List your company

Medical Question Answering on MedExpQA

86.19Overall AccuracyGemini-2.5-Flash
13.410832.305451.270.0946Jan 5, 2026Jan 10, 2026Jan 15, 2026Jan 21, 2026Jan 26, 2026Jan 31, 2026Feb 6, 2026

Evaluation results

MethodLinks
Gemini-2.5-FlashCategory=Proprietary2026.0186.1985.928888.9688.6487.6886.0888.4888.4888.9677.7683.0482.24—
o4-miniCategory=Proprietary2026.0182.9984.1688.4890.0888.6487.0485.4488.888.6487.8444.9679.0482.72—
GPT-5Category=Proprietary2026.0182.6384.9687.287.5287.6885.9286.486.7286.2486.7256.9673.2881.92—
DeepSeek-R1Category=Open-Weight2026.0182.2584.9687.6888.3287.848878.7287.5288.6484.1664.871.5274.88—
gpt-oss-120BCategory=Open-Weight2026.0181.9186.488.1688.6490.2487.0484.968887.6878.0855.274.5673.92—
Claude-4.0-SonnetCategory=Proprietary2026.0180.6583.0487.0488.1686.8883.6887.0488.1688.328056.3268.9670.24—
LLaMA-4-MaverickCategory=Open-Weight2026.0180.1783.3686.2488.1686.8883.3682.8888.1687.6880.4854.7267.6872.48—
GPT-4.1Category=Proprietary2026.0179.8484.328487.3684.886.7281.1288.1685.2884.9652.6464.873.92—
MA-RAG-extBackbone=Qwen3-8B, Ranking Agent=extrinsic verification2026.0278.4—————————————
GPT-4oCategory=Proprietary2026.0176.8583.285.4487.0487.5282.8882.485.7685.4482.0836.1652.4871.84—
GPT-5-miniCategory=Proprietary2026.0176.11808485.685.7682.8880.3285.4484.488029.9261.673.28—
DeepSeek-V3Category=Open-Weight2026.0175.9682.5684.4886.0882.484.9680.9684.4887.3676.9647.3654.5659.36—
TC-RAGBackbone=Qwen3-8B2026.0275.2—————————————
GPT-4.1-miniCategory=Proprietary2026.0174.7980.3286.0885.9286.482.0880.4885.1284.6475.8425.4456.6468.48—
Multi-RefineBackbone=Qwen3-8B2026.0273.6—————————————
SR-RAGBackbone=Qwen3-8B2026.0272.8—————————————
MA-RAG-intBackbone=Qwen3-8B, Ranking Agent=intrinsic uncertainty2026.0272.8—————————————
gpt-oss-20BCategory=Open-Weight2026.0172.3181.2876.9682.0884.3280.876.1682.481.1268.6428.4858.5666.88—
CoTBackbone=Qwen3-8B2026.0272—————————————
FLAREBackbone=Qwen3-8B2026.0271.2—————————————
SCBackbone=Qwen3-8B2026.0270.4—————————————
FL-RAGBackbone=Qwen3-8B2026.0269.6—————————————
LLaMA-4-ScoutCategory=Open-Weight2026.0169.0475.283.279.281.2872.1672.878.5677.126844.3238.2458.4—
MedGemma-27BCategory=Open-Weight2026.0169.0375.0482.568080.874.7274.0880.1680.167617.645.661.6—
Phi-4-ReasoningCategory=Open-Weight2026.0168.0479.5285.685.4484.1683.5275.5274.08847217.7644.1630.72—
HuatuoGPT-o1-72BCategory=Open-Weight2026.0167.5579.5280.3284.1683.0480.876.4885.68461.9239.683619.04—
Qwen3-8BBackbone=Qwen3-8B2026.0267.2—————————————
Llama-3.1-8BBackbone=Llama-3.1-8B2026.0267.2—————————————
FS-RAGBackbone=Qwen3-8B2026.0267.2—————————————
HuatuoGPT-o1-70BCategory=Open-Weight2026.0166.7162.0880.1678.8879.846472.4879.3680.870.8833.9243.8454.24—
LLaMA-3.3-70BCategory=Open-Weight2026.0166.5166.0882.481.4480.4858.7266.8878.5681.4467.5243.0442.7248.8—
LLaMA-3.1-70BCategory=Open-Weight2026.0166.4873.680.6478.8878.0872.4866.5676.4877.2867.8443.6838.5643.68—
UltraMedical-3.1-8BBackbone=UltraMedical-3.1-8B2026.0266.4—————————————
Claude-3.5-HaikuCategory=Proprietary2026.0164.6372.6478.48075.3674.47280.88049.7633.7643.235.2—
Qwen2.5-72BCategory=Open-Weight2026.0164.5976.4878.8879.6877.675.5270.0880.4879.250.2442.2428.9635.68—
QwQ-32BCategory=Open-Weight2026.0163.8481.9283.6884.4882.5679.0468.9684.1683.686417.9215.8419.84—
HuatuoGPT-o1-8BBackbone=HuatuoGPT-o1-8B2026.0263.2—————————————
GPT-4o-miniCategory=Proprietary2026.0162.7568.1675.5278.8873.2870.2462.8876.3274.7261.7627.8438.0845.28—
Gemma-3-27BCategory=Open-Weight2026.0161.7967.8474.7271.3674.2466.8864.1672.3272.9662.416.1641.7656.64—
Qwen3-14B-thinkingCategory=Open-Weight2026.0161.0878.7279.6879.5281.7680.6473.680.1677.9257.618.0811.6813.6—
GPT-4.1-nanoCategory=Proprietary2026.0159.666.0878.0873.4472.9661.9257.1274.5671.685229.4435.242.72—
Baichuan-M2-32BCategory=Open-Weight2026.0159.3379.3683.0476.879.5277.1267.528074.5626.5620.6423.0423.84—
Phi-4Category=Open-Weight2026.0154.5759.0479.269.674.5662.45271.3669.4441.4419.0430.5626.24—
Qwen3-14BCategory=Open-Weight2026.0154.1773.1274.0873.2872.867.8458.8875.5273.4438.2413.1213.9215.84—
Qwen3-8B-thinkingCategory=Open-Weight2026.0154.1173.2876.6473.2874.7270.8867.3674.2474.7226.0814.7213.2810.08—
GPT-5-nanoCategory=Proprietary2026.0153.851.846460.9665.926852.6464.4863.6857.1217.7639.240—
Qwen2.5-14BCategory=Open-Weight2026.0152.9267.5273.286069.2862.0855.366867.3631.8420.3228.1631.84—
Gemma-3-12BCategory=Open-Weight2026.0152.8461.926864.865.4455.3654.7266.2465.7653.610.0827.0441.12—
Mistral-Small-3.1-24BCategory=Open-Weight2026.0152.2868.9678.2471.3676.1666.8854.2472.9672.4830.7210.8812.4812—
DeepSeek-R1-Qwen3-8BCategory=Open-Weight2026.0150.0870.2473.7666.566463.8463.6866.5666.2428.3211.6812.9613.12—
Qwen3-4B-thinkingCategory=Open-Weight2026.0148.3766.087266.2466.0862.45666.5663.5221.1218.0813.68.8—
Qwen3-8BCategory=Open-Weight2026.0145.8163.6870.2458.8863.3658.5653.4461.4460.3216.9611.5222.249.12—
MedGemma-4BCategory=Open-Weight2026.0144.774866.5655.6860.6445.1241.4454.5654.2441.617.1221.7630.56—
Qwen2.5-7BCategory=Open-Weight2026.0143.7557.7664.859.5252.3252.9648.1655.254.0831.214.2420.1614.56—
Qwen3-4BCategory=Open-Weight2026.0143.2361.9266.8856.1661.2853.1247.365656.9617.2815.5216.1610.08—
HuatuoGPT-o1-8BCategory=Open-Weight2026.0142.9655.5263.8460.3257.2847.5242.5657.7658.8840.6411.211.688.32—
HuatuoGPT-o1-7BCategory=Open-Weight2026.0142.4859.258.0862.2463.5256.4854.7257.9257.7610.7211.689.767.68—
LLaMA-3.1-8BCategory=Open-Weight2026.0138.9644.9668.6452.3250.7241.630.2455.0447.8430.5621.9213.1210.56—
Bio-Medical-LLaMA-3-8BCategory=Open-Weight2026.0138.7543.8462.8846.448.1641.7631.524042.8830.8824.827.3624.48—
OpenBioLLM-70BCategory=Open-Weight2026.0135.9725.7670.7263.6840.826.7221.4447.258.5629.1210.7214.2422.72—
Gemma-3-4BCategory=Open-Weight2026.0135.6942.8852.9647.6845.7642.0833.644.9644.9635.5210.7215.3611.84—
Qwen3-1.7BCategory=Open-Weight2026.0135.3249.2851.364441.2835.5233.4441.4441.9215.8422.425.7621.6—
Qwen2.5-3BCategory=Open-Weight2026.0134.5350.449.2846.8843.684436.1643.8444.814.8813.1214.8812.48—
LLaMA-3.2-3BCategory=Open-Weight2026.0131.9339.8458.8845.639.5237.4422.8843.8427.8425.7612.6416.3212.64—
MediPhiCategory=Open-Weight2026.0131.4728.9653.2844.1650.5624.1629.1238.7239.5213.4417.7617.2820.64—
Phi-4-mini-ReasoningCategory=Open-Weight2026.0131.3228.9661.1246.2449.624.815.6835.239.042418.416.3216.48—
Phi-4-miniCategory=Open-Weight2026.0131.2134.5658.0836.840.835.842835.6834.0822.8814.5616.6416.64—
MedReason-8BCategory=Open-Weight2026.0123.5346.5654.5616.9616.6439.843218.421.769.769.69.66.72—
Mistral-7B-v0.3Category=Open-Weight2026.0121.828.4832.6415.5239.0419.3619.5219.230.416.9618.5611.210.72—
OpenBioLLM-8BCategory=Open-Weight2026.0116.2117.4430.2414.5624.89.2810.424.821.6126.569.1213.76—
HuatuoGPTfamily=HuatuoGPT, size=8B2025.12——67—————56.3————56.4
m1family=m1, size=7B2025.12——62.2—————48.1————48.6
MedReasonfamily=MedReason, size=8B2025.12——64.3—————58.4————55.1
Ourfamily=Our, size=8B2025.12——69.7—————69.7————62.2
Ourfamily=Our, size=8B, shots=2-shot2025.12——68.1—————65————64