K-EXAONE 2.0
K-EXAONE 2.0LG AI ResearchOpen weightsReasoningReleased Jul 31, 2026
Overall score
—
Not enough evidence to rank yet
Context window
262K
262,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet
Benchmark results (15)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Knowledge
| HLE | 18.3 | #60 of 69 |
| MMLU-Pro | 83.5 | #27 of 67 |
| MMMLU | 86.6 | #5 of 11 |
Math
| AIME26 | 92.3 | #21 of 29 |
| HMMT Feb 2026 | 78.4 | #19 of 24 |
| IMOAnswerBench | 78.6 | #7 of 9 |
Agentic & tool use
| Terminal-Bench 2.1 | 43.8 | #62 of 68 |
| Claw-Eval | 77.7 | #2 of 36 |
Coding
| SWE-bench Verified | 68.2 | #67 of 98 |
| SciCode | 37.4 | #17 of 23 |
Instruction following
| IFEval | 92.4 | #13 of 53 |
| IFBench | 72.6 | #28 of 42 |
Multilingual
| PolyMath | 71.3 | #5 of 6 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price | — | — | — |
LG AI Research publishes K-EXAONE 2.0 under Apache-2.0 for self-hosting and does not publish a first-party hosted token rate for this exact checkpoint. We represent the open-weight row as self-host/free-per-token before infrastructure costs.
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.