List your company

Verification on VerifyBench Hard 1.0 (test)

91.9Mean@3 AccuracyCoSineVerifier-Tool-4B
76.61280.58184.5588.519Dec 1, 2025

Evaluation results

MethodLinks
CoSineVerifier-Tool-4BVerifier Type=CoT Verifier, Model Access Category=Open-source2025.1291.9
CoSineVerifier-32BVerifier Type=Labeling Verifier2025.1290
CompassVerifier-32BVerifier Type=Labeling Verifier2025.1288.9
o3Verifier Type=CoT Verifier, Model Access Category=Closed-source2025.1288.7
Qwen3-235B-A22B-2507Verifier Type=CoT Verifier, Model Access Category=Open-source2025.1287.7
CompassVerifier-32B (CoT)Verifier Type=CoT Verifier, Model Access Category=Open-source2025.1286.5
Gemini2.5-FlashVerifier Type=CoT Verifier, Model Access Category=Closed-source2025.1286
CoSineVerifier-4BVerifier Type=Labeling Verifier2025.1285.4
Qwen3-32BVerifier Type=CoT Verifier, Model Access Category=Open-source2025.1285.2
CompassVerifier-7BVerifier Type=Labeling Verifier2025.1285.2
GPT-oss-20BVerifier Type=CoT Verifier, Model Access Category=Open-source2025.1284.7
GPT-4oVerifier Type=CoT Verifier, Model Access Category=Closed-source2025.1284.6
Qwen3-4B-Instruct-2507Verifier Type=CoT Verifier, Model Access Category=Open-source2025.1284.1
Qwen3-8BVerifier Type=CoT Verifier, Model Access Category=Open-source2025.1283.6
XVerify-8B-IVerifier Type=Labeling Verifier2025.1283.3
CompassVerifier-7B (CoT)Verifier Type=CoT Verifier, Model Access Category=Open-source2025.1282.6
Qwen3-4BVerifier Type=CoT Verifier, Model Access Category=Open-source2025.1280.3
LLaMA3.3-70B-InstructVerifier Type=CoT Verifier, Model Access Category=Open-source2025.1277.2