 275, ahead of 60% of the field, and 16.7 points behind GPT-6 Astra (max) at 95.8%. The results either side are claude-sonnet-4-20250514_59K (79.2%) and Qwen3.5 9B (79.0%). It covers expert-level science questions. The board median is 71.7%, so K-EXAONE-236B-A23B is 7.4 points above it. Source: HuggingFace GPQA Diamond leaderboard, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: solid, ahead of 73% of the field on average across 2 benchmarks. Its best board here is MMLU-Pro (#18 of 136) and its weakest is GPQA Diamond (#110 of 275).
Reading these numbers
The 2 scores on this page come from 2 sources: HuggingFace GPQA Diamond leaderboard (1), HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #81 EXAONE-4.5-33B (52.1)
- #82 Claude Haiku 5.5 (max) (52.1)
- #83 NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (52.0)
- #85 Grok 4.5 (high) (52.0)
- #86 Darwin-398B-JGOS (52.0)
- #87 SWE-2 (max) (51.9)
More from LGAI-EXAONE
- EXAONE-4.5-33B (#81, 52.1)
- EXAONE-3.5-32B-Instruct (#359, 48.4)
- EXAONE-3.5-7.8B-Instruct (#500, 46.6)
- EXAONE-3.5-2.4B-Instruct (#562, 45.7)
Compare it on the live leaderboard → · How the aggregate score works