LG AI Research
availableShows if the model has enough results for an index.K-EXAONE 2.0
K-EXAONE 2.0 is a reasoning model from LG AI Research. 18 benchmarks count toward its score, in 6 categories.
IndexOverall score out of 100.50.3 ±5.3
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.262K
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
18 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| Instruction-Following Eval | Instruction | 92.4% | 50.4 | — | — | Jeffrey Zhou et al. |
| AIME 2026 | Math | 92.3% | 52.2 | — | — | Qwen |
| MMMLU | Knowledge | 86.6% | — | — | — | OpenAI |
| Massive Multitask Language Understanding Professional | Knowledge | 83.5% | 52.1 | — | — | Yubo Wang et al. |
| Artificial Analysis GPQA Diamond | Knowledge | 82.9% | 53.5 | — | — | Artificial Analysis |
| GPQA Diamond | Knowledge | 82.2% | 54.1 | — | — | David Rein et al. |
| IMOAnswerBench | Math | 78.6% | — | — | — | DeepSeek-AI |
| Harvard-MIT Mathematics Tournament February 2026 | Math | 78.4% | 48.8 | — | — | Qwen |
| Claw-Eval | Agentic | 77.7% | 80.5 | — | — | Bowen Ye et al. |
| Instruction Following Benchmark | Instruction | 72.6% | 50.5 | — | — | Benchmark authors |
| PolyMath | Multilingual | 71.3% | — | — | — | Qwen |
| Software Engineering Benchmark Verified | Coding | 68.2% | 52.2 | — | — | Carlos E. Jimenez et al. |
| Artificial Analysis Long Context Reasoning | Reasoning | 56.2% | 47.1 | — | — | Artificial Analysis |
| Terminal-Bench 2.1 (provider run) | Agentic | 43.8% | 49.9 | — | — | DeepSeek-AI |
| Terminal-Bench 2.1 (provider run) | Agentic | 43.8% | 49.9 | — | — | DeepSeek-AI |
| Artificial Analysis SciCode | Coding | 42.0% | 51.2 | — | — | Artificial Analysis |
| Scientific Code Benchmark | Coding | 37.4% | 47.1 | — | — | Benchmark authors |
| Artificial Analysis Intelligence Index | Knowledge | 19.7% | 47.0 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 18.6% | 44.7 | — | — | Artificial Analysis |
| Humanity's Last Exam | Knowledge | 18.3% | 44.3 | — | — | Center for AI Safety et al. |
| Artificial Analysis Omniscience Accuracy | Knowledge | 13.1% | 30.1 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.9% | 40.3 | — | — | Artificial Analysis |
18 benchmarks count, from 19 of 22 results. A grey row does not count. Too few models took that benchmark.