List your company

Natural Language Inference on BioNLI

72.46Accuracy (Chinese)LLaMA-3.2-3B
6.659223.742140.82557.9079Jan 5, 2026

Evaluation results

MethodLinks
LLaMA-3.2-3BCategory=Open-Weight, Parameters=3B2026.0172.4645.0536.1743.4760.453.4954.4855.6931.220.0927.1620.1443.32
o4-miniCategory=Proprietary, Variant=mini2026.0168.9773.3467.1366.968.4267.0870.2471.0661.4232.349.255.2462.61
gpt-oss-20BCategory=Open-Weight, Parameters=20B2026.0168.8862.7761.5560.2464.2264.662.8163.9155.1624.4746.6454.2357.46
Claude-4.0-SonnetCategory=Proprietary, Variant=Sonnet2026.0168.3175.4663.8859.7262.9858.7268.4867.9554.7445.4747.3853.8260.58
GPT-5Category=Proprietary2026.0165.773.4157.7356.76367.4760.3262.9851.6448.4345.8645.4358.22
MediPhiCategory=Open-Weight, Backbone=Phi2026.0164.5672.4668.5373.8960.1641.8572.5774.0825.7344.6321.3542.755.21
gpt-oss-120BCategory=Open-Weight, Parameters=120B2026.0164.0770.9359.6260.1363.7664.6263.163.2967.241.4949.7458.1460.51
GPT-4o-miniCategory=Proprietary, Variant=mini2026.0163.5263.7149.2346.1753.5657.0549.9850.1242.2327.6540.9931.4447.97
Phi-4-ReasoningCategory=Open-Weight, Type=Reasoning2026.0163.1469.1659.4755.8461.8759.3357.6861.6557.7415.2548.7837.8953.98
Baichuan-M2-32BCategory=Open-Weight, Parameters=32B2026.0162.7157.550.3659.8658.8359.7154.755.6736.4830.7941.0743.3150.92
DeepSeek-R1Category=Open-Weight, Variant=R12026.0162.5974.1760.1960.4856.8755.4264.3262.4951.0950.5254.5949.1458.49
Gemini-2.5-FlashCategory=Proprietary, Variant=Flash2026.0162.4469.0658.1359.458.7461.8261.2960.6653.7655.5463.9354.5959.95
GPT-5-miniCategory=Proprietary, Variant=mini2026.0160.9968.9360.258.0459.2459.0963.3163.8653.6326.3233.5252.4954.97
DeepSeek-R1-Qwen3-8BCategory=Open-Weight, Backbone=Qwen3, Parameters=8B2026.0159.3564.4351.3448.3452.4248.9352.6354.9744.6711.5418.213.9243.39
GPT-4.1-miniCategory=Proprietary, Variant=mini2026.0159.164.6855.9652.4955.8754.8958.9559.8746.8121.3936.3737.9650.36
Qwen2.5-3BCategory=Open-Weight, Parameters=3B2026.0158.5363.5249.3546.7958.7758.8155.0554.320.771.7212.8610.4940.91
Qwen3-14BCategory=Open-Weight, Parameters=14B2026.0158.2168.7257.6252.8658.3557.1663.2661.6149.152.4132.6329.0449.25
Qwen3-14B-thinkingCategory=Open-Weight, Parameters=14B, Type=Thinking2026.0157.7969.9659.8356.7161.9260.4365.1462.6855.642.627.1933.8851.15
Mistral-Small-3.1-24BCategory=Open-Weight, Parameters=24B2026.0153.6365.0148.4143.9747.2848.8243.948.1142.662421.332.4943.3
Phi-4-miniCategory=Open-Weight, Variant=mini2026.0153.4954.3951.7548.4154.6543.943.649.3238.8231.531.7141.145.22
HuatuoGPT-o1-72BCategory=Open-Weight, Parameters=72B, Type=Reasoning (o1)2026.0152.8164.9259.0857.5453.9355.5961.6163.3344.2614.8840.3225.4149.47
Phi-4Category=Open-Weight2026.0152.2659.452.5551.6953.7852.2454.5254.9644.4534.9944.6435.9749.29
Qwen2.5-14BCategory=Open-Weight, Parameters=14B2026.0152.1967.448.8745.2945.6848.6351.3153.2445.4759.0470.5338.0152.14
Qwen3-4BCategory=Open-Weight, Parameters=4B2026.0152.1759.0440.7638.7649.6943.7550.249.5111.723.2124.314.5636.47
LLaMA-3.1-8BCategory=Open-Weight, Parameters=8B2026.0152.138.3736.3935.4268.5145.443.8440.9439.9949.9438.4712.6741.84
QwQ-32BCategory=Open-Weight, Parameters=32B2026.0151.8459.0349.3547.1548.4647.3150.7750.8647.1939.3943.3545.348.33
DeepSeek-V3Category=Open-Weight, Variant=V32026.0151.3763.9149.851.949.2848.6652.2150.8143.5942.3337.7832.8547.87
Qwen3-1.7BCategory=Open-Weight, Parameters=1.7B2026.0151.2954.7745.4155.5649.7741.5645.147.0749.6437.2247.3942.4447.27
LLaMA-4-MaverickCategory=Open-Weight, Variant=Maverick2026.0150.3161.5946.1345.7450.1753.1448.9849.0439.6763.1942.3937.3948.98
Qwen3-4B-thinkingCategory=Open-Weight, Parameters=4B, Type=Thinking2026.0150.2661.9850.4547.1151.7549.6554.1954.5726.593.4327.411.6640.75
Qwen2.5-7BCategory=Open-Weight, Parameters=7B2026.0150.2262.0453.8747.8849.6144.754.6250.1145.4328.7738.6729.1646.26
GPT-4.1Category=Proprietary2026.0149.6764.5351.249.0749.6852.2751.4551.3940.2945.0941.0934.2348.33
HuatuoGPT-o1-7BCategory=Open-Weight, Parameters=7B, Type=Reasoning (o1)2026.0149.0257.6652.0351.4354.4649.9552.4955.1116.972.746.524.0137.7
Qwen3-8B-thinkingCategory=Open-Weight, Parameters=8B, Type=Thinking2026.0148.7262.3452.5248.3656.0350.556.1156.5629.988.2729.7223.3943.54
LLaMA-4-ScoutCategory=Open-Weight, Variant=Scout2026.0148.1456.4642.5242.4743.5545.1447.6544.0440.8454.1962.8244.0447.65
Qwen2.5-72BCategory=Open-Weight, Parameters=72B2026.0147.666555.3952.6250.0753.5958.9260.0738.9671.455.4629.453.21
Qwen3-8BCategory=Open-Weight, Parameters=8B2026.0147.0261.241.138.8851.1645.5945.2948.1935.023.7952.7417.0840.59
LLaMA-3.3-70BCategory=Open-Weight, Parameters=70B2026.0146.858.445.3541.2942.444.246.6846.013969.3348.7629.3846.47
MedGemma-27BCategory=Open-Weight, Parameters=27B, Backbone=Gemma2026.0146.3954.8145.351.2248.4252.0551.3350.7648.7524.6741.9446.146.81
GPT-4.1-nanoCategory=Proprietary, Variant=nano2026.0146.3555.6648.3545.1553.8652.7250.2449.2148.2246.2643.8939.7448.31
GPT-5-nanoCategory=Proprietary, Variant=nano2026.0145.941.1434.1745.4851.2342.1149.3151.5158.1931.5558.9455.0147.04
HuatuoGPT-o1-70BCategory=Open-Weight, Parameters=70B, Type=Reasoning (o1)2026.0144.6258.7547.6546.343.5846.8848.0449.3537.8155.3539.0533.8745.94
Phi-4-mini-ReasoningCategory=Open-Weight, Variant=mini, Type=Reasoning2026.0143.1859.2848.1144.6931.6320.3737.4337.0635.9845.1435.0423.8538.48
GPT-4oCategory=Proprietary2026.0138.7745.3542.0940.141.247.0842.9642.7634.3115.8833.7834.1738.2
Claude-3.5-HaikuCategory=Proprietary, Variant=Haiku2026.0137.7550.1839.7740.4740.1144.7940.4940.6837.0947.1270.8925.7642.93
Gemma-3-27BCategory=Open-Weight, Parameters=27B2026.0136.9349.2636.7239.2439.794439.2239.6135.4712.5131.737.0236.79
LLaMA-3.1-70BCategory=Open-Weight, Parameters=70B2026.0135.1758.5635.935.9536.1940.6737.735.6934.5458.8832.9126.1539.03
Gemma-3-4BCategory=Open-Weight, Parameters=4B2026.0135.0539.8735.2934.4736.0133.3834.433.834.212.3226.5832.9831.53
Bio-Medical-LLaMA-3-8BCategory=Open-Weight, Backbone=LLaMA-3, Parameters=8B2026.0135.0340.8425.9731.7634.8325.7332.1929.8326.0736.2830.8935.0132.04
Mistral-7B-v0.3Category=Open-Weight, Parameters=7B2026.0133.772.9615.3732.3726.5227.1522.7919.8214.179.8410.8710.7818.87
HuatuoGPT-o1-8BCategory=Open-Weight, Parameters=8B, Type=Reasoning (o1)2026.0133.6834.4136.2631.3744.0235.3537.8637.1227.491.7821.647.5629.04
Gemma-3-12BCategory=Open-Weight, Parameters=12B2026.0132.3938.3234.5232.2935.8237.373635.2839.354.8355.1535.6934.75
MedGemma-4BCategory=Open-Weight, Parameters=4B, Backbone=Gemma2026.0130.7236.5339.8535.2832.5936.435.6736.3332.3316.3228.5228.0732.38
MedReason-8BCategory=Open-Weight, Parameters=8B2026.0127.66.414.324.1525.5330.9124.11.698.430.4937.0923.8616.22
OpenBioLLM-70BCategory=Open-Weight, Parameters=70B2026.0112.7732.5626.8615.5510.2610.9222.3627.5311.4711.4716.1615.9317.82
OpenBioLLM-8BCategory=Open-Weight, Parameters=8B2026.019.1911.6813.8317.58.928.7317.1519.1310.2114.5111.2512.2812.86