Benchmark Almanac

MortgageTax

Claude Opus 5 72.1% leads since July 2026
Not in model cards

Vision models read mortgage tax certificates given as images. They extract the year, parcel number and county, and compute the annualized amount due.

1,258 documents with a 20-sample public validation set. Vals archived it as saturated by September 1st, 2026.

Kind
Finance
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
Kept private
Strongest model tested
Claude Fable 5.1 #7 on the capability index
Last model added
September 2026
Scores refreshed
November 12th, 2026
88
Entries on its own leaderboard, 87 models we track

Claude Opus 5 leads with 72.1% among models released by September 2026

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

88 entries. Scroll sideways for the rest.

  1. 72.1 Claude Opus 5
  2. 70.8 Claude Fable 5.1
  3. 70.3 Claude Opus 4.7
  4. 70.0 Claude Sonnet 5
  5. 69.9 Claude Opus 4.8
  6. 69.4 Gemini 3.1 Pro
  7. 69.1 Gemini 3 Pro
  8. 68.9 Gemini 2.5 Pro (snapshot unspecified)
  9. 68.9 Claude Fable 5
  10. 68.8 GPT-5.5
  11. 68.7 Gemini 3 Flash
  12. 68.7 Claude 3.7 Sonnet
  13. 68.7 Claude Opus 4.5
  14. 68.7 Gemini 3.5 Flash-Lite
  15. 68.5 Claude Opus 4.6
  16. 68.4 MiniMax-M3
  17. 68.3 GPT-5.4
  18. 68.3 Qwen3.6 27B
  19. 68.1 Gemini 3.5 Flash
  20. 68.0 Gemini 3.1 Flash-Lite
  21. 68.0 Qwen 3.6 Plus
  22. 67.7 Claude Sonnet 4.6
  23. 67.6 Gemini 3.6 Flash
  24. 67.4 Qwen 3.5 Flash (hosted 35B-A3B)
  25. 67.3 GPT-5.6 Terra
  26. 67.3 GPT-5.6 Luna
  27. 67.3 GPT-5.6 Sol
  28. 67.2 Gemini 2.5 Pro
  29. 67.1 GPT-5.2
  30. 66.9 GPT-5 mini
  31. 66.7 Gemini 3.7 Flash
  32. 66.5 Kimi K2.5
  33. 66.3 Kimi K3
  34. 66.2 Qwen3.7-Plus
  35. 66.1 Muse Spark 1.1
  36. 65.9 GPT-4.1
  37. 65.8 Kimi K2.6
  38. 65.7 o3
  39. 65.5 GPT-4.1 mini
  40. 65.5 GPT-5
  41. 65.4 Muse Spark 1.2
  42. 65.3 Gemini 3.8 Flash
  43. 64.9 Qwen 3.8 27B
  44. 64.8 o4-mini
  45. 64.2 Grok 4.6
  46. 64.1 Claude 3.5 Sonnet
  47. 64.0 Claude Sonnet 4.5
  48. 64.0 Inkling
  49. 64.0 Qwen 3.8 Max
  50. 63.5 GPT-5.4 Mini
  51. 62.6 Gemini 2.5 Flash
  52. 62.5 Claude Sonnet 4
  53. 62.3 Inkling-Small
  54. 62.2 Claude Haiku 4.5
  55. 62.1 Magistral Small 1.2
  56. 61.8 Grok 4.5
  57. 61.4 GPT-5.1
  58. 61.4 Gemma 4 31B IT
  59. 61.2 Mistral Small 3.1
  60. 61.1 Claude Opus 4.1
  61. 61.0 GPT-4o
  62. 60.8 Qwen 3.5 Plus (hosted 397B-A17B)
  63. 60.4 Gemini 2.0 Flash
  64. 59.3 MiMo-V2.5
  65. 59.1 GPT-5.4 Nano
  66. 58.6 Claude Opus 4
  67. 58.5 Llama 4 Maverick
  68. 58.4 Gemini 2.5 Flash
  69. 57.8 Llama 4 Scout
  70. 57.5 Gemini 2.5 Flash-Lite
  71. 57.4 GPT-4o
  72. 56.8 Gemini 1.5 Pro
  73. 54.5 GPT-4o mini
  74. 53.6 GPT-5 nano
  75. 52.8 GPT-4.1 nano
  76. 52.1 Mistral Large 3
  77. 51.9 Magistral Medium 1.2
  78. 48.3 Grok 4.3
  79. 45.4 Grok 4.20
  80. 44.5 Grok 4
  81. 42.8 Gemini 1.5 Flash
  82. 42.6 Grok 4.1 Fast
  83. 42.1 Grok 4 Fast
  84. 38.8 Llama 3.2 90B
  85. 36.5 Mistral Medium 3.1
  86. 28.9 Mistral Medium 3.5
  87. 23.3 Llama 3.2 11B
  88. 3.46 Grok 2 Vision (1212)
  1. 1 Claude Opus 5 72.1%
  2. 2 Claude Fable 5.1 70.8%
  3. 3 Claude Opus 4.7 70.3%
  4. 4 Claude Sonnet 5 70%
  5. 5 Claude Opus 4.8 69.9%
  6. 6 Gemini 3.1 Pro 69.4%
  7. 7 Gemini 3 Pro 69.1%
  8. 8 Gemini 2.5 Pro (snapshot unspecified) 68.9%
  9. 9 Claude Fable 5 68.9%
  10. 10 GPT-5.5 68.8%
  11. 11 Gemini 3 Flash 68.7%
  12. 12 Claude 3.7 Sonnet non-thinking 68.7%
  13. 13 Claude Opus 4.5 non-thinking 68.7%
  14. 14 Gemini 3.5 Flash-Lite 68.7%
  15. 15 Claude Opus 4.6 thinking 68.5%
  16. 16 MiniMax-M3 68.4%
  17. 17 GPT-5.4 xhigh 68.3%
  18. 18 Qwen3.6 27B 68.3%
  19. 19 Gemini 3.5 Flash 68.1%
  20. 20 Gemini 3.1 Flash-Lite 68%
  21. 21 Qwen 3.6 Plus 68%
  22. 22 Claude Sonnet 4.6 67.7%
  23. 23 Gemini 3.6 Flash 67.6%
  24. 24 Qwen 3.5 Flash (hosted 35B-A3B) 67.4%
  25. 25 GPT-5.6 Terra 67.3%
  26. 26 GPT-5.6 Luna 67.3%
  27. 27 GPT-5.6 Sol 67.3%
  28. 28 Gemini 2.5 Pro Jun 2025 67.2%
  29. 29 GPT-5.2 67.1%
  30. 30 GPT-5 mini 66.9%
  31. 31 Gemini 3.7 Flash 66.7%
  32. 32 Kimi K2.5 thinking 66.5%
  33. 33 Kimi K3 66.3%
  34. 34 Qwen3.7-Plus 66.2%
  35. 35 Muse Spark 1.1 66.1%
  36. 36 GPT-4.1 65.9%
  37. 37 Kimi K2.6 65.8%
  38. 38 o3 65.7%
  39. 39 GPT-4.1 mini 65.5%
  40. 40 GPT-5 65.5%
  41. 41 Muse Spark 1.2 65.4%
  42. 42 Gemini 3.8 Flash 65.3%
  43. 43 Qwen 3.8 27B 64.9%
  44. 44 o4-mini 64.8%
  45. 45 Grok 4.6 64.2%
  46. 46 Claude 3.5 Sonnet 64.1%
  47. 47 Claude Sonnet 4.5 thinking 64%
  48. 48 Inkling 64%
  49. 49 Qwen 3.8 Max 64%
  50. 50 GPT-5.4 Mini 63.5%
  51. 51 Gemini 2.5 Flash Sep 2025, non-thinking 62.6%
  52. 52 Claude Sonnet 4 non-thinking 62.5%
  53. 53 Inkling-Small 62.3%
  54. 54 Claude Haiku 4.5 thinking 62.2%
  55. 55 Magistral Small 1.2 62.1%
  56. 56 Grok 4.5 61.8%
  57. 57 GPT-5.1 61.4%
  58. 58 Gemma 4 31B IT 61.4%
  59. 59 Mistral Small 3.1 61.2%
  60. 60 Claude Opus 4.1 non-thinking 61.1%
  61. 61 GPT-4o Aug 2024 61%
  62. 62 Qwen 3.5 Plus (hosted 397B-A17B) thinking 60.8%
  63. 63 Gemini 2.0 Flash Feb 2025 60.4%
  64. 64 MiMo-V2.5 59.3%
  65. 65 GPT-5.4 Nano 59.1%
  66. 66 Claude Opus 4 non-thinking 58.6%
  67. 67 Llama 4 Maverick 58.5%
  68. 68 Gemini 2.5 Flash Apr 2025, non-thinking 58.4%
  69. 69 Llama 4 Scout 57.8%
  70. 70 Gemini 2.5 Flash-Lite Sep 2025, thinking 57.5%
  71. 71 GPT-4o Nov 2024 57.4%
  72. 72 Gemini 1.5 Pro Sep 2024 56.8%
  73. 73 GPT-4o mini 54.5%
  74. 74 GPT-5 nano 53.6%
  75. 75 GPT-4.1 nano 52.8%
  76. 76 Mistral Large 3 52.1%
  77. 77 Magistral Medium 1.2 51.9%
  78. 78 Grok 4.3 48.3%
  79. 79 Grok 4.20 reasoning 45.4%
  80. 80 Grok 4 44.5%
  81. 81 Gemini 1.5 Flash Sep 2024 42.8%
  82. 82 Grok 4.1 Fast reasoning 42.6%
  83. 83 Grok 4 Fast reasoning 42.1%
  84. 84 Llama 3.2 90B 38.8%
  85. 85 Mistral Medium 3.1 36.5%
  86. 86 Mistral Medium 3.5 28.9%
  87. 87 Llama 3.2 11B 23.3%
  88. 88 Grok 2 Vision (1212) 3.46%

Source: Official MortgageTax leaderboard

#EntryScoreSettingDateSource
1 Claude Opus 5 72.1% Jul 2026 Official leaderboard
2 Claude Fable 5.1 70.8% Sep 2026 Official leaderboard
3 Claude Opus 4.7 70.3% Apr 2026 Official leaderboard
4 Claude Sonnet 5 70% Jun 2026 Official leaderboard
5 Claude Opus 4.8 69.9% May 2026 Official leaderboard
6 Gemini 3.1 Pro 69.4% Feb 2026 Official leaderboard
7 Gemini 3 Pro 69.1% Nov 2025 Official leaderboard
8 Gemini 2.5 Pro (snapshot unspecified) 68.9% Official leaderboard
9 Claude Fable 5 68.9% Jun 2026 Official leaderboard
10 GPT-5.5 68.8% Apr 2026 Official leaderboard
11 Gemini 3 Flash 68.7% Dec 2025 Official leaderboard
12 Claude 3.7 Sonnet 68.7% non-thinking Feb 2025 Official leaderboard
13 Claude Opus 4.5 68.7% non-thinking Nov 2025 Official leaderboard
14 Gemini 3.5 Flash-Lite 68.7% Jul 2026 Official leaderboard
15 Claude Opus 4.6 68.5% thinking Feb 2026 Official leaderboard
16 MiniMax-M3 68.4% Jun 2026 Official leaderboard
17 GPT-5.4 68.3% xhigh Mar 2026 Official leaderboard
18 Qwen3.6 27B 68.3% Apr 2026 Official leaderboard
19 Gemini 3.5 Flash 68.1% May 2026 Official leaderboard
20 Gemini 3.1 Flash-Lite 68% Mar 2026 Official leaderboard
21 Qwen 3.6 Plus 68% Mar 2026 Official leaderboard
22 Claude Sonnet 4.6 67.7% Feb 2026 Official leaderboard
23 Gemini 3.6 Flash 67.6% Jul 2026 Official leaderboard
24 Qwen 3.5 Flash (hosted 35B-A3B) 67.4% Feb 2026 Official leaderboard
25 GPT-5.6 Terra 67.3% Jul 2026 Official leaderboard
26 GPT-5.6 Luna 67.3% Jul 2026 Official leaderboard
27 GPT-5.6 Sol 67.3% Jul 2026 Official leaderboard
28 Gemini 2.5 Pro Jun 2025 67.2% Jun 2025 Official leaderboard
29 GPT-5.2 67.1% Dec 2025 Official leaderboard
30 GPT-5 mini 66.9% Aug 2025 Official leaderboard
31 Gemini 3.7 Flash 66.7% Aug 2026 Official leaderboard
32 Kimi K2.5 66.5% thinking Jan 2026 Official leaderboard
33 Kimi K3 66.3% Jul 2026 Official leaderboard
34 Qwen3.7-Plus 66.2% Jun 2026 Official leaderboard
35 Muse Spark 1.1 66.1% Jul 2026 Official leaderboard
36 GPT-4.1 65.9% Apr 2025 Official leaderboard
37 Kimi K2.6 65.8% Apr 2026 Official leaderboard
38 o3 65.7% Apr 2025 Official leaderboard
39 GPT-4.1 mini 65.5% Apr 2025 Official leaderboard
40 GPT-5 65.5% Aug 2025 Official leaderboard
41 Muse Spark 1.2 65.4% Aug 2026 Official leaderboard
42 Gemini 3.8 Flash 65.3% Sep 2026 Official leaderboard
43 Qwen 3.8 27B 64.9% Aug 2026 Official leaderboard
44 o4-mini 64.8% Apr 2025 Official leaderboard
45 Grok 4.6 64.2% Aug 2026 Official leaderboard
46 Claude 3.5 Sonnet 64.1% Jun 2024 Official leaderboard
47 Claude Sonnet 4.5 64% thinking Sep 2025 Official leaderboard
48 Inkling 64% Jul 2026 Official leaderboard
49 Qwen 3.8 Max 64% Aug 2026 Official leaderboard
50 GPT-5.4 Mini 63.5% Mar 2026 Official leaderboard
51 Gemini 2.5 Flash Sep 2025 62.6% non-thinking Sep 2025 Official leaderboard
52 Claude Sonnet 4 62.5% non-thinking May 2025 Official leaderboard
53 Inkling-Small 62.3% Jul 2026 Official leaderboard
54 Claude Haiku 4.5 62.2% thinking Oct 2025 Official leaderboard
55 Magistral Small 1.2 62.1% Sep 2025 Official leaderboard
56 Grok 4.5 61.8% Jul 2026 Official leaderboard
57 GPT-5.1 61.4% Nov 2025 Official leaderboard
58 Gemma 4 31B IT 61.4% Apr 2026 Official leaderboard
59 Mistral Small 3.1 61.2% Mar 2025 Official leaderboard
60 Claude Opus 4.1 61.1% non-thinking Aug 2025 Official leaderboard
61 GPT-4o Aug 2024 61% Aug 2024 Official leaderboard
62 Qwen 3.5 Plus (hosted 397B-A17B) 60.8% thinking Feb 2026 Official leaderboard
63 Gemini 2.0 Flash Feb 2025 60.4% Feb 2025 Official leaderboard
64 MiMo-V2.5 59.3% Apr 2026 Official leaderboard
65 GPT-5.4 Nano 59.1% Mar 2026 Official leaderboard
66 Claude Opus 4 58.6% non-thinking May 2025 Official leaderboard
67 Llama 4 Maverick 58.5% Apr 2025 Official leaderboard
68 Gemini 2.5 Flash Apr 2025 58.4% non-thinking Apr 2025 Official leaderboard
69 Llama 4 Scout 57.8% Apr 2025 Official leaderboard
70 Gemini 2.5 Flash-Lite Sep 2025 57.5% thinking Sep 2025 Official leaderboard
71 GPT-4o Nov 2024 57.4% Nov 2024 Official leaderboard
72 Gemini 1.5 Pro Sep 2024 56.8% Sep 2024 Official leaderboard
73 GPT-4o mini 54.5% Jul 2024 Official leaderboard
74 GPT-5 nano 53.6% Aug 2025 Official leaderboard
75 GPT-4.1 nano 52.8% Apr 2025 Official leaderboard
76 Mistral Large 3 52.1% Dec 2025 Official leaderboard
77 Magistral Medium 1.2 51.9% Sep 2025 Official leaderboard
78 Grok 4.3 48.3% Apr 2026 Official leaderboard
79 Grok 4.20 45.4% reasoning Feb 2026 Official leaderboard
80 Grok 4 44.5% Jul 2025 Official leaderboard
81 Gemini 1.5 Flash Sep 2024 42.8% Aug 2024 Official leaderboard
82 Grok 4.1 Fast 42.6% reasoning Nov 2025 Official leaderboard
83 Grok 4 Fast 42.1% reasoning Sep 2025 Official leaderboard
84 Llama 3.2 90B 38.8% Sep 2024 Official leaderboard
85 Mistral Medium 3.1 36.5% Aug 2025 Official leaderboard
86 Mistral Medium 3.5 28.9% Apr 2026 Official leaderboard
87 Llama 3.2 11B 23.3% Sep 2024 Official leaderboard
88 Grok 2 Vision (1212) 3.46% Dec 2024 Official leaderboard

The best score, 72.1%, costs $0.07 a task

Runs on the cost frontier score higher than any run that's cheaper. Qwen 3.5 Flash (hosted 35B-A3B) comes within 4.7 points of the best for $0.002 a task, 34 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Google DeepMind Meta Mistral AI Qwen Anthropic Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.00001 $0.0001 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Claude Opus 5 Gemini 3.1 Pro Gemini 3 Flash Qwen 3.5 Flash (hosted 35B-A3B) Gemini 2.5 Flash, non-thinking Gemini 1.5 Flash Llama 3.2 11B 0% 20% 40% 60% 80% 100% $0.00001 $0.0001 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Claude Opus 5 Gemini 3.1 Flash-Lite

Source: Official MortgageTax leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Opus 5 72.1% $0.07 405
Claude Fable 5.1 70.8% $0.17 898
Claude Opus 4.7 70.3% $0.08 846
Claude Sonnet 5 70% $0.08 2,787
Claude Opus 4.8 69.9% $0.11 1,697
Gemini 3.1 Pro 69.4% $0.02 1,453
Gemini 3 Pro 69.1% $0.04 2,928
Claude Fable 5 68.9% $0.17 948
GPT-5.5 68.8% $0.07 1,303
Gemini 3 Flash 68.7% $0.007 1,988
Claude 3.7 Sonnet non-thinking 68.7% $0.02 212
Claude Opus 4.5 non-thinking 68.7% $0.09 264
Gemini 3.5 Flash-Lite 68.7% $0.004 1,357
Claude Opus 4.6 thinking 68.5% $0.06 1,457
MiniMax-M3 68.4% $0.008 985
GPT-5.4 xhigh 68.3% $0.10 2,873
Qwen3.6 27B 68.3% $0.02 3,598
Gemini 3.5 Flash 68.1% $0.02 1,468
Gemini 3.1 Flash-Lite 68% $0.003 1,389
Qwen 3.6 Plus 68% $0.01 3,393
Claude Sonnet 4.6 67.7% $0.04 1,976
Claude Opus 4.5 thinking 67.7% $0.18 1,403
Gemini 3.6 Flash 67.6% $0.02 2,001
Qwen 3.5 Flash (hosted 35B-A3B) 67.4% $0.002 3,748
GPT-5.6 Terra 67.3% $0.02 362
GPT-5.6 Luna 67.3% $0.005 2,461
GPT-5.6 Sol 67.3% $0.07 835
Gemini 2.5 Pro Jun 2025 67.2% $0.004 237
GPT-5.2 67.1% $0.05 5,933
GPT-5 mini 66.9% $0.004 1,672
Claude 3.7 Sonnet thinking 66.8% $0.02 730
Gemini 3.7 Flash 66.7% $0.01 856
Kimi K2.5 thinking 66.5% $0.01 3,033
Kimi K3 66.3% $0.04 2,209
Qwen3.7-Plus 66.2% $0.008 3,120
Muse Spark 1.1 66.1% $0.02 2,460
GPT-4.1 65.9% $0.006 178
Kimi K2.6 65.8% $0.03 4,865
o3 65.7% $0.01 709
GPT-4.1 mini 65.5% $0.003 156
GPT-5 65.5% $0.03 2,593
Muse Spark 1.2 65.4% $0.03 3,349
Gemini 3.8 Flash 65.3% $0.05 5,642
Qwen 3.8 27B 64.9% $0.01 2,762
o4-mini 64.8% $0.01 964
Grok 4.6 64.2% $0.01 447
Claude 3.5 Sonnet 64.1% $0.02 164
Claude Sonnet 4.5 thinking 64% $0.05 2,627
Inkling 64% $0.06 4,106
Qwen 3.8 Max 64% $0.03 2,410
GPT-5.4 Mini 63.5% $0.04 8,736
Gemini 2.5 Flash Sep 2025 non-thinking 62.6% $0.001 1,507
Claude Sonnet 4 non-thinking 62.5% $0.02 223
Inkling-Small 62.3% $0.01 8,449
Claude Haiku 4.5 thinking 62.2% $0.02 3,302
Magistral Small 1.2 62.1% $0.004 1,045
Gemini 2.5 Flash Sep 2025 thinking 61.9% $0.001 1,507
Grok 4.5 61.8% $0.01 685
GPT-5.1 61.4% $0.03 2,402
Gemma 4 31B IT 61.4% 1,355
Mistral Small 3.1 61.2% $0.0005 169
Claude Opus 4.1 non-thinking 61.1% $0.09 335
GPT-4o Aug 2024 61% $0.007 130
Qwen 3.5 Plus (hosted 397B-A17B) thinking 60.8% $0.01 3,408
Gemini 2.0 Flash Feb 2025 60.4% $0.0001 188
Gemini 2.0 Flash Feb 2025 59.7% $0.0003 163
MiMo-V2.5 59.3% $0.002 1,869
GPT-5.4 Nano 59.1% $0.003 875
Claude Opus 4 non-thinking 58.6% $0.09 335
Llama 4 Maverick 58.5% $0.0008 176
Gemini 2.5 Flash Apr 2025 non-thinking 58.4% $0.002 668
Llama 4 Scout 57.8% $0.0006 140
Gemini 2.5 Flash-Lite Sep 2025 thinking 57.5% $0.0003 2,009
Gemini 2.5 Flash Apr 2025 thinking 57.5% $0.004 1,519
GPT-4o Nov 2024 57.4% $0.007 148
Gemini 1.5 Pro Sep 2024 56.8% $0.002 152
Claude Opus 4.1 thinking 56.1% $0.14 964
Gemini 2.5 Flash-Lite Sep 2025 non-thinking 55.8% $0.0005 688
GPT-4o mini 54.5% $0.0008 112
GPT-5 nano 53.6% $0.002 5,229
GPT-4.1 nano 52.8% $0.001 135
Mistral Large 3 52.1% $0.003 211
Magistral Medium 1.2 51.9% $0.02 1,661
Claude Sonnet 4 thinking 49.9% $0.05 2,637
Grok 4.3 48.3% $0.01 2,536
Grok 4.20 reasoning 45.4% $0.02 2,041
Grok 4 44.5% $0.09 3,864
Gemini 1.5 Flash Sep 2024 42.8% $0.0001 146
Grok 4.1 Fast reasoning 42.6% $0.002 2,972
Grok 4 Fast reasoning 42.1% $0.005 7,147
Llama 3.2 90B 38.8% $0.0006 134
Mistral Medium 3.1 36.5% $0.003 179
Grok 4.1 Fast non-reasoning 34.3% $0.001 163
Mistral Medium 3.5 28.9% $0.02 2,053
Grok 4 Fast non-reasoning 25.3% $0.003 5,023
Llama 3.2 11B 23.3% $0.00009 160
Grok 2 Vision (1212) 3.46% $0.004 178

6 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic Google DeepMind
Own leaderboard Not tested since Sep 2026
Claude Opus 5 72.1%

Source: Official MortgageTax leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2024 2025 2026 Near the ceiling (85%) Claude Opus 5 Gemini 3.1 Pro Claude 3.7 Sonnet Claude 3.5 Sonnet 0% 20% 40% 60% 80% 100% 2024 2025 2026 Near the ceiling (85%) Claude Opus 5 Claude 3.5 Sonnet

Source: Official MortgageTax leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Law, finance and medicine

All 179 in Law, finance and medicine
  • MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy. Qwen 3.8 Max 80.4%
  • HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
  • HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
  • FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy. Ling-3.1-flash 81.7%
  • KBL In use Models answer Korean legal knowledge and reasoning tasks and Korean bar exam questions. It has 7 knowledge tasks, 4 reasoning tasks and 2,510 bar exam items. Solar Pro 4 77.5%
  • KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. Solar Pro 4 93.2%