List your company

Domain Capability Evaluation on in-house domain capability benchmarks

86.1Overall PerformanceYuvion-32B (Agent)
-3.44419.80343.0566.297Jun 26, 2026

Evaluation results

MethodLinks
Yuvion-32B (Agent)Category=Yuvion (Ours)2026.0686.195.3591.2181.1678.9583.6683.5292.4994.5377.7894.7873.67
Yuvion-32BCategory=Yuvion (Ours)2026.0685.789590.5680.578.6580.9782.3992.7694.5577.9394.5675.66
Yuvion-8BCategory=Yuvion (Ours)2026.0682.3893.287.3173.5177.5473.5382.0591.5491.4871.396.7367.96
Qwen3.6-PlusCategory=Proprietary2026.0681.8387.1392.3478.1173.1383.1271.1886.2394.7472.2692.4669.44
Qwen3-MaxCategory=Proprietary2026.0681.4189.390.4276.7468.7783.1480.7887.7493.3169.0589.7866.49
GPT-5.4Category=Proprietary2026.0680.7387.993.5679.7764.2275.6182.6985.1694.7776.877.5370
DeepSeek-R1Category=Open-source2026.0680.548891.4577.0667.9482.8175.0288.8694.7971.9888.0860
GLM-5Category=Open-source2026.0679.8484.5790.3777.262.3682.5682.4287.3692.4770.4788.6159.9
Qwen3-32BCategory=Open-source2026.0679.7988.491.4173.5366.2774.7679.7786.0294.2266.3390.7766.24
Qwen3.5-PlusCategory=Proprietary2026.0677.9289.7592.3878.9161.0282.7953.4979.894.1973.7885.1965.79
Qwen3.5-397B-A17BCategory=Open-source2026.0677.458891.9477.3962.1181.3551.7781.6793.9972.4785.2166.09
Qwen3.5-122B-A10BCategory=Open-source2026.0677.384.6591.1173.7967.9676.3359.5484.1494.567.8585.5364.93
Qwen3.5-27BCategory=Open-source2026.0677.1786.5590.6672.5768.7377.5458.9284.0692.7468.283.765.2
Qwen3-30B-A3B-2507Category=Open-source2026.0677.1487.3192.1671.4868.571.0877.680.7287.8760.8688.9162.01
DeepSeek-V3.2Category=Open-source2026.0676.2785.288.9568.7549.871.6278.0482.8994.3870.7383.2665.37
Qwen3.5-35B-A3BCategory=Open-source2026.0675.4683.4190.3671.0264.3275.8555.4883.0690.8167.2181.5367.03
KIMI-K2.5Category=Open-source2026.0674.6187.5291.8758.4838.7982.7176.0679.6191.2671.9174.7267.82
Qwen3-8BCategory=Open-source2026.0673.7181.2689.0969.4657.5168.3565.2980.8890.6561.8283.163.42
Qwen3.5-9BCategory=Open-source2026.0672.6878.4884.5568.4864.5569.3848.0682.487.7365.1384.266.49
Minimax-M2.5Category=Open-source2026.0672.688.191.3555.3461.174.479.2640.891.1871.0383.2662.76
Qwen3Guard-8BCategory=Guard2026.06000000000000
Llama-Guard4-12BCategory=Guard2026.06000000000000