Vals AI

MedCode

Can models support the medical billing process?

Not in index
Healthcare
Source ↗

Models106

Top result63.6%Claude Opus 5

Top-3 spread4.8 pts

Updated29 Oct 2026

Result and cost

105 of 106 results

Results

106 results

#ModelResultCostTime

01Claude Opus 563.6% ±2.0$0.15725 s

02Gemini 3.1 Pro Preview59.1% ±2.0$0.02539 s

03Gemini 4 Argon58.8% ±2.1$0.13780 s

04Claude Fable 556.1% ±2.2$0.5912 min

05Gemini 3 Flash Preview55.9% ±2.1$0.006244 s

06Gemini 3.5 Flash55.8% ±2.1$0.07425 s

07Claude Opus 4.754.9% ±2.2$0.22654 s

08Claude Fable 5.153.5% ±2.2$1.124 min

09Gemini 3.7 Flash53.4% ±2.1$0.0389.2 s

10Claude Opus 4.853.2% ±2.2$0.3512 min

10Gemini 3.6 Flash53.2% ±2.2$0.04417 s

12Claude Sonnet 5.552.9% ±2.1$0.3924 min

13GPT-5.152.7% ±2.2$0.01455 s

14Gemini 3 Pro52.2% ±2.1$0.02856 s

15Claude Haiku 5.551.5% ±2.2$0.0324 min

16Muse Spark51.3% ±2.2$0.00532 min

17Gemini 2.5 Pro50.6% ±2.1$0.01527 s

18Muse Wonder Full49.9% ±2.2$0.2473 min

19Claude Opus 5.549.8% ±2.3$0.6344 min

20GPT-5.249.7% ±2.3$0.0193 min

21GPT-549.6% ±2.1$0.04658 s

21Grok 4.749.6% ±2.2$0.1054 min

23Kimi K349.4% ±2.2$0.09437 s

24Muse Spark 1.249.3% ±2.2$0.03960 s

25Claude Opus 4.5 Thinking49.2% ±2.0$0.09661 s

26Claude Opus 4.6 (Adaptive)49.1% ±2.1$0.2443 min

26GPT-5.549.1% ±2.2$0.1613 min

28GPT-6.1 Sol48.8% ±2.1$0.0852 min

29GPT-6 Astra48.5% ±2.1$0.4512 min

30Claude Opus 4.648.2% ±2.0$0.00624.1 s

31Gemini 3.8 Flash48.1% ±2.2$0.01843 s

32Gemini 3.1 Flash Lite Preview47.6% ±2.1$0.0028.6 s

33Claude Sonnet 547.5% ±2.3$0.2792 min

34o347.3% ±2.2$0.0318 s

35Claude Opus 4.1 Thinking47.2% ±2.1$0.26933 s

36GPT-6 Sol47.1% ±2.1$0.08663 s

37MiniMax M346.3% ±2.1$0.01263 s

38Claude Opus 4.545.2% ±1.9$0.00685.0 s

39MiMo-V2.6-Pro45.0% ±2.1$0.00953 min

40Grok 4.644.7% ±2.3$0.052 min

40GPT-6 Luna44.7% ±2.3$0.00732 min

42Claude Sonnet 4.5 Thinking44.1% ±2.0$0.10174 s

43GPT-5.6 Sol44.0% ±2.3$0.2812 min

44Gemini 3.5 Flash-Lite43.5% ±2.0$0.00816.0 s

45GPT-5.6 Terra43.4% ±2.2$0.04718 s

46Grok 4.543.3% ±2.3$0.04860 s

47Hy4 preview43.2% ±2.1$0.0627 min

48GPT-5 mini43.0% ±2.0$0.005628 s

49GLM-5.342.9% ±2.1$0.0823 min

50DeepSeek V4 Pro 081342.5% ±2.2$0.0613 min

51GPT-5.6 Luna42.4% ±2.3$0.01681 s

52GLM-5.141.6% ±2.1$0.02478 s

53DeepSeek V4 Flash 073141.4% ±2.1$0.022 min

53Claude Opus 4.141.4% ±2.0$0.20613 s

55GPT-5.441.3% ±2.1$0.2123 min

56Inkling41.2% ±2.2$0.1273 min

56DeepSeek V4.1 Flash 101741.2% ±2.0$0.01235 s

58MiMo-V2.6-Flash41.1% ±2.0$0.00292 min

59GPT-5.4 nano41.0% ±2.3$0.000848.0 s

60GLM-5.240.8% ±2.2$0.0452 min

61Mistral Large 440.7% ±2.2$0.02169 s

61Qwen3.8 Max40.7% ±2.0$0.1216 min

63Claude Sonnet 4.540.6% ±2.0$0.04212 s

64Gemini 2.5 Flash (Preview)40.5% ±1.9$0.003713 s

64DeepSeek V4 Pro 042340.5% ±2.1$0.0616 min

66Gemini 2.5 Flash Thinking40.4% ±2.0$0.003723 s

67Gemini 2.5 Flash Preview Thinking40.3% ±1.9$0.003716 s

68Kimi K2.640.1% ±2.0$0.0415 min

69Kimi K2.5 Thinking39.3% ±2.1$0.01775 s

70Qwen3.7 Max38.8% ±2.2$0.04229 s

71Gemini 2.5 Flash38.4% ±1.9$0.003722 s

72Grok 438.1% ±2.2$0.03489 s

72Grok 4.338.1% ±2.1$0.02244 s

74Inkling-Small37.9% ±2.2$0.0173 min

75Grok 4 Fast (Reasoning)37.4% ±1.9$0.002118 s

76Qwen3.6 Plus36.9% ±2.0$0.01656 s

77Llama4 Maverick Instruct Basic36.5% ±2.0$0.002921 s

78Claude Sonnet 4 Thinking35.0% ±1.9$0.0740 s

79MiniMax M2.734.4% ±2.0$0.007430 s

80Gemini 2.5 Flash Lite Preview Thinking34.2% ±1.7$0.001210 s

81MiniMax M2.134.1% ±1.9—20 s

82Claude Sonnet 433.9% ±1.9$0.0397.3 s

83o4-mini33.8% ±2.0$0.01821 s

83Mistral Medium 3.533.8% ±1.1$0.05335 s

85Qwen3.5 Flash33.0% ±1.8$0.003963 s

86GLM-4.732.8% ±2.0$0.00672 min

87Claude Haiku 4.5 Thinking32.7% ±2.0$0.0234 s

88MiMo-V2.5-Pro32.5% ±1.9$0.006738 s

89Ling 3.0 Flash32.3% ±1.9$0.00169.6 s

90Grok 4.20 (Reasoning)32.2% ±2.1$0.03617 s

91MiMo-V2.531.9% ±2.0$0.002218 s

92Qwen3 VL Plus31.7% ±1.8$0.002510.0 s

93Qwen3 Max31.4% ±1.9$0.0153 min

94Mercury 2.531.3% ±2.0$0.00457.9 s

95GPT-5 nano30.4% ±1.9$0.001730 s

96Grok 4 Fast Non Reasoning30.0% ±2.0$0.002118 s

97Ling 3.0 Flash Af Rc329.3% ±1.9$0.001431 s

98Qwen3.8-27B28.7% ±2.0$0.0589 s

99Grok 4.1 Fast Non Reasoning28.3% ±1.9$0.00224.5 s

100Grok 4.1 Fast (Reasoning)28.1% ±2.0$0.002147 s

101Gemini 2.5 Flash-Lite27.1% ±1.8$0.00135.7 s

101Gemini 2.5 Flash Lite Preview27.1% ±1.9$0.00146.2 s

103Llama 4 Scout 17B 16E Instruct23.3% ±1.7$0.002211 s

104Laguna M.123.1% ±1.7$0.00371 s

105Laguna XS.221.3% ±1.7$0.001433 s

106Command A+19.7% ±1.8$0.0562 min