List your company

Factuality on BIOS

56FactualityPROXIMALByte
7.1219.8132.545.19Feb 6, 2026

Evaluation results

MethodLinks
PROXIMALByteSafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 4 17B×16E, Decoding level=Byte-level, NCR threshold=>= 75%2026.0256
PROXIMALByteSafe model (ps)=COMMA 7B, Risky model (pr)=LLAMA 4 17B×16E, Decoding level=Byte-level, NCR threshold=>= 75%2026.0256
PROXIMALSafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Token-level, NCR threshold=>= 75%2026.0253
PROXIMALByteSafe model (ps)=COMMA 7B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0252
TOKENSWAPSafe model (ps)=COMMA 7B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0249
PROXIMALByteSafe model (ps)=COMMA 7B, Risky model (pr)=QWEN 2.5 72B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0249
PROXIMALByteSafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=QWEN 2.5 72B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0248
TOKENSWAPSafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 4 17B×16E, Decoding level=Byte-level, NCR threshold=>= 75%2026.0247
RCADSafe model (ps)=COMMA 7B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0246
TOKENSWAPSafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Token-level, NCR threshold=>= 75%2026.0244
TOKENSWAPSafe model (ps)=COMMA 7B, Risky model (pr)=QWEN 2.5 72B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0242
MEMFREESafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Token-level, NCR threshold=>= 75%2026.0237
RCADSafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Token-level, NCR threshold=>= 75%2026.0237
CP-FUSESafe model (ps)=COMMA 7B, Risky model (pr)=LLAMA 4 17B×16E, Decoding level=Byte-level, NCR threshold=>= 75%2026.0237
TOKENSWAPSafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=QWEN 2.5 72B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0237
RCADSafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 4 17B×16E, Decoding level=Byte-level, NCR threshold=>= 75%2026.0236
RCADSafe model (ps)=COMMA 7B, Risky model (pr)=LLAMA 4 17B×16E, Decoding level=Byte-level, NCR threshold=>= 75%2026.0236
CP-FUSESafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 4 17B×16E, Decoding level=Byte-level, NCR threshold=>= 75%2026.0227
CP-FUSESafe model (ps)=COMMA 7B, Risky model (pr)=QWEN 2.5 72B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0225
CP-FUSESafe model (ps)=COMMA 7B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0223
CP-FUSESafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Token-level, NCR threshold=>= 75%2026.0220
CP-FUSESafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=QWEN 2.5 72B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0218
SAFESafe model (ps)=COMMA 7B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0216
SAFESafe model (ps)=COMMA 7B, Risky model (pr)=QWEN 2.5 72B, Decoding level=Byte-level, NCR threshold=>= 75%2026.0216
SAFESafe model (ps)=COMMA 7B, Risky model (pr)=LLAMA 4 17B×16E, Decoding level=Byte-level, NCR threshold=>= 75%2026.0216
SAFESafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 3.1 70B, Decoding level=Token-level, NCR threshold=>= 75%2026.029
SAFESafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=QWEN 2.5 72B, Decoding level=Byte-level, NCR threshold=>= 75%2026.029
SAFESafe model (ps)=TINYCOMMA 1.8B, Risky model (pr)=LLAMA 4 17B×16E, Decoding level=Byte-level, NCR threshold=>= 75%2026.029