Other · model
LFM3-1.7B benchmark scores
As of 2026-10-29, LFM3-1.7B (Other) has measured scores on 19 benchmarks and estimated scores on 55 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 65.8% | estimated ± 3.0 pp, medium confidence |
| AA-HLE | 5.7% | estimated ± 3.8 pp, high confidence |
| AA-SciCode | 29.5% | estimated ± 3.0 pp, high confidence |
| CritPt | 0.4% | estimated ± 4.0 pp, high confidence |
| GDPval-AA | 19.0% | estimated ± 5.5 pp, medium confidence |
| GPQA Diamond | 63.4% | measured |
| HLE | 7.2% | measured |
| IFBench | 73.0% | measured |
| AA-LCR | 52.8% | measured |
| LiveCodeBench v6 | 73.5% | measured |
| SciCode | 28.5% | measured |
| Terminal-Bench 2.1 | 12.9% | measured |
| BrowseComp | 88.9% | estimated ± 7.0 pp, low confidence |
| HLE w/ tools | 13.9% | measured |
| IFEval | 96.7% | measured |
| LongBench v2 | 57.0% | estimated ± 5.8 pp, low confidence |
| VITA-Bench | 24.7% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 1.7% | estimated ± 3.1 pp, medium confidence |
| AA Coding Index | 23.8% | estimated ± 5.3 pp, medium confidence |
| APEX-Agents | 0.0% | estimated ± 0.6 pp, low confidence |
| APEX-Agents-AA | 11.0% | estimated ± 5.5 pp, medium confidence |
| SWE-bench Verified | 43.4% | measured |
| AutomationBench | 41.3% | measured |
| BFCL v4 | 71.4% | measured |
| CyberGym | 84.8% | estimated ± 4.6 pp, medium confidence |
| JobBench | 14.7% | estimated ± 6.4 pp, medium confidence |
| SWE-bench Pro | 17.8% | estimated ± 4.6 pp, medium confidence |
| τ³-bench results | 68.0% | measured |
| WideResearch | 49.2% | estimated ± 4.8 pp, low confidence |
| AA Agentic Index | 18.4% | estimated ± 5.9 pp, medium confidence |
| MMLU-Pro | 6.0% | estimated ± 4.6 pp, medium confidence |
| AA-IFBench | 58.4% | estimated ± 7.4 pp, medium confidence |
| Artificial Analysis Intelligence Index | 10.7% | estimated ± 6.3 pp, medium confidence |
| GPQA | 63.4% | measured |
| MMLU | 66.9% | estimated ± 1.0 pp, medium confidence |
| AA-Omniscience Accuracy | 7.1% | measured |
| MMMLU | 80.0% | estimated ± 1.7 pp, high confidence |
| AA MMLU-Pro | 82.0% | estimated ± 0.7 pp, medium confidence |
| Gert Labs | 48.4% | estimated ± 8.2 pp, low confidence |
| AA Harvey LAB v1.0 | 56.2% | estimated ± 1.7 pp, low confidence |
| AA Tau3 Banking | 46.1% | estimated ± 3.8 pp, medium confidence |
| ARC-AGI-1 | 28.4% | estimated ± 7.6 pp, low confidence |
| OSWorld-Verified | 72.4% | estimated ± 3.8 pp, medium confidence |
| Vals GPQA Diamond | 73.0% | estimated ± 8.5 pp, low confidence |
| Vals MMLU-Pro | 80.6% | estimated ± 2.4 pp, medium confidence |
| Vals SWE-bench | 26.0% | estimated ± 6.8 pp, low confidence |
| CWE-Bench-AA | 6.4% | estimated ± 5.2 pp, low confidence |
| AA Cyber Index | 33.9% | estimated ± 9.4 pp, medium confidence |
| DeepsecBench-AA | 0.0% | estimated ± 7.4 pp, low confidence |
| AA ITBench | 21.5% | estimated ± 4.4 pp, medium confidence |
| HLE w/o tools | 9.5% | estimated ± 4.3 pp, medium confidence |
| SWE Multilingual | 23.0% | measured |
| Toolathlon-Verified | 24.0% | estimated ± 5.7 pp, low confidence |
| Vibe Code Bench | 0.6% | estimated ± 8.1 pp, low confidence |
| C-Eval | 86.6% | estimated ± 1.2 pp, high confidence |
| Claw-Eval | 68.6% | measured |
| DeepPlanning | 32.9% | estimated ± 8.3 pp, low confidence |
| MCP Atlas | 32.6% | measured |
| MCP-Tasks | 62.7% | estimated ± 0.6 pp, medium confidence |
| MMLU-Redux | 91.9% | estimated ± 0.8 pp, low confidence |
| NL2Repo | 21.4% | estimated ± 3.4 pp, medium confidence |
| QwenClawBench | 53.2% | estimated ± 2.6 pp, high confidence |
| SuperGPQA | 50.0% | estimated ± 6.9 pp, medium confidence |
| Toolathlon | 36.3% | estimated ± 7.5 pp, medium confidence |
| LiveCodeBench Pro | 31.7% | measured |
| MMLU-Pro (Arcee) | 75.7% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 71.4% | estimated ± 2.3 pp, low confidence |
| ResearchClawBench | 19.4% | estimated ± 1.3 pp, high confidence |
| STEMBench | 2.2% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 0.3% | estimated ± 4.3 pp, low confidence |
| LiveCodeBench | 52.5% | estimated ± 14.6 pp, low confidence |
| MRCRv2 | 23.1% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 59.7% | estimated ± 2.6 pp, low confidence |
| PinchBench | 99.0% | estimated ± 5.0 pp, low confidence |