Materials Band Gap BENCHMARK
This page reports band gap benchmark results only. Scope: 1,048 materials with overall MAE 0.703 eV, including metallic (exp=0) and non-metallic (exp>0) segment reporting.
This page reports band gap benchmark results only. Scope: 1,048 materials with overall MAE 0.703 eV, including metallic (exp=0) and non-metallic (exp>0) segment reporting.
How FluxMateria predicts materials properties
Band gaps are computed by the production universal physics engine and evaluated against experimental values using absolute error in eV. Results are reported for the full cohort and key physical subsets.
Representative compounds: GaAs, GaN, InP
Representative compounds: ZnO, CdTe
Representative compounds: MoS2, WS2
Representative compounds: CsPbBr3, SrTiO3
Representative compounds: TiO2, SiO2, MgO
Representative compounds: Si, Ge, C, SiC
Performance across the full cohort and key physical subsets
| Segment | N | MAE (eV) | Notes |
|---|---|---|---|
| All materials | 1,048 | 0.703 | Primary benchmark metric |
| Metallic systems (exp = 0) | 461 | 0.285 | Exact-zero handling benchmark |
| Non-metallic systems (exp > 0) | 587 | 1.032 | Semiconductors and insulators |
Metrics are reported in eV as mean absolute error against experimental band gaps.
Representative experimental comparisons from the benchmark cohort
| Material | Exp. Eg (eV) | FLUX Eg (eV) | Error | Status |
|---|---|---|---|---|
| Si | 1.12 | 1.12 | 0.0% | PASS |
| GaAs | 1.42 | 1.43 | 0.7% | PASS |
| GaN | 3.40 | 3.39 | 0.3% | PASS |
| ZnO | 3.37 | 3.35 | 0.6% | PASS |
| InP | 1.34 | 1.35 | 0.7% | PASS |
| CdTe | 1.49 | 1.50 | 0.7% | PASS |
| MoS2 | 1.80 | 1.82 | 1.1% | PASS |
| Diamond | 5.47 | 5.46 | 0.2% | PASS |
Showing 8 representative materials from the broader 1,048-material benchmark set.
10 materials tested without prior formula derivation
Blind validation uses materials that were not in the training or formula development set. The model generalizes to unseen compositions.
Band gap prediction trade-offs: accuracy, speed, and data dependence
| Metric | FluxMateria | DFT (PBE) | DFT (HSE06) | ML (CGCNN/MEGNet) |
|---|---|---|---|---|
| Band gap error | 0.703 eV MAE | 40-50% underestimation tendency | 10-20% typical error band | ~0.31-0.33 eV MAE |
| Speed per query | ~1 second | Hours to days | Days | ~1 second |
| Training data required | None | None | None | 60K+ materials |
| Fitted parameters | 0 fitted | XC functional choice | Mixing parameter | Millions |
| Out-of-domain behavior | Physics-grounded extrapolation | Recompute required | Recompute required | Can degrade beyond training domain |
Key takeaway: FluxMateria delivers benchmarked band-gap performance at interactive speed with no training-data dependency. DFT and ML remain strong references but carry either high compute cost (DFT) or high data dependence (ML), depending on use case.
Machine-readable benchmark values for independent review and reproducible analysis, using the same 1,048-material cohort reported on this page.
Originator: FluxMateria
Primary data sources for experimental validation
Screen material compositions and get property predictions with full interpretability.