List your company

Natural Language Inference on MedNLI (test)

86.57AccuracyT5
10.067629.928849.7969.6512May 28, 2021Mar 4, 2022Dec 10, 2022Sep 16, 2023Jun 23, 2024Mar 30, 2025Jan 5, 2026

Evaluation results

MethodLinks
T5Model Size=Large2021.0586.57————————————
SciFiveModel Size=Large, Pre-training=PubMed2021.0586.57————————————
Clinical MosaicFine-tuned=true2025.0286.5————————————
BlueBERTModel Size=Large2021.0586.36————————————
SciFiveModel Size=Large, Pre-training=PMC2021.0586.36————————————
BioBERTModel Size=Large2021.0586.08————————————
SciFiveModel Size=Large, Pre-training=PubMed+PMC2021.0586.08————————————
BioBERTModel Size=Base2021.0585.3————————————
BlueBERTModel Size=Base2021.0584.88————————————
SciFiveModel Size=Base, Pre-training=PubMed2021.0584.25————————————
Clinical Discharge BERT2025.0284.1————————————
T5Model Size=Base2021.0584————————————
BERTModel Size=Base, Variant=base2021.0583.9————————————
SciFiveModel Size=Base, Pre-training=PMC2021.0583.8————————————
SciFiveModel Size=Base, Pre-training=PubMed+PMC2021.0583.8————————————
Bio+Clinical BERT2025.0282.7————————————
BioBERT2025.0280.8————————————
Discharge Summary BERT2025.0280.6————————————
BERT2025.0277.6————————————
GPT-5LLM Category=Proprietary2026.0176.518186.3585.8985.7682.1283.3684.7485.6380.3943.2254.0565.65
o4-miniLLM Category=Proprietary2026.0176.1484.9288.7687.6987.4585.0584.487.2687.7979.121.6751.8667.75
GPT-5-miniLLM Category=Proprietary2026.0175.1383.7788.5687.7186.4883.3682.8686.7987.2372.5532.1946.9663.09
GPT-4.1LLM Category=Proprietary2026.0175.183.1287.7585.3384.8882.2482.4185.1286.4371.638.8150.0263.42
gpt-oss-120BLLM Category=Open-Weight2026.0174.0482.2387.2184.7186.0782.2982.7185.2985.772.5325.4248.8565.45
SOTAModel Size=Base2021.0573.5————————————
p=0.20fine-tuning=true, at interaction=142022.0373.3————————————
p=0.30fine-tuning=true, at interaction=72022.0373.2————————————
p=0.05fine-tuning=true, at interaction=32022.0372.9————————————
p=0.25fine-tuning=true, at interaction=122022.0372.9————————————
p=0.45fine-tuning=true, at interaction=72022.0372.9————————————
p=0.35fine-tuning=true, at interaction=72022.0372.8————————————
p=0.40fine-tuning=true, at interaction=92022.0372.6————————————
p=0.50fine-tuning=true, at interaction=92022.0372.6————————————
GP-TS rhofine-tuning=true, at interaction=92022.0372.6————————————
p=0.15fine-tuning=true, at interaction=132022.0372.5————————————
GP-TS psifine-tuning=true, at interaction=62022.0372.3————————————
p=0.10fine-tuning=true, at interaction=92022.0371.9————————————
GPT-4.1-miniLLM Category=Proprietary2026.0171.2282.7487.7285.3982.8679.2780.9382.6582.7563.4719.947.359.69
Claude-4.0-SonnetLLM Category=Proprietary2026.0171.0781.485.6679.3275.7578.5380.176.1378.368.3534.5257.8456.88
DeepSeek-V3LLM Category=Open-Weight2026.0168.7578.4284.3577.9979.1575.0375.0576.578.5368.134.2145.9151.76
GPT-4oLLM Category=Proprietary2026.0168.6878.1881.7575.4475.4776.1276.8778.6275.1571.2927.2746.8861.18
GPT-4o-miniLLM Category=Proprietary2026.0168.0779.7784.8481.3179.1978.1177.0580.379.6562.0329.1234.6650.77
LLaMA-4-MaverickLLM Category=Open-Weight2026.0167.8574.0385.0173.7570.5671.0778.1672.7975.4465.836.3948.4862.78
gpt-oss-20BLLM Category=Open-Weight2026.0167.8481.8276.8283.5684.1980.8979.9783.4482.9853.1115.8634.3657.05
RoBERTa basefine-tuning=true, at interaction=02022.0367.5————————————
DeepSeek-R1LLM Category=Open-Weight2026.0167.4477.9383.3774.9176.7576.173.0374.6577.5259.4634.9645.9754.67
Gemini-2.5-FlashLLM Category=Proprietary2026.0167.3471.8383.4870.7169.667.7869.869.2670.1267.1446.9159.262.22
Qwen2.5-72BLLM Category=Open-Weight2026.0167.0380.4585.3183.883.677.5778.6182.7882.7349.3334.0633.6532.43
MedGemma-27BLLM Category=Open-Weight2026.0166.6677.1981.5874.374.8675.0377.8476.1777.2667.9626.2736.5154.88
Gemma-3-27BLLM Category=Open-Weight2026.0166.0377.582.7570.1673.6973.557872.573.3271.9324.5438.7355.62
LLaMA-4-ScoutLLM Category=Open-Weight2026.0165.7676.7181.4571.2572.2868.470.5872.7173.1468.7534.5942.4956.8
Phi-4-ReasoningLLM Category=Open-Weight2026.0164.2679.8285.5381.382.0679.5978.3976.9982.3857.4711.3132.9923.34
Qwen3-14BLLM Category=Open-Weight2026.0163.7280.7282.7281.3377.8879.0678.1981.5782.5344.4221.2722.8132.14
Phi-4LLM Category=Open-Weight2026.0163.1475.9283.8877.9179.3977.874.1676.6478.4747.8423.931.6830.09
GPT-4.1-nanoLLM Category=Proprietary2026.016371.5283.575.1375.0970.9769.6372.4275.8156.5624.5333.2847.57
Qwen3-14B-thinkingLLM Category=Open-Weight2026.0162.8480.4984.6980.5979.2579.5278.6281.8680.9953.278.5517.3728.89
QwQ-32BLLM Category=Open-Weight2026.0162.477.7183.8176.6877.6175.4778.1277.0877.2234.1428.1331.0231.81
HuatuoGPT-o1-72BLLM Category=Open-Weight2026.0162.3477.9884.5780.8778.774.1977.0979.4480.1447.4119.2728.7619.68
GPT-5-nanoLLM Category=Proprietary2026.0162.2573.2577.8870.0278.9772.2869.6578.6280.9354.8216.7532.3841.4
Baichuan-M2-32BLLM Category=Open-Weight2026.0160.676.6180.8878.5577.5974.6173.3278.1978.0530.6719.5530.5328.69
Qwen2.5-14BLLM Category=Open-Weight2026.0160.3680.0682.0380.8879.1575.2176.8181.148133.3813.0627.3414.27
LLaMA-3.3-70BLLM Category=Open-Weight2026.0160.3461.4982.1667.6567.3166.5869.7967.2367.7864.0833.4737.0839.49
HuatuoGPT-o1-70BLLM Category=Open-Weight2026.0159.6167.2879.2466.7966.2767.5866.9666.7667.4462.0331.383439.58
LLaMA-3.1-70BLLM Category=Open-Weight2026.0159.566.2777.4567.8567.6165.8667.2368.167.8861.9632.934.7336.19
Qwen3-8B-thinkingLLM Category=Open-Weight2026.0159.0777.8582.2980.279.7378.2975.6580.280.4231.528.3319.1715.24
Gemma-3-12BLLM Category=Open-Weight2026.0158.7763.5482.1266.9267.0267.9769.4964.6766.4165.557.3134.9549.3
Qwen3-4B-thinkingLLM Category=Open-Weight2026.0157.1278.7784.5378.0576.0678.5276.7976.6776.8423.8211.911.9711.49
Claude-3.5-HaikuLLM Category=Proprietary2026.0156.8669.2878.1467.4766.4167.8969.5466.7368.7851.389.9834.0532.65
DeepSeek-R1-Qwen3-8BLLM Category=Open-Weight2026.0156.7977.7380.5875.887675.5171.2876.3676.531.5312.2112.4115.53
Qwen2.5-7BLLM Category=Open-Weight2026.0156.279.4182.9979.0677.2567.7671.5778.3677.2327.119.2713.8310.55
Qwen3-8BLLM Category=Open-Weight2026.0155.9975.9877.4972.0169.4977.1572.5570.9770.927.313.0624.820.24
Mistral-Small-3.1-24BLLM Category=Open-Weight2026.0154.2475.6983.5673.7368.5863.9564.1273.3874.1730.1512.1511.4619.92
Qwen3-4BLLM Category=Open-Weight2026.0153.4476.7882.3368.5757.7372.971.8775.473.3717.7818.5311.0114.99
Qwen3-1.7BLLM Category=Open-Weight2026.0151.5868.4475.2966.5862.1554.249.3365.1463.7927.3823.5930.6132.43
MedGemma-4BLLM Category=Open-Weight2026.0151.3558.772.26061.9259.1658.1659.6663.6644.2615.2331.831.39
Phi-4-miniLLM Category=Open-Weight2026.0151.2264.3377.5168.5266.9461.8545.1265.9468.1732.5618.4721.5423.67
Gemma-3-4BLLM Category=Open-Weight2026.0150.8464.8473.7261.3158.8958.0863.2562.6762.8145.937.5629.6321.35
Qwen2.5-3BLLM Category=Open-Weight2026.0150.5675.179.1769.7465.8959.6861.7269.7972.1512.8314.5512.2113.85
HuatuoGPT-o1-7BLLM Category=Open-Weight2026.0149.2273.7179.3271.2172.5257.1865.8772.6773.975.665.587.964.98
LLaMA-3.1-8BLLM Category=Open-Weight2026.0148.2350.5766.5661.7160.6152.757.9362.3763.2338.5323.8422.5718.14
HuatuoGPT-o1-8BLLM Category=Open-Weight2026.0142.7653.1460.7858.1759.4545.858.1759.0559.0332.635.9111.049.95
MediPhiLLM Category=Open-Weight2026.0140.6629.3374.0461.4156.3736.7335.4756.7558.7318.1927.7511.9821.2
Phi-4-mini-ReasoningLLM Category=Open-Weight2026.0139.1749.3375.6558.3460.8621.3617.640.6939.7930.4324.382526.59
Bio-Medical-LLaMA-3-8BLLM Category=Open-Weight2026.0138.7840.3857.5344.5339.4938.5733.6938.5140.332.6733.5133.0733.17
LLaMA-3.2-3BLLM Category=Open-Weight2026.0138.1730.5963.4649.8840.7836.4431.0150.4253.933.2920.822.8524.62
OpenBioLLM-70BLLM Category=Open-Weight2026.0136.0728.2372.6358.0330.4429.1931.1652.1162.2923.0212.0114.5519.19
Mistral-7B-v0.3LLM Category=Open-Weight2026.0124.4437.2213.6919.8241.5428.3124.8334.6841.2716.0912.7611.3211.76
MedReason-8BLLM Category=Open-Weight2026.0121.1141.6111.258.759.5640.8545.3323.773.668.4411.3224.2524.53
OpenBioLLM-8BLLM Category=Open-Weight2026.0113.015.5920.9311.9517.065.126.3120.1421.212.299.6710.2215.62