Other · model
K-EXAONE 2.0 benchmark scores
As of 2026-11-22, K-EXAONE 2.0 (Other) has measured scores on 22 benchmarks and estimated scores on 94 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 | 7.6% | measured |
| CritPt | 0.9% | measured |
| GDPval-AA | 15.4% | measured |
| GPQA Diamond | 82.2% | measured |
| HLE | 18.3% | measured |
| IFBench | 72.6% | measured |
| AA-LCR | 56.2% | measured |
| LiveCodeBench v6 | 76.5% | estimated ± 4.4 pp, high confidence |
| AA-Omniscience Accuracy | 14.5% | measured |
| SciCode | 37.4% | measured |
| Terminal-Bench 2.1 | 43.8% | measured |
| BrowseComp | 54.7% | estimated ± 9.2 pp, medium confidence |
| HLE w/ tools | 41.2% | estimated ± 5.3 pp, low confidence |
| IFEval | 92.4% | measured |
| LongBench v2 | 53.3% | estimated ± 5.5 pp, medium confidence |
| VITA-Bench | 55.6% | estimated ± 10.7 pp, low confidence |
| AA Coding Index | 37.3% | estimated ± 5.3 pp, medium confidence |
| APEX-Agents | 10.5% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 15.5% | estimated ± 9.5 pp, medium confidence |
| BioMysteryBench (human-difficult) | 15.7% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 73.6% | estimated ± 9.6 pp, medium confidence |
| SWE-bench Verified | 68.2% | measured |
| BFCL v4 | 70.5% | estimated ± 2.7 pp, high confidence |
| CyberGym | 36.0% | estimated ± 6.0 pp, low confidence |
| JobBench | 10.2% | estimated ± 8.7 pp, low confidence |
| SWE-bench Pro | 45.4% | estimated ± 4.5 pp, high confidence |
| WideResearch | 65.7% | estimated ± 7.8 pp, low confidence |
| AA Agentic Index | 11.2% | estimated ± 3.1 pp, high confidence |
| MMLU-Pro | 83.5% | measured |
| AA-IFBench | 57.7% | estimated ± 7.4 pp, medium confidence |
| BBH | 98.0% | estimated ± 2.8 pp, medium confidence |
| GPQA | 82.1% | estimated ± 1.2 pp, high confidence |
| MMLU | 80.3% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 81.7% | estimated ± 2.1 pp, medium confidence |
| Vals LiveCodeBench | 83.2% | estimated ± 0.8 pp, low confidence |
| Vals MMLU-Pro | 82.2% | estimated ± 1.6 pp, medium confidence |
| MATH-500 | 97.3% | estimated ± 3.1 pp, medium confidence |
| MMMLU | 86.6% | measured |
| AIME 2025 | 93.5% | estimated ± 1.8 pp, medium confidence |
| AA MMLU-Pro | 83.2% | estimated ± 0.8 pp, medium confidence |
| Gert Labs | 28.5% | estimated ± 10.0 pp, low confidence |
| AA Tau3 Banking | 21.7% | estimated ± 4.1 pp, medium confidence |
| ARC-AGI-1 | 75.4% | estimated ± 2.5 pp, medium confidence |
| ARC-AGI-2 | 14.3% | estimated ± 9.7 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 | 6.7% | estimated ± 4.2 pp, low confidence |
| FrontierMath v2 (Tier 4) | 0.0% | estimated ± 4.1 pp, low confidence |
| FrontierMath v2 (Tiers 1-3) | 22.7% | estimated ± 8.8 pp, low confidence |
| FrontierSWE v2 | 7.2% | estimated ± 14.2 pp, low confidence |
| MazeBench | 0.4% | estimated ± 5.5 pp, low confidence |
| OSWorld-Verified | 73.9% | estimated ± 3.8 pp, low confidence |
| Terminal-Bench 4.1 | 0.0% | estimated ± 10.9 pp, low confidence |
| Vals SWE-bench | 57.9% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 40.2% | estimated ± 7.3 pp, low confidence |
| CWE-Bench-AA | 21.9% | estimated ± 10.1 pp, low confidence |
| DeepsecBench-AA | 0.1% | estimated ± 8.9 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 3.5% | estimated ± 2.1 pp, low confidence |
| AA ITBench | 35.8% | estimated ± 5.1 pp, low confidence |
| Bug Hunt Bench | 15.9% | estimated ± 10.5 pp, low confidence |
| CursorBench 4.0 | 28.4% | estimated ± 4.9 pp, medium confidence |
| CWE-bench v1 | 23.3% | estimated ± 6.4 pp, low confidence |
| DeepSWE | 37.6% | estimated ± 7.5 pp, low confidence |
| DRACO | 61.9% | estimated ± 2.0 pp, low confidence |
| FrontierCode 2.0 | 26.1% | estimated ± 9.3 pp, low confidence |
| HLE w/o tools | 23.1% | estimated ± 2.7 pp, medium confidence |
| PostTrainBench v1.1 | 25.9% | estimated ± 7.4 pp, low confidence |
| Toolathlon-Verified | 37.7% | estimated ± 3.1 pp, medium confidence |
| VulcanBench Frontier v4 | 72.0% | estimated ± 6.8 pp, low confidence |
| GDP.pdf | 17.0% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 8.6 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| Vibe Code Bench | 0.0% | estimated ± 8.4 pp, medium confidence |
| Hermes Bench | 44.4% | estimated ± 2.9 pp, medium confidence |
| Hermes Index | 14.8% | estimated ± 8.7 pp, low confidence |
| ExploitGym | 0.1% | estimated ± 10.6 pp, low confidence |
| C-Eval | 88.5% | estimated ± 0.9 pp, low confidence |
| Claw-Eval | 77.7% | measured |
| HMMT Feb 2025 | 91.5% | estimated ± 1.9 pp, low confidence |
| HMMT Feb 2026 | 78.4% | measured |
| HMMT Nov 2025 | 87.7% | estimated ± 2.8 pp, high confidence |
| INCLUDE | 85.3% | estimated ± 1.9 pp, low confidence |
| MAXIFE | 84.0% | estimated ± 4.7 pp, medium confidence |
| MCP Atlas | 57.0% | estimated ± 10.7 pp, low confidence |
| MMAnswerBench | 78.2% | estimated ± 1.3 pp, medium confidence |
| MMLU-ProX | 84.5% | estimated ± 1.0 pp, medium confidence |
| MMLU-Redux | 93.8% | estimated ± 0.5 pp, medium confidence |
| NL2Repo | 23.1% | estimated ± 6.2 pp, low confidence |
| NOVA-63 | 58.0% | estimated ± 1.3 pp, medium confidence |
| PolyMath | 71.3% | measured |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 59.5% | estimated ± 7.2 pp, medium confidence |
| Toolathlon | 27.1% | estimated ± 6.3 pp, low confidence |
| HealthBench Hard | 8.9% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 84.1% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 74.3% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 20.8% | estimated ± 1.3 pp, medium confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 26.0% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 45.4% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| HealthBench Professional (raw) | 38.2% | estimated ± 4.5 pp, medium confidence |
| ScarfBench | 40.4% | estimated ± 14.0 pp, low confidence |
| STEMBench | 2.3% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 10.6% | estimated ± 4.3 pp, low confidence |
| LiveCodeBench | 71.8% | estimated ± 14.6 pp, low confidence |
| OpenHarmony Bench v1.0 | 51.0% | estimated ± 2.4 pp, medium confidence |
| IMOAnswerBench | 78.6% | measured |
| MRCRv2 | 23.8% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 60.0% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 9.7% | estimated ± 10.2 pp, low confidence |