Other · model
K-EXAONE 2.0 benchmark scores
As of 2026-10-07, K-EXAONE 2.0 (Other) has measured scores on 20 benchmarks and estimated scores on 60 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 82.9% | measured |
| AA-HLE | 18.6% | measured |
| AA-SciCode | 42.0% | measured |
| AIME26 | 92.3% | measured |
| Artificial Analysis Intelligence Index | 19.7% | measured |
| CritPt | 0.9% | measured |
| GDPval-AA | 33.1% | estimated ± 9.4 pp, low confidence |
| GPQA Diamond | 82.2% | measured |
| HLE | 18.3% | measured |
| IFBench | 72.6% | measured |
| AA-LCR | 56.2% | measured |
| LiveCodeBench v6 | 84.1% | estimated ± 3.3 pp, high confidence |
| AA-Omniscience Accuracy | 13.1% | measured |
| SciCode | 37.4% | measured |
| Terminal-Bench 2.1 | 43.8% | measured |
| BrowseComp | 82.0% | estimated ± 9.4 pp, low confidence |
| IFEval | 92.4% | measured |
| LongBench v2 | 0.6% | estimated ± 5.9 pp, low confidence |
| VITA-Bench | 55.6% | estimated ± 10.7 pp, low confidence |
| AA Coding Index | 38.2% | estimated ± 5.1 pp, medium confidence |
| BioMysteryBench (human-difficult) | 20.0% | estimated ± 5.9 pp, low confidence |
| SWE-bench Verified | 68.2% | measured |
| BFCL v4 | 100.0% | estimated ± 8.6 pp, low confidence |
| JobBench | 45.9% | estimated ± 8.4 pp, low confidence |
| SWE-bench Pro | 42.7% | estimated ± 3.2 pp, high confidence |
| AA Agentic Index | 27.7% | estimated ± 5.1 pp, low confidence |
| MMLU-Pro | 83.5% | measured |
| FrontierMath v2 (Tiers 1-3) | 24.4% | estimated ± 8.4 pp, low confidence |
| GPQA | 82.2% | estimated ± 0.4 pp, high confidence |
| AA-IFBench | 63.0% | estimated ± 8.2 pp, medium confidence |
| Gert Labs | 62.7% | estimated ± 9.1 pp, low confidence |
| ARC-AGI-1 | 75.1% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 33.9% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 24.3% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 40.9% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 3.0 | 2.8% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 2.4% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 0.0% | estimated ± 14.6 pp, low confidence |
| Vals GPQA Diamond | 81.2% | estimated ± 2.0 pp, medium confidence |
| Vals LiveCodeBench | 83.2% | estimated ± 0.8 pp, low confidence |
| Vals MMLU-Pro | 82.2% | estimated ± 1.6 pp, medium confidence |
| Vals SWE-bench | 57.9% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 39.8% | estimated ± 7.4 pp, low confidence |
| AA Terminal-Bench 2.1 | 52.1% | estimated ± 3.5 pp, medium confidence |
| AA Terminal-Bench 4.0 | 0.0% | estimated ± 8.9 pp, low confidence |
| CursorBench 4.0 | 13.2% | estimated ± 3.5 pp, medium confidence |
| HLE w/o tools | 13.8% | estimated ± 4.4 pp, high confidence |
| PostTrainBench v1.1 | 23.5% | estimated ± 7.2 pp, low confidence |
| Vibe Code Bench | 0.7% | estimated ± 8.1 pp, medium confidence |
| C-Eval | 85.2% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 77.7% | measured |
| HMMT Feb 2025 | 89.9% | estimated ± 1.8 pp, low confidence |
| HMMT Feb 2026 | 78.4% | measured |
| MCP Atlas | 77.5% | estimated ± 11.2 pp, low confidence |
| MCP-Tasks | 100.0% | estimated ± 6.4 pp, low confidence |
| MMAnswerBench | 78.2% | estimated ± 1.3 pp, medium confidence |
| MMLU-Redux | 92.2% | estimated ± 0.7 pp, high confidence |
| NL2Repo | 24.8% | estimated ± 6.1 pp, low confidence |
| SuperGPQA | 52.6% | estimated ± 7.5 pp, medium confidence |
| HealthBench Hard | 7.0% | estimated ± 7.7 pp, low confidence |
| MedXpertQA (Text) | 36.6% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 84.1% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 73.3% | estimated ± 4.7 pp, medium confidence |
| ResearchClawBench | 20.8% | estimated ± 1.3 pp, medium confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 26.3% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 35.3% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 38.5% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 66.7% | estimated ± 1.8 pp, low confidence |
| AIME 2025 | 93.1% | estimated ± 1.5 pp, medium confidence |
| LiveCodeBench | 78.8% | estimated ± 10.2 pp, low confidence |
| OpenHarmony Bench | 51.0% | estimated ± 2.4 pp, medium confidence |
| IMOAnswerBench | 78.6% | measured |
| MMMLU | 86.6% | measured |
| MMLU | 79.7% | estimated ± 1.1 pp, low confidence |
| MATH-500 | 97.3% | estimated ± 3.1 pp, medium confidence |