List your company

Factuality Correction on BIO (test)

51PrecisionRAC
-31.16-9.8311.532.83Jan 16, 2026

Evaluation results

MethodLinks
RACBase Model=gpt-oss-120b2026.015128421128
RACBase Model=gpt-oss-120b2026.015128421128
LLM2Base Model=gpt-oss-120b2026.014831411027
LLM2Base Model=gpt-oss-120b2026.014831411027
FCBase Model=mixtral-8x22b-instruct2026.014633411211
FACTCORRECTORBase Model=mixtral-8x22b-instruct2026.014633411211
LLM2Base Model=llama-3.3-70b-instruct2026.014521361218
LLM2Base Model=llama-3.3-70b-instruct2026.014521361218
FCBase Model=llama-3.3-70b-instruct2026.014422351217
FACTCORRECTORBase Model=llama-3.3-70b-instruct2026.014422351217
LLM2Base Model=mixtral-8x22b-instruct2026.01423037117
RACBase Model=llama-3.3-70b-instruct2026.014221331217
LLM2Base Model=mixtral-8x22b-instruct2026.01423037117
RACBase Model=llama-3.3-70b-instruct2026.014221331216
FCBase Model=gpt-oss-120b2026.014029361024
FACTCORRECTORBase Model=gpt-oss-120b2026.014029361024
RACBase Model=mixtral-8x22b-instruct2026.01392934513
RACBase Model=mixtral-8x22b-instruct2026.01392934513
CRITICBase Model=llama-3.3-70b-instruct2026.01371829813
CRITICBase Model=llama-3.3-70b-instruct2026.01371829813
CRITICBase Model=mixtral-8x22b-instruct2026.0127222555
LLM1Base Model=mixtral-8x22b-instruct2026.0127252727
CRITICBase Model=mixtral-8x22b-instruct2026.0127222555
LLM1Base Model=mixtral-8x22b-instruct2026.0127252727
FCBase Model=granite-4.0-h-small2026.01261020143
FACTCORRECTORBase Model=granite-4.0-h-small2026.01261020143
LLM1Base Model=llama-3.3-70b-instruct2026.01231419711
LLM1Base Model=llama-3.3-70b-instruct2026.01231419711
RACBase Model=granite-4.0-h-small2026.0122816104
RACBase Model=granite-4.0-h-small2026.0122816104
LLM2Base Model=granite-4.0-h-small2026.01191316133
LLM2Base Model=granite-4.0-h-small2026.01191316133
CRITICBase Model=granite-4.0-h-small2026.01122842
CRITICBase Model=granite-4.0-h-small2026.01122842
SFTBase Model=mixtral-8x22b-instruct2026.0150252
SFTBase Model=granite-4.0-h-small2026.015026-2
SFTBase Model=llama-3.3-70b-instruct2026.011-2-16-3
CRITICBase Model=gpt-oss-120b2026.0100001
CRITICBase Model=gpt-oss-120b2026.0100001
LLM1Base Model=granite-4.0-h-small2026.01-3-1-220
LLM1Base Model=granite-4.0-h-small2026.01-3-1-220
SFTBase Model=gpt-oss-120b2026.01-40-20-4
LLM1Base Model=gpt-oss-120b2026.01-28-10-22-246
LLM1Base Model=gpt-oss-120b2026.01-28-10-22-246