Tax Agent Bench
The official leaderboard hasn’t scored a model released after GPT-6.2 Sol (November 2026). Labs report their own numbers for one newer model: Inkling 2 Mini at 14.1%.
Agents research 391 expert-written US corporate tax questions with tools and submit one cited written answer. A judge grades it against a rubric and checks that citations are real.
Splits are 5 public, 193 licensable validation and 193 private test questions. Main metric is all-pass accuracy, with weighted pass as partial credit. 80 models on the board on October 29th, 2026.
- Made by
- Vals AI
- Released
- September 2026
- Kind
- Finance
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Law, Economics and business
- Language
- English
- Interaction
- Agentic
- Environment
- Browser
- Items from
- Written by experts
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents, Law and finance
- Strongest model tested
- GPT-6.2 Astra #1 on the capability index
- Last in a launch post
- November 2026
- Last model added
- November 2026
- Scores refreshed
- November 18th, 2026
Gemini 4 Hydrogen leads with 52.3% Gemini 4 Hydrogen leads with 52.3%
Best score per entry from the benchmark's own leaderboard, read on November 18th, 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. This view shows only models we track, each at its best.
Gemini 4 Hydrogen leads with 52.3%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
- 52.3
Gemini 4 Hydrogen
- 51.8
Gemini 4 Carbon
- 50.8 Claude Fable 5.1
- 49.7
Qwen3.8 Max (0902)
- 49.2
Gemini 4 Argon
- 47.1 Claude Opus 5
- 44.5 Claude Opus 5.5
- 44.4
DeepSeek V4.1 Flash 1017
- 43.3 GLM-5.3
- 43.0
Muse Wonder Full
- 42.4
Muse Spark 1.3
- 42.0 Claude Sonnet 5.5
- 40.4
Qwen4-Max
- 38.9
Inkling 2 Small
- 38.3 Claude Fable 5
- 38.2
Muse Ember
- 36.3
Muse Wonder
- 35.8 Grok 4.7
- 34.4
Tencent Hy4
- 33.7 Grok 4.6
- 33.4 Kimi K3
- 32.8
Muse Spark 1.2
- 32.6
Tencent Hy4 preview
- 32.4 MiMo-V2.6 Pro
- 32.1
MiniMax-M3.1-Flash
- 32.1
Gemini 3.8 Flash
- 32.1
Qwen 3.8 Max
- 32.1 Claude Fable 5.2
- 31.9 Claude Haiku 5.5
- 31.6 GLM-5.3-Flash
- 31.1 GPT-5.6 Sol
- 31.1
Ember-1
- 30.9
Qwen 3.8 27B
- 30.7
Mistral Large 4
- 30.4
Mistral Large 4 Preview
- 30.0 GPT-5.6 Terra
- 30.0 Claude Opus 4.8
- 29.4 Claude Sonnet 5
- 28.5 MiMo-V2.6 Flash
- 28.1
DeepSeek V4 Flash 0731
- 27.3
Step 5 Preview
- 26.8
DeepSeek V4 Pro 0813
- 26.6
DeepSeek V4.1 Flash
- 26.3
Muse Spark Open
- 25.8 Claude Sonnet 4.6
- 25.2
DeepSeek-V4-Pro
- 24.9 Kimi K3.1 Pro
- 24.9 Grok 4.5
- 24.8 GPT-6.2 Sol
- 24.8 GPT-5.6 Luna
- 23.7 Claude Opus 4.7
- 23.3 Hy4 Flash
- 22.8
Gemini 3.7 Flash
- 21.8 GPT-6.2 Astra
- 21.8 GPT-5.5
- 21.8 GPT-6.1 Sol
- 21.6
Gemini 3.5 Flash
- 20.7 GPT-6 Astra
- 20.6
Ling-3.0-flash-Fin
- 20.6
MiniMax-M3
- 19.9 GPT-6 Luna
- 18.2 Mercury 3
- 18.0
Gemini 3.6 Flash
- 17.1 GPT-6.1 Terra
- 15.8
Qwen3.7-Max
- 15.4
Inkling-Small
- 15.3
Inkling
- 15.0 GPT-6 Sol
- 12.4 Kimi K2.6
- 11.8
Gemini 3 Flash
- 11.6
Nemotron 3.5 Super VL
- 11.5 MiMo-V2.5-Pro
- 10.5
Qwen3.7-Plus
- 9.29
Gemini 3.1 Pro
- 8.81 GPT-5.4 Mini
- 8.81 Beam 1.0
- 7.77 MiMo-V2.5
- 7.68
Qwen 3.6 Plus
- 7.25
Gemini 3.5 Flash-Lite
- 6.95 Grok 4.20
- 6.87
MiniMax-M2.7
- 6.18 Grok 4.3
- 5.86 Claude Haiku 4.5
- 4.97 GPT-5.4 Nano
- 4.48
Mistral Medium 3.5
- 3.11
Gemini 3.1 Flash-Lite
- 2.59
Nemotron 3.5 Lightning 30B-A3B
- 2.49 Mercury 2.5
- 1
Gemini 4 Hydrogen 52.3%
- 2
Gemini 4 Carbon 51.8%
- 3 Claude Fable 5.1 50.8%
- 4
Qwen3.8 Max (0902) 49.7%
- 5
Gemini 4 Argon 49.2%
- 6 Claude Opus 5 47.1%
- 7 Claude Opus 5.5 44.5%
- 8
DeepSeek V4.1 Flash 1017 44.4%
- 9 GLM-5.3 43.3%
- 10
Muse Wonder Full 43%
- 11
Muse Spark 1.3 max 42.4%
- 12 Claude Sonnet 5.5 42%
- 13
Qwen4-Max 40.4%
- 14
Inkling 2 Small 38.9%
- 15 Claude Fable 5 38.3%
- 16
Muse Ember 38.2%
- 17
Muse Wonder 36.3%
- 18 Grok 4.7 35.8%
- 19
Tencent Hy4 34.4%
- 20 Grok 4.6 33.7%
- 21 Kimi K3 33.4%
- 22
Muse Spark 1.2 32.8%
- 23
Tencent Hy4 preview 32.6%
- 24 MiMo-V2.6 Pro 32.4%
- 25
MiniMax-M3.1-Flash 32.1%
- 26
Gemini 3.8 Flash 32.1%
- 27
Qwen 3.8 Max 32.1%
- 28 Claude Fable 5.2 32.1%
- 29 Claude Haiku 5.5 31.9%
- 30 GLM-5.3-Flash 31.6%
- 31 GPT-5.6 Sol 31.1%
- 32
Ember-1 31.1%
- 33
Qwen 3.8 27B 30.9%
- 34
Mistral Large 4 30.7%
- 35
Mistral Large 4 Preview 30.4%
- 36 GPT-5.6 Terra 30%
- 37 Claude Opus 4.8 30%
- 38 Claude Sonnet 5 29.4%
- 39 MiMo-V2.6 Flash 28.5%
- 40
DeepSeek V4 Flash 0731 28.1%
- 41
Step 5 Preview 27.3%
- 42
DeepSeek V4 Pro 0813 26.8%
- 43
DeepSeek V4.1 Flash 26.6%
- 44
Muse Spark Open 26.3%
- 45 Claude Sonnet 4.6 25.8%
- 46
DeepSeek-V4-Pro 25.2%
- 47 Kimi K3.1 Pro 24.9%
- 48 Grok 4.5 24.9%
- 49 GPT-6.2 Sol 24.8%
- 50 GPT-5.6 Luna 24.8%
- 51 Claude Opus 4.7 23.7%
- 52 Hy4 Flash 23.3%
- 53
Gemini 3.7 Flash 22.8%
- 54 GPT-6.2 Astra 21.8%
- 55 GPT-5.5 21.8%
- 56 GPT-6.1 Sol 21.8%
- 57
Gemini 3.5 Flash 21.6%
- 58 GPT-6 Astra 20.7%
- 59
Ling-3.0-flash-Fin 20.6%
- 60
MiniMax-M3 20.6%
- 61 GPT-6 Luna 19.9%
- 62 Mercury 3 18.2%
- 63
Gemini 3.6 Flash 18%
- 64 GPT-6.1 Terra 17.1%
- 65
Qwen3.7-Max 15.8%
- 66
Inkling-Small 15.4%
- 67
Inkling 15.3%
- 68 GPT-6 Sol 15%
- 69 Kimi K2.6 12.4%
- 70
Gemini 3 Flash 11.8%
- 71
Nemotron 3.5 Super VL 11.6%
- 72 MiMo-V2.5-Pro 11.5%
- 73
Qwen3.7-Plus 10.5%
- 74
Gemini 3.1 Pro 9.29%
- 75 GPT-5.4 Mini 8.81%
- 76 Beam 1.0 8.81%
- 77 MiMo-V2.5 7.77%
- 78
Qwen 3.6 Plus 7.68%
- 79
Gemini 3.5 Flash-Lite 7.25%
- 80 Grok 4.20 reasoning 6.95%
- 81
MiniMax-M2.7 6.87%
- 82 Grok 4.3 6.18%
- 83 Claude Haiku 4.5 thinking 5.86%
- 84 GPT-5.4 Nano 4.97%
- 85
Mistral Medium 3.5 4.48%
- 86
Gemini 3.1 Flash-Lite 3.11%
- 87
Nemotron 3.5 Lightning 30B-A3B 2.59%
- 88 Mercury 2.5 2.49%
Source: Official Tax Agent Bench leaderboard
- 52.3
Gemini 4 Hydrogen
- 51.8
Gemini 4 Carbon
- 50.8 Claude Fable 5.1
- 49.7
Qwen3.8 Max (0902)
- 49.2
Gemini 4 Argon
- 47.1 Claude Opus 5
- 44.5 Claude Opus 5.5
- 44.4
DeepSeek V4.1 Flash 1017
- 43.3 GLM-5.3
- 43.0
Muse Wonder Full
- 42.4
Muse Spark 1.3
- 42.0 Claude Sonnet 5.5
- 40.4
Qwen4-Max
- 38.9
Inkling 2 Small
- 38.3 Claude Fable 5
- 38.2
Muse Ember
- 36.3
Muse Wonder
- 35.8 Grok 4.7
- 34.4
Tencent Hy4
- 33.7 Grok 4.6
- 33.4 Kimi K3
- 32.8
Muse Spark 1.2
- 32.6
Tencent Hy4 preview
- 32.4 MiMo-V2.6 Pro
- 32.1
MiniMax-M3.1-Flash
- 32.1
Gemini 3.8 Flash
- 32.1
Qwen 3.8 Max
- 32.1 Claude Fable 5.2
- 31.9 Claude Haiku 5.5
- 31.6 GLM-5.3-Flash
- 31.1 GPT-5.6 Sol
- 31.1
Ember-1
- 30.9
Qwen 3.8 27B
- 30.7
Mistral Large 4
- 30.4
Mistral Large 4 Preview
- 30.0 GPT-5.6 Terra
- 30.0 Claude Opus 4.8
- 29.4 Claude Sonnet 5
- 28.5 MiMo-V2.6 Flash
- 28.1
DeepSeek V4 Flash 0731
- 27.3
Step 5 Preview
- 26.8
DeepSeek V4 Pro 0813
- 26.6
DeepSeek V4.1 Flash
- 26.3
Muse Spark Open
- 25.8 Claude Sonnet 4.6
- 25.2
DeepSeek-V4-Pro
- 24.9 Kimi K3.1 Pro
- 24.9 Grok 4.5
- 24.8 GPT-6.2 Sol
- 24.8 GPT-5.6 Luna
- 23.7 Claude Opus 4.7
- 22.8
Gemini 3.7 Flash
- 21.8 GPT-6.2 Astra
- 21.8 GPT-5.5
- 21.8 GPT-6.1 Sol
- 21.6
Gemini 3.5 Flash
- 20.7 GPT-6 Astra
- 20.6
Ling-3.0-flash-Fin
- 20.6
MiniMax-M3
- 19.9 GPT-6 Luna
- 18.2 Mercury 3
- 18.0
Gemini 3.6 Flash
- 17.1 GPT-6.1 Terra
- 15.8
Qwen3.7-Max
- 15.4
Inkling-Small
- 15.3
Inkling
- 15.0 GPT-6 Sol
- 12.4 Kimi K2.6
- 11.8
Gemini 3 Flash
- 11.6
Nemotron 3.5 Super VL
- 11.5 MiMo-V2.5-Pro
- 10.5
Qwen3.7-Plus
- 9.29
Gemini 3.1 Pro
- 8.81 GPT-5.4 Mini
- 8.81 Beam 1.0
- 7.77 MiMo-V2.5
- 7.68
Qwen 3.6 Plus
- 7.25
Gemini 3.5 Flash-Lite
- 6.95 Grok 4.20
- 6.87
MiniMax-M2.7
- 6.18 Grok 4.3
- 5.86 Claude Haiku 4.5
- 4.97 GPT-5.4 Nano
- 4.48
Mistral Medium 3.5
- 3.11
Gemini 3.1 Flash-Lite
- 2.59
Nemotron 3.5 Lightning 30B-A3B
- 2.49 Mercury 2.5
- 1
Gemini 4 Hydrogen 52.3%
- 2
Gemini 4 Carbon 51.8%
- 3 Claude Fable 5.1 50.8%
- 4
Qwen3.8 Max (0902) 49.7%
- 5
Gemini 4 Argon 49.2%
- 6 Claude Opus 5 47.1%
- 7 Claude Opus 5.5 44.5%
- 8
DeepSeek V4.1 Flash 1017 44.4%
- 9 GLM-5.3 43.3%
- 10
Muse Wonder Full 43%
- 11
Muse Spark 1.3 max 42.4%
- 12 Claude Sonnet 5.5 42%
- 13
Qwen4-Max 40.4%
- 14
Inkling 2 Small 38.9%
- 15 Claude Fable 5 38.3%
- 16
Muse Ember 38.2%
- 17
Muse Wonder 36.3%
- 18 Grok 4.7 35.8%
- 19
Tencent Hy4 34.4%
- 20 Grok 4.6 33.7%
- 21 Kimi K3 33.4%
- 22
Muse Spark 1.2 32.8%
- 23
Tencent Hy4 preview 32.6%
- 24 MiMo-V2.6 Pro 32.4%
- 25
MiniMax-M3.1-Flash 32.1%
- 26
Gemini 3.8 Flash 32.1%
- 27
Qwen 3.8 Max 32.1%
- 28 Claude Fable 5.2 32.1%
- 29 Claude Haiku 5.5 31.9%
- 30 GLM-5.3-Flash 31.6%
- 31 GPT-5.6 Sol 31.1%
- 32
Ember-1 31.1%
- 33
Qwen 3.8 27B 30.9%
- 34
Mistral Large 4 30.7%
- 35
Mistral Large 4 Preview 30.4%
- 36 GPT-5.6 Terra 30%
- 37 Claude Opus 4.8 30%
- 38 Claude Sonnet 5 29.4%
- 39 MiMo-V2.6 Flash 28.5%
- 40
DeepSeek V4 Flash 0731 28.1%
- 41
Step 5 Preview 27.3%
- 42
DeepSeek V4 Pro 0813 26.8%
- 43
DeepSeek V4.1 Flash 26.6%
- 44
Muse Spark Open 26.3%
- 45 Claude Sonnet 4.6 25.8%
- 46
DeepSeek-V4-Pro 25.2%
- 47 Kimi K3.1 Pro 24.9%
- 48 Grok 4.5 24.9%
- 49 GPT-6.2 Sol 24.8%
- 50 GPT-5.6 Luna 24.8%
- 51 Claude Opus 4.7 23.7%
- 52
Gemini 3.7 Flash 22.8%
- 53 GPT-6.2 Astra 21.8%
- 54 GPT-5.5 21.8%
- 55 GPT-6.1 Sol 21.8%
- 56
Gemini 3.5 Flash 21.6%
- 57 GPT-6 Astra 20.7%
- 58
Ling-3.0-flash-Fin 20.6%
- 59
MiniMax-M3 20.6%
- 60 GPT-6 Luna 19.9%
- 61 Mercury 3 18.2%
- 62
Gemini 3.6 Flash 18%
- 63 GPT-6.1 Terra 17.1%
- 64
Qwen3.7-Max 15.8%
- 65
Inkling-Small 15.4%
- 66
Inkling 15.3%
- 67 GPT-6 Sol 15%
- 68 Kimi K2.6 12.4%
- 69
Gemini 3 Flash 11.8%
- 70
Nemotron 3.5 Super VL 11.6%
- 71 MiMo-V2.5-Pro 11.5%
- 72
Qwen3.7-Plus 10.5%
- 73
Gemini 3.1 Pro 9.29%
- 74 GPT-5.4 Mini 8.81%
- 75 Beam 1.0 8.81%
- 76 MiMo-V2.5 7.77%
- 77
Qwen 3.6 Plus 7.68%
- 78
Gemini 3.5 Flash-Lite 7.25%
- 79 Grok 4.20 reasoning 6.95%
- 80
MiniMax-M2.7 6.87%
- 81 Grok 4.3 6.18%
- 82 Claude Haiku 4.5 thinking 5.86%
- 83 GPT-5.4 Nano 4.97%
- 84
Mistral Medium 3.5 4.48%
- 85
Gemini 3.1 Flash-Lite 3.11%
- 86
Nemotron 3.5 Lightning 30B-A3B 2.59%
- 87 Mercury 2.5 2.49%
Source: Official Tax Agent Bench leaderboard
- 52.3
Gemini 4 Hydrogen
- 51.8
Gemini 4 Carbon
- 50.8 Claude Fable 5.1
- 49.7
Qwen3.8 Max (0902)
- 49.2
Gemini 4 Argon
- 47.1 Claude Opus 5
- 44.5 Claude Opus 5.5
- 44.4
DeepSeek V4.1 Flash 1017
- 43.3 GLM-5.3
- 43.0
Muse Wonder Full
- 42.4
Muse Spark 1.3
- 42.0 Claude Sonnet 5.5
- 40.4
Qwen4-Max
- 38.9
Inkling 2 Small
- 38.3 Claude Fable 5
- 38.2
Muse Ember
- 36.3
Muse Wonder
- 35.8 Grok 4.7
- 34.4
Tencent Hy4
- 33.7 Grok 4.6
- 33.4 Kimi K3
- 32.8
Muse Spark 1.2
- 32.6
Tencent Hy4 preview
- 32.4 MiMo-V2.6 Pro
- 32.1
MiniMax-M3.1-Flash
- 32.1
Gemini 3.8 Flash
- 32.1
Qwen 3.8 Max
- 32.1 Claude Fable 5.2
- 31.9 Claude Haiku 5.5
- 31.6 GLM-5.3-Flash
- 31.1 GPT-5.6 Sol
- 31.1
Ember-1
- 30.9
Qwen 3.8 27B
- 30.7
Mistral Large 4
- 30.4
Mistral Large 4 Preview
- 30.0 GPT-5.6 Terra
- 30.0 Claude Opus 4.8
- 29.4 Claude Sonnet 5
- 28.5 MiMo-V2.6 Flash
- 28.1
DeepSeek V4 Flash 0731
- 27.3
Step 5 Preview
- 26.8
DeepSeek V4 Pro 0813
- 26.6
DeepSeek V4.1 Flash
- 26.3
Muse Spark Open
- 25.8 Claude Sonnet 4.6
- 25.2
DeepSeek-V4-Pro
- 24.9 Kimi K3.1 Pro
- 24.9 Grok 4.5
- 24.8 GPT-6.2 Sol
- 24.8 GPT-5.6 Luna
- 23.7 Claude Opus 4.7
- 22.8
Gemini 3.7 Flash
- 21.8 GPT-6.2 Astra
- 21.8 GPT-5.5
- 21.8 GPT-6.1 Sol
- 21.6
Gemini 3.5 Flash
- 20.7 GPT-6 Astra
- 20.6
Ling-3.0-flash-Fin
- 20.6
MiniMax-M3
- 19.9 GPT-6 Luna
- 18.2 Mercury 3
- 18.0
Gemini 3.6 Flash
- 17.1 GPT-6.1 Terra
- 15.8
Qwen3.7-Max
- 15.4
Inkling-Small
- 15.3
Inkling
- 15.0 GPT-6 Sol
- 14.1
Inkling 2 Mini
- 12.4 Kimi K2.6
- 11.8
Gemini 3 Flash
- 11.6
Nemotron 3.5 Super VL
- 11.5 MiMo-V2.5-Pro
- 10.5
Qwen3.7-Plus
- 9.29
Gemini 3.1 Pro
- 8.81 GPT-5.4 Mini
- 8.81 Beam 1.0
- 7.77 MiMo-V2.5
- 7.68
Qwen 3.6 Plus
- 7.25
Gemini 3.5 Flash-Lite
- 6.95 Grok 4.20
- 6.87
MiniMax-M2.7
- 6.18 Grok 4.3
- 5.86 Claude Haiku 4.5
- 4.97 GPT-5.4 Nano
- 4.48
Mistral Medium 3.5
- 3.11
Gemini 3.1 Flash-Lite
- 2.59
Nemotron 3.5 Lightning 30B-A3B
- 2.49 Mercury 2.5
- 1
Gemini 4 Hydrogen 52.3%
- 2
Gemini 4 Carbon 51.8%
- 3 Claude Fable 5.1 50.8%
- 4
Qwen3.8 Max (0902) 49.7%
- 5
Gemini 4 Argon 49.2%
- 6 Claude Opus 5 47.1%
- 7 Claude Opus 5.5 44.5%
- 8
DeepSeek V4.1 Flash 1017 44.4%
- 9 GLM-5.3 43.3%
- 10
Muse Wonder Full 43%
- 11
Muse Spark 1.3 max 42.4%
- 12 Claude Sonnet 5.5 42%
- 13
Qwen4-Max 40.4%
- 14
Inkling 2 Small 38.9%
- 15 Claude Fable 5 38.3%
- 16
Muse Ember 38.2%
- 17
Muse Wonder 36.3%
- 18 Grok 4.7 35.8%
- 19
Tencent Hy4 34.4%
- 20 Grok 4.6 33.7%
- 21 Kimi K3 33.4%
- 22
Muse Spark 1.2 32.8%
- 23
Tencent Hy4 preview 32.6%
- 24 MiMo-V2.6 Pro 32.4%
- 25
MiniMax-M3.1-Flash 32.1%
- 26
Gemini 3.8 Flash 32.1%
- 27
Qwen 3.8 Max 32.1%
- 28 Claude Fable 5.2 32.1%
- 29 Claude Haiku 5.5 31.9%
- 30 GLM-5.3-Flash 31.6%
- 31 GPT-5.6 Sol 31.1%
- 32
Ember-1 31.1%
- 33
Qwen 3.8 27B 30.9%
- 34
Mistral Large 4 30.7%
- 35
Mistral Large 4 Preview 30.4%
- 36 GPT-5.6 Terra 30%
- 37 Claude Opus 4.8 30%
- 38 Claude Sonnet 5 29.4%
- 39 MiMo-V2.6 Flash 28.5%
- 40
DeepSeek V4 Flash 0731 28.1%
- 41
Step 5 Preview 27.3%
- 42
DeepSeek V4 Pro 0813 26.8%
- 43
DeepSeek V4.1 Flash 26.6%
- 44
Muse Spark Open 26.3%
- 45 Claude Sonnet 4.6 25.8%
- 46
DeepSeek-V4-Pro 25.2%
- 47 Kimi K3.1 Pro 24.9%
- 48 Grok 4.5 24.9%
- 49 GPT-6.2 Sol 24.8%
- 50 GPT-5.6 Luna 24.8%
- 51 Claude Opus 4.7 23.7%
- 52
Gemini 3.7 Flash 22.8%
- 53 GPT-6.2 Astra 21.8%
- 54 GPT-5.5 21.8%
- 55 GPT-6.1 Sol 21.8%
- 56
Gemini 3.5 Flash 21.6%
- 57 GPT-6 Astra 20.7%
- 58
Ling-3.0-flash-Fin 20.6%
- 59
MiniMax-M3 20.6%
- 60 GPT-6 Luna 19.9%
- 61 Mercury 3 18.2%
- 62
Gemini 3.6 Flash 18%
- 63 GPT-6.1 Terra 17.1%
- 64
Qwen3.7-Max 15.8%
- 65
Inkling-Small 15.4%
- 66
Inkling 15.3%
- 67 GPT-6 Sol 15%
- 68
Inkling 2 Mini 14.1%
- 69 Kimi K2.6 12.4%
- 70
Gemini 3 Flash 11.8%
- 71
Nemotron 3.5 Super VL 11.6%
- 72 MiMo-V2.5-Pro 11.5%
- 73
Qwen3.7-Plus 10.5%
- 74
Gemini 3.1 Pro 9.29%
- 75 GPT-5.4 Mini 8.81%
- 76 Beam 1.0 8.81%
- 77 MiMo-V2.5 7.77%
- 78
Qwen 3.6 Plus 7.68%
- 79
Gemini 3.5 Flash-Lite 7.25%
- 80 Grok 4.20 reasoning 6.95%
- 81
MiniMax-M2.7 6.87%
- 82 Grok 4.3 6.18%
- 83 Claude Haiku 4.5 thinking 5.86%
- 84 GPT-5.4 Nano 4.97%
- 85
Mistral Medium 3.5 4.48%
- 86
Gemini 3.1 Flash-Lite 3.11%
- 87
Nemotron 3.5 Lightning 30B-A3B 2.59%
- 88 Mercury 2.5 2.49%
Sources: Official Tax Agent Bench leaderboard and labs’ model cards
| # | Entry | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 52.3% ±7.1 | Nov 2026 | Official leaderboard | |
| 2 | | 51.8% ±7.1 | Oct 2026 | Official leaderboard | |
| 3 | Claude Fable 5.1 | 50.8% ±7.1 | Sep 2026 | Official leaderboard | |
| 4 | | 49.7% ±7.1 | Sep 2026 | Official leaderboard | |
| 5 | | 49.2% ±7.1 | Sep 2026 | Official leaderboard | |
| 6 | Claude Opus 5 | 47.1% ±7.1 | Jul 2026 | Official leaderboard | |
| 7 | Claude Opus 5.5 | 44.5% ±7 | Sep 2026 | Official leaderboard | |
| 8 | | 44.4% ±7 | Oct 2026 | Official leaderboard | |
| 9 | GLM-5.3 | 43.3% ±7 | Aug 2026 | Official leaderboard | |
| 10 | | 43% ±7 | Oct 2026 | Official leaderboard | |
| 11 | | 42.4% ±6.9 | max | Sep 2026 | Official leaderboard |
| 12 | Claude Sonnet 5.5 | 42% ±7 | Sep 2026 | Official leaderboard | |
| 13 | | 40.4% ±6.9 | Nov 2026 | Official leaderboard | |
| 14 | | 38.9% ±6.4 | Nov 2026 | Official leaderboard | |
| 15 | Claude Fable 5 | 38.3% ±6.9 | Jun 2026 | Official leaderboard | |
| 16 | | 38.2% ±6.9 | Nov 2026 | Official leaderboard | |
| 17 | | 36.3% ±6.8 | Oct 2026 | Official leaderboard | |
| 18 | Grok 4.7 | 35.8% ±6.8 | Sep 2026 | Official leaderboard | |
| 19 | | 34.4% ±6.5 | Nov 2026 | Official leaderboard | |
| 20 | Grok 4.6 | 33.7% ±6.7 | Aug 2026 | Official leaderboard | |
| 21 | Kimi K3 | 33.4% ±6.6 | Jul 2026 | Official leaderboard | |
| 22 | | 32.8% ±5.4 | Aug 2026 | Official leaderboard | |
| 23 | | 32.6% ±6.6 | Aug 2026 | Official leaderboard | |
| 24 | MiMo-V2.6 Pro | 32.4% ±6.6 | Sep 2026 | Official leaderboard | |
| 25 | | 32.1% ±6.6 | Oct 2026 | Official leaderboard | |
| 26 | | 32.1% ±6.6 | Sep 2026 | Official leaderboard | |
| 27 | | 32.1% ±6.6 | Aug 2026 | Official leaderboard | |
| 28 | Claude Fable 5.2 | 32.1% ±6.6 | Nov 2026 | Official leaderboard | |
| 29 | Claude Haiku 5.5 | 31.9% ±6.6 | Oct 2026 | Official leaderboard | |
| 30 | GLM-5.3-Flash | 31.6% ±6.6 | Aug 2026 | Official leaderboard | |
| 31 | GPT-5.6 Sol | 31.1% ±6.5 | Jul 2026 | Official leaderboard | |
| 32 | | 31.1% ±6.5 | Sep 2026 | Official leaderboard | |
| 33 | | 30.9% ±6.5 | Aug 2026 | Official leaderboard | |
| 34 | | 30.7% ±6.5 | Oct 2026 | Official leaderboard | |
| 35 | | 30.4% ±6.5 | Oct 2026 | Official leaderboard | |
| 36 | GPT-5.6 Terra | 30% ±6.5 | Jul 2026 | Official leaderboard | |
| 37 | Claude Opus 4.8 | 30% ±6.5 | May 2026 | Official leaderboard | |
| 38 | Claude Sonnet 5 | 29.4% ±6.4 | Jun 2026 | Official leaderboard | |
| 39 | MiMo-V2.6 Flash | 28.5% ±6.2 | Sep 2026 | Official leaderboard | |
| 40 | | 28.1% ±6.2 | Jul 2026 | Official leaderboard | |
| 41 | | 27.3% ±6.1 | Sep 2026 | Official leaderboard | |
| 42 | | 26.8% ±6.1 | Aug 2026 | Official leaderboard | |
| 43 | | 26.6% ±6.2 | Sep 2026 | Official leaderboard | |
| 44 | | 26.3% ±5.2 | Oct 2026 | Official leaderboard | |
| 45 | Claude Sonnet 4.6 | 25.8% ±6.2 | Feb 2026 | Official leaderboard | |
| 46 | | 25.2% ±6 | Apr 2026 | Official leaderboard | |
| 47 | Kimi K3.1 Pro | 24.9% ±6.1 | Oct 2026 | Official leaderboard | |
| 48 | Grok 4.5 | 24.9% ±6.1 | Jul 2026 | Official leaderboard | |
| 49 | GPT-6.2 Sol | 24.8% ±6.1 | Nov 2026 | Official leaderboard | |
| 50 | GPT-5.6 Luna | 24.8% ±6.1 | Jul 2026 | Official leaderboard | |
| 51 | Claude Opus 4.7 | 23.7% ±6 | Apr 2026 | Official leaderboard | |
| 52 | Hy4 Flash | 23.3% ±6 | Official leaderboard | ||
| 53 | | 22.8% ±5.9 | Aug 2026 | Official leaderboard | |
| 54 | GPT-6.2 Astra | 21.8% ±5.5 | Nov 2026 | Official leaderboard | |
| 55 | GPT-5.5 | 21.8% ±5.8 | Apr 2026 | Official leaderboard | |
| 56 | GPT-6.1 Sol | 21.8% ±5.8 | Sep 2026 | Official leaderboard | |
| 57 | | 21.6% ±5.8 | May 2026 | Official leaderboard | |
| 58 | GPT-6 Astra | 20.7% ±5.7 | Sep 2026 | Official leaderboard | |
| 59 | | 20.6% ±5.7 | Sep 2026 | Official leaderboard | |
| 60 | | 20.6% ±5.6 | Jun 2026 | Official leaderboard | |
| 61 | GPT-6 Luna | 19.9% ±5.6 | Sep 2026 | Official leaderboard | |
| 62 | Mercury 3 | 18.2% ±5 | Oct 2026 | Official leaderboard | |
| 63 | | 18% ±5.4 | Jul 2026 | Official leaderboard | |
| 64 | GPT-6.1 Terra | 17.1% ±5.3 | Oct 2026 | Official leaderboard | |
| 65 | | 15.8% ±5.1 | May 2026 | Official leaderboard | |
| 66 | | 15.4% ±4.6 | Jul 2026 | Official leaderboard | |
| 67 | | 15.3% ±4.7 | Jul 2026 | Official leaderboard | |
| 68 | GPT-6 Sol | 15% ±5 | Sep 2026 | Official leaderboard | |
| 69 | Kimi K2.6 | 12.4% ±4.7 | Apr 2026 | Official leaderboard | |
| 70 | | 11.8% ±4.6 | Dec 2025 | Official leaderboard | |
| 71 | | 11.6% ±4.3 | Oct 2026 | Official leaderboard | |
| 72 | MiMo-V2.5-Pro | 11.5% ±3.8 | Apr 2026 | Official leaderboard | |
| 73 | | 10.5% ±3.9 | Jun 2026 | Official leaderboard | |
| 74 | | 9.29% ±4.1 | Feb 2026 | Official leaderboard | |
| 75 | GPT-5.4 Mini | 8.81% ±4 | Mar 2026 | Official leaderboard | |
| 76 | Beam 1.0 | 8.81% ±3.7 | Oct 2026 | Official leaderboard | |
| 77 | MiMo-V2.5 | 7.77% ±3.5 | Apr 2026 | Official leaderboard | |
| 78 | | 7.68% ±3.5 | Mar 2026 | Official leaderboard | |
| 79 | | 7.25% ±3.7 | Jul 2026 | Official leaderboard | |
| 80 | Grok 4.20 | 6.95% ±3.4 | reasoning | Feb 2026 | Official leaderboard |
| 81 | | 6.87% ±3.3 | Mar 2026 | Official leaderboard | |
| 82 | Grok 4.3 | 6.18% ±3.4 | Apr 2026 | Official leaderboard | |
| 83 | Claude Haiku 4.5 | 5.86% ±3 | thinking | Oct 2025 | Official leaderboard |
| 84 | GPT-5.4 Nano | 4.97% ±2.8 | Mar 2026 | Official leaderboard | |
| 85 | | 4.48% ±2.9 | Apr 2026 | Official leaderboard | |
| 86 | | 3.11% ±2.5 | Mar 2026 | Official leaderboard | |
| 87 | | 2.59% ±2.2 | Aug 2026 | Official leaderboard | |
| 88 | Mercury 2.5 | 2.49% ±2 | Sep 2026 | Official leaderboard |
| # | Model | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 52.3% ±7.1 | Nov 2026 | Official leaderboard | |
| 2 | | 51.8% ±7.1 | Oct 2026 | Official leaderboard | |
| 3 | Claude Fable 5.1 | 50.8% ±7.1 | Sep 2026 | Official leaderboard | |
| 4 | | 49.7% ±7.1 | Sep 2026 | Official leaderboard | |
| 5 | | 49.2% ±7.1 | Sep 2026 | Official leaderboard | |
| 6 | Claude Opus 5 | 47.1% ±7.1 | Jul 2026 | Official leaderboard | |
| 7 | Claude Opus 5.5 | 44.5% ±7 | Sep 2026 | Official leaderboard | |
| 8 | | 44.4% ±7 | Oct 2026 | Official leaderboard | |
| 9 | GLM-5.3 | 43.3% ±7 | Aug 2026 | Official leaderboard | |
| 10 | | 43% ±7 | Oct 2026 | Official leaderboard | |
| 11 | | 42.4% ±6.9 | max | Sep 2026 | Official leaderboard |
| 12 | Claude Sonnet 5.5 | 42% ±7 | Sep 2026 | Official leaderboard | |
| 13 | | 40.4% ±6.9 | Nov 2026 | Official leaderboard | |
| 14 | | 38.9% ±6.4 | Nov 2026 | Official leaderboard | |
| 15 | Claude Fable 5 | 38.3% ±6.9 | Jun 2026 | Official leaderboard | |
| 16 | | 38.2% ±6.9 | Nov 2026 | Official leaderboard | |
| 17 | | 36.3% ±6.8 | Oct 2026 | Official leaderboard | |
| 18 | Grok 4.7 | 35.8% ±6.8 | Sep 2026 | Official leaderboard | |
| 19 | | 34.4% ±6.5 | Nov 2026 | Official leaderboard | |
| 20 | Grok 4.6 | 33.7% ±6.7 | Aug 2026 | Official leaderboard | |
| 21 | Kimi K3 | 33.4% ±6.6 | Jul 2026 | Official leaderboard | |
| 22 | | 32.8% ±5.4 | Aug 2026 | Official leaderboard | |
| 23 | | 32.6% ±6.6 | Aug 2026 | Official leaderboard | |
| 24 | MiMo-V2.6 Pro | 32.4% ±6.6 | Sep 2026 | Official leaderboard | |
| 25 | | 32.1% ±6.6 | Oct 2026 | Official leaderboard | |
| 26 | | 32.1% ±6.6 | Sep 2026 | Official leaderboard | |
| 27 | | 32.1% ±6.6 | Aug 2026 | Official leaderboard | |
| 28 | Claude Fable 5.2 | 32.1% ±6.6 | Nov 2026 | Official leaderboard | |
| 29 | Claude Haiku 5.5 | 31.9% ±6.6 | Oct 2026 | Official leaderboard | |
| 30 | GLM-5.3-Flash | 31.6% ±6.6 | Aug 2026 | Official leaderboard | |
| 31 | GPT-5.6 Sol | 31.1% ±6.5 | Jul 2026 | Official leaderboard | |
| 32 | | 31.1% ±6.5 | Sep 2026 | Official leaderboard | |
| 33 | | 30.9% ±6.5 | Aug 2026 | Official leaderboard | |
| 34 | | 30.7% ±6.5 | Oct 2026 | Official leaderboard | |
| 35 | | 30.4% ±6.5 | Oct 2026 | Official leaderboard | |
| 36 | GPT-5.6 Terra | 30% ±6.5 | Jul 2026 | Official leaderboard | |
| 37 | Claude Opus 4.8 | 30% ±6.5 | May 2026 | Official leaderboard | |
| 38 | Claude Sonnet 5 | 29.4% ±6.4 | Jun 2026 | Official leaderboard | |
| 39 | MiMo-V2.6 Flash | 28.5% ±6.2 | Sep 2026 | Official leaderboard | |
| 40 | | 28.1% ±6.2 | Jul 2026 | Official leaderboard | |
| 41 | | 27.3% ±6.1 | Sep 2026 | Official leaderboard | |
| 42 | | 26.8% ±6.1 | Aug 2026 | Official leaderboard | |
| 43 | | 26.6% ±6.2 | Sep 2026 | Official leaderboard | |
| 44 | | 26.3% ±5.2 | Oct 2026 | Official leaderboard | |
| 45 | Claude Sonnet 4.6 | 25.8% ±6.2 | Feb 2026 | Official leaderboard | |
| 46 | | 25.2% ±6 | Apr 2026 | Official leaderboard | |
| 47 | Kimi K3.1 Pro | 24.9% ±6.1 | Oct 2026 | Official leaderboard | |
| 48 | Grok 4.5 | 24.9% ±6.1 | Jul 2026 | Official leaderboard | |
| 49 | GPT-6.2 Sol | 24.8% ±6.1 | Nov 2026 | Official leaderboard | |
| 50 | GPT-5.6 Luna | 24.8% ±6.1 | Jul 2026 | Official leaderboard | |
| 51 | Claude Opus 4.7 | 23.7% ±6 | Apr 2026 | Official leaderboard | |
| 52 | | 22.8% ±5.9 | Aug 2026 | Official leaderboard | |
| 53 | GPT-6.2 Astra | 21.8% ±5.5 | Nov 2026 | Official leaderboard | |
| 54 | GPT-5.5 | 21.8% ±5.8 | Apr 2026 | Official leaderboard | |
| 55 | GPT-6.1 Sol | 21.8% ±5.8 | Sep 2026 | Official leaderboard | |
| 56 | | 21.6% ±5.8 | May 2026 | Official leaderboard | |
| 57 | GPT-6 Astra | 20.7% ±5.7 | Sep 2026 | Official leaderboard | |
| 58 | | 20.6% ±5.7 | Sep 2026 | Official leaderboard | |
| 59 | | 20.6% ±5.6 | Jun 2026 | Official leaderboard | |
| 60 | GPT-6 Luna | 19.9% ±5.6 | Sep 2026 | Official leaderboard | |
| 61 | Mercury 3 | 18.2% ±5 | Oct 2026 | Official leaderboard | |
| 62 | | 18% ±5.4 | Jul 2026 | Official leaderboard | |
| 63 | GPT-6.1 Terra | 17.1% ±5.3 | Oct 2026 | Official leaderboard | |
| 64 | | 15.8% ±5.1 | May 2026 | Official leaderboard | |
| 65 | | 15.4% ±4.6 | Jul 2026 | Official leaderboard | |
| 66 | | 15.3% ±4.7 | Jul 2026 | Official leaderboard | |
| 67 | GPT-6 Sol | 15% ±5 | Sep 2026 | Official leaderboard | |
| 68 | Kimi K2.6 | 12.4% ±4.7 | Apr 2026 | Official leaderboard | |
| 69 | | 11.8% ±4.6 | Dec 2025 | Official leaderboard | |
| 70 | | 11.6% ±4.3 | Oct 2026 | Official leaderboard | |
| 71 | MiMo-V2.5-Pro | 11.5% ±3.8 | Apr 2026 | Official leaderboard | |
| 72 | | 10.5% ±3.9 | Jun 2026 | Official leaderboard | |
| 73 | | 9.29% ±4.1 | Feb 2026 | Official leaderboard | |
| 74 | GPT-5.4 Mini | 8.81% ±4 | Mar 2026 | Official leaderboard | |
| 75 | Beam 1.0 | 8.81% ±3.7 | Oct 2026 | Official leaderboard | |
| 76 | MiMo-V2.5 | 7.77% ±3.5 | Apr 2026 | Official leaderboard | |
| 77 | | 7.68% ±3.5 | Mar 2026 | Official leaderboard | |
| 78 | | 7.25% ±3.7 | Jul 2026 | Official leaderboard | |
| 79 | Grok 4.20 | 6.95% ±3.4 | reasoning | Feb 2026 | Official leaderboard |
| 80 | | 6.87% ±3.3 | Mar 2026 | Official leaderboard | |
| 81 | Grok 4.3 | 6.18% ±3.4 | Apr 2026 | Official leaderboard | |
| 82 | Claude Haiku 4.5 | 5.86% ±3 | thinking | Oct 2025 | Official leaderboard |
| 83 | GPT-5.4 Nano | 4.97% ±2.8 | Mar 2026 | Official leaderboard | |
| 84 | | 4.48% ±2.9 | Apr 2026 | Official leaderboard | |
| 85 | | 3.11% ±2.5 | Mar 2026 | Official leaderboard | |
| 86 | | 2.59% ±2.2 | Aug 2026 | Official leaderboard | |
| 87 | Mercury 2.5 | 2.49% ±2 | Sep 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | 52.3% | Nov 2026 | Official leaderboard | ||
| 2 | 51.8% | Oct 2026 | Official leaderboard | ||
| 3 | Claude Fable 5.1 | 50.8% | Sep 2026 | Official leaderboard | |
| 4 | 49.7% | Sep 2026 | Official leaderboard | ||
| 5 | 49.2% | Sep 2026 | Official leaderboard | ||
| 6 | Claude Opus 5 | 47.1% | Jul 2026 | Official leaderboard | |
| 7 | Claude Opus 5.5 | 44.5% | Sep 2026 | Official leaderboard | |
| 8 | 44.4% | Oct 2026 | Official leaderboard | ||
| 9 | GLM-5.3 | 43.3% | Aug 2026 | Official leaderboard | |
| 10 | 43% | Oct 2026 | Official leaderboard | ||
| 11 | 42.4% | max | Sep 2026 | Official leaderboard | |
| 12 | Claude Sonnet 5.5 | 42% | Sep 2026 | Official leaderboard | |
| 13 | 40.4% | Nov 2026 | Official leaderboard | ||
| 14 | 38.9% | Nov 2026 | Official leaderboard | ||
| 15 | Claude Fable 5 | 38.3% | Jun 2026 | Official leaderboard | |
| 16 | 38.2% | Nov 2026 | Official leaderboard | ||
| 17 | 36.3% | Oct 2026 | Official leaderboard | ||
| 18 | Grok 4.7 | 35.8% | Sep 2026 | Official leaderboard | |
| 19 | 34.4% | Nov 2026 | Official leaderboard | ||
| 20 | Grok 4.6 | 33.7% | Aug 2026 | Official leaderboard | |
| 21 | Kimi K3 | 33.4% | Jul 2026 | Official leaderboard | |
| 22 | 32.8% | Aug 2026 | Official leaderboard | ||
| 23 | 32.6% | Aug 2026 | Official leaderboard | ||
| 24 | MiMo-V2.6 Pro | 32.4% | Sep 2026 | Official leaderboard | |
| 25 | 32.1% | Oct 2026 | Official leaderboard | ||
| 26 | 32.1% | Sep 2026 | Official leaderboard | ||
| 27 | 32.1% | Aug 2026 | Official leaderboard | ||
| 28 | Claude Fable 5.2 | 32.1% | Nov 2026 | Official leaderboard | |
| 29 | Claude Haiku 5.5 | 31.9% | Oct 2026 | Official leaderboard | |
| 30 | GLM-5.3-Flash | 31.6% | Aug 2026 | Official leaderboard | |
| 31 | GPT-5.6 Sol | 31.1% | Jul 2026 | Official leaderboard | |
| 32 | 31.1% | Sep 2026 | Official leaderboard | ||
| 33 | 30.9% | Aug 2026 | Official leaderboard | ||
| 34 | 30.7% | Oct 2026 | Official leaderboard | ||
| 35 | 30.4% | Oct 2026 | Official leaderboard | ||
| 36 | GPT-5.6 Terra | 30% | Jul 2026 | Official leaderboard | |
| 37 | Claude Opus 4.8 | 30% | May 2026 | Official leaderboard | |
| 38 | Claude Sonnet 5 | 29.4% | Jun 2026 | Official leaderboard | |
| 39 | MiMo-V2.6 Flash | 28.5% | Sep 2026 | Official leaderboard | |
| 40 | 28.1% | Jul 2026 | Official leaderboard | ||
| 41 | 27.3% | Sep 2026 | Official leaderboard | ||
| 42 | 26.8% | Aug 2026 | Official leaderboard | ||
| 43 | 26.6% | Sep 2026 | Official leaderboard | ||
| 44 | 26.3% | Oct 2026 | Official leaderboard | ||
| 45 | Claude Sonnet 4.6 | 25.8% | Feb 2026 | Official leaderboard | |
| 46 | 25.2% | Apr 2026 | Official leaderboard | ||
| 47 | Kimi K3.1 Pro | 24.9% | Oct 2026 | Official leaderboard | |
| 48 | Grok 4.5 | 24.9% | Jul 2026 | Official leaderboard | |
| 49 | GPT-6.2 Sol | 24.8% | Nov 2026 | Official leaderboard | |
| 50 | GPT-5.6 Luna | 24.8% | Jul 2026 | Official leaderboard | |
| 51 | Claude Opus 4.7 | 23.7% | Apr 2026 | Official leaderboard | |
| 52 | 22.8% | Aug 2026 | Official leaderboard | ||
| 53 | GPT-6.2 Astra | 21.8% | Nov 2026 | Official leaderboard | |
| 54 | GPT-5.5 | 21.8% | Apr 2026 | Official leaderboard | |
| 55 | GPT-6.1 Sol | 21.8% | Sep 2026 | Official leaderboard | |
| 56 | 21.6% | May 2026 | Official leaderboard | ||
| 57 | GPT-6 Astra | 20.7% | Sep 2026 | Official leaderboard | |
| 58 | 20.6% | Sep 2026 | Official leaderboard | ||
| 59 | 20.6% | Jun 2026 | Official leaderboard | ||
| 60 | GPT-6 Luna | 19.9% | Sep 2026 | Official leaderboard | |
| 61 | Mercury 3 | 18.2% | Oct 2026 | Official leaderboard | |
| 62 | 18% | Jul 2026 | Official leaderboard | ||
| 63 | GPT-6.1 Terra | 17.1% | Oct 2026 | Official leaderboard | |
| 64 | 15.8% | May 2026 | Official leaderboard | ||
| 65 | 15.4% | Jul 2026 | Official leaderboard | ||
| 66 | 15.3% | Jul 2026 | Official leaderboard | ||
| 67 | GPT-6 Sol | 15% | Sep 2026 | Official leaderboard | |
| 68 | 14.1% | Nov 2026 | Lab model card | ||
| 69 | Kimi K2.6 | 12.4% | Apr 2026 | Official leaderboard | |
| 70 | 11.8% | Dec 2025 | Official leaderboard | ||
| 71 | 11.6% | Oct 2026 | Official leaderboard | ||
| 72 | MiMo-V2.5-Pro | 11.5% | Apr 2026 | Official leaderboard | |
| 73 | 10.5% | Jun 2026 | Official leaderboard | ||
| 74 | 9.29% | Feb 2026 | Official leaderboard | ||
| 75 | GPT-5.4 Mini | 8.81% | Mar 2026 | Official leaderboard | |
| 76 | Beam 1.0 | 8.81% | Oct 2026 | Official leaderboard | |
| 77 | MiMo-V2.5 | 7.77% | Apr 2026 | Official leaderboard | |
| 78 | 7.68% | Mar 2026 | Official leaderboard | ||
| 79 | 7.25% | Jul 2026 | Official leaderboard | ||
| 80 | Grok 4.20 | 6.95% | reasoning | Feb 2026 | Official leaderboard |
| 81 | 6.87% | Mar 2026 | Official leaderboard | ||
| 82 | Grok 4.3 | 6.18% | Apr 2026 | Official leaderboard | |
| 83 | Claude Haiku 4.5 | 5.86% | thinking | Oct 2025 | Official leaderboard |
| 84 | GPT-5.4 Nano | 4.97% | Mar 2026 | Official leaderboard | |
| 85 | 4.48% | Apr 2026 | Official leaderboard | ||
| 86 | 3.11% | Mar 2026 | Official leaderboard | ||
| 87 | 2.59% | Aug 2026 | Official leaderboard | ||
| 88 | Mercury 2.5 | 2.49% | Sep 2026 | Official leaderboard |
Labs report scores for 2 models in their cards. Switch the scores above to rank them together.
Other ways to score it
The benchmark’s own leaderboard also reports Weighted pass, another way to score the whole test. Labs sometimes quote it instead of the headline. Gemini 4 Argon leads it. Arrows show how far a model moved from its overall rank among the models we track.
Partial credit: the weighted pass rate the board shows beside the all-pass accuracy. 87 models we track have a score here.
- 1
Gemini 4 Argon ↑4 79%
- 2
Gemini 4 Hydrogen ↓1 78.4%
- 3 Claude Fable 5.1 77.9%
- 4 Claude Opus 5 ↑2 76.7%
- 5
Gemini 4 Carbon ↓3 76.4%
- 6 GLM-5.3 ↑3 75.2%
- 7
Muse Wonder Full ↑3 75%
- 8
DeepSeek V4.1 Flash 1017 74.9%
- 9
Qwen3.8 Max (0902) ↓5 74.3%
- 10 Claude Sonnet 5.5 ↑2 73.4%
Accuracy against latency
The Vals scatter chart with its x axis switched from Cost to Latency: mean time per test against accuracy, on a log scale. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Latency (mean per test) |
|---|---|---|---|
| 52.3% | 1,095 s | ||
| 51.8% | 2,086 s | ||
| Claude Fable 5.1 | 50.8% | 1,714 s | |
| 49.7% | 5,231 s | ||
| 49.2% | 985.63 s | ||
| Claude Opus 5 | 47.1% | 1,008 s | |
| Claude Opus 5.5 | 44.5% | 4,013 s | |
| 44.4% | 1,264 s | ||
| GLM-5.3 | 43.3% | 3,053 s | |
| 43% | 1,084 s | ||
| max | 42.4% | 248.82 s | |
| Claude Sonnet 5.5 | 42% | 3,561 s | |
| 40.4% | 1,473 s | ||
| 38.9% | 414.04 s | ||
| Claude Fable 5 | 38.3% | 866.63 s | |
| 38.2% | 90.13 s | ||
| 37.9% | 505.37 s | ||
| 36.3% | 492.84 s | ||
| Grok 4.7 | 35.8% | 996.47 s | |
| 34.4% | 3,808 s | ||
| Grok 4.6 | 33.7% | 657.84 s | |
| Kimi K3 | 33.4% | 2,415 s | |
| 32.8% | 119.91 s | ||
| 32.6% | 2,464 s | ||
| MiMo-V2.6 Pro | 32.4% | 1,548 s | |
| 32.1% | 1,963 s | ||
| 32.1% | 178.33 s | ||
| Claude Fable 5.2 | 32.1% | 299.74 s | |
| 32.1% | 2,436 s | ||
| Claude Haiku 5.5 | 31.9% | 2,974 s | |
| GLM-5.3-Flash | 31.6% | 1,297 s | |
| GPT-5.6 Sol | 31.1% | 2,681 s | |
| 31.1% | 1,846 s | ||
| 30.9% | 1,334 s | ||
| 30.7% | 1,023 s | ||
| 30.4% | 3,438 s | ||
| GPT-5.6 Terra | 30% | 3,631 s | |
| Claude Opus 4.8 | 30% | 479.2 s | |
| Claude Sonnet 5 | 29.4% | 1,159 s | |
| MiMo-V2.6 Flash | 28.5% | 1,039 s | |
| 28.1% | 337.34 s | ||
| 27.3% | 1,289 s | ||
| 26.8% | 1,597 s | ||
| 26.6% | 349.08 s | ||
| 26.3% | 701.83 s | ||
| Claude Sonnet 4.6 | 25.8% | 707.31 s | |
| 25.2% | 1,245 s | ||
| Kimi K3.1 Pro | 24.9% | 3,519 s | |
| Grok 4.5 | 24.9% | 283.57 s | |
| GPT-6.2 Sol | 24.8% | 2,617 s | |
| GPT-5.6 Luna | 24.8% | 2,566 s | |
| Claude Opus 4.7 | 23.7% | 279.04 s | |
| Hy4 Flash | 23.3% | 371.72 s | |
| 22.8% | 87.24 s | ||
| GPT-6.2 Astra | 21.8% | 3,693 s | |
| GPT-5.5 | 21.8% | 951.81 s | |
| GPT-6.1 Sol | 21.8% | 1,214 s | |
| 21.7% | 233 s | ||
| GPT-6 Astra | 20.7% | 900.59 s | |
| 20.6% | 333.83 s | ||
| 20.6% | 314.57 s | ||
| GPT-6 Luna | 20% | 1,996 s | |
| Mercury 3 | 18.2% | 269.27 s | |
| 18% | 105.32 s | ||
| GPT-6.1 Terra | 17.1% | 2,751 s | |
| 15.8% | 209.73 s | ||
| 15.4% | 385.25 s | ||
| 15.3% | 810.56 s | ||
| GPT-6 Sol | 15% | 1,052 s | |
| Kimi K2.6 | 12.4% | 924.42 s | |
| 11.8% | 100.62 s | ||
| 11.6% | 72.66 s | ||
| MiMo-V2.5-Pro | 11.5% | 376.51 s | |
| 10.5% | 310.26 s | ||
| 9.3% | 100.96 s | ||
| Beam 1.0 | 8.8% | 57.99 s | |
| GPT-5.4 Mini | 8.8% | 1,006 s | |
| MiMo-V2.5 | 7.8% | 500.83 s | |
| 7.7% | 378.16 s | ||
| 7.3% | 47.46 s | ||
| Grok 4.20 | reasoning | 7% | 89.26 s |
| 6.9% | 302.85 s | ||
| Grok 4.3 | 6.2% | 97.52 s | |
| Claude Haiku 4.5 | thinking | 5.9% | 155.02 s |
| GPT-5.4 Nano | 5% | 220.31 s | |
| 4.5% | 430.67 s | ||
| 3.1% | 18.74 s | ||
| 2.6% | 1,180 s | ||
| Mercury 2.5 | 2.5% | 29.67 s |
Accuracy against latency
The Vals scatter chart with its x axis switched from Cost to Latency: mean time per test against accuracy, on a log scale. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Latency (mean per test) |
|---|---|---|---|
| 52.3% | 1,095 s | ||
| 51.8% | 2,086 s | ||
| Claude Fable 5.1 | 50.8% | 1,714 s | |
| 49.7% | 5,231 s | ||
| 49.2% | 985.63 s | ||
| Claude Opus 5 | 47.1% | 1,008 s | |
| Claude Opus 5.5 | 44.5% | 4,013 s | |
| 44.4% | 1,264 s | ||
| GLM-5.3 | 43.3% | 3,053 s | |
| 43% | 1,084 s | ||
| max | 42.4% | 248.82 s | |
| Claude Sonnet 5.5 | 42% | 3,561 s | |
| 40.4% | 1,473 s | ||
| 38.9% | 414.04 s | ||
| Claude Fable 5 | 38.3% | 866.63 s | |
| 38.2% | 90.13 s | ||
| 37.9% | 505.37 s | ||
| 36.3% | 492.84 s | ||
| Grok 4.7 | 35.8% | 996.47 s | |
| 34.4% | 3,808 s | ||
| Grok 4.6 | 33.7% | 657.84 s | |
| Kimi K3 | 33.4% | 2,415 s | |
| 32.8% | 119.91 s | ||
| 32.6% | 2,464 s | ||
| MiMo-V2.6 Pro | 32.4% | 1,548 s | |
| 32.1% | 1,963 s | ||
| 32.1% | 178.33 s | ||
| Claude Fable 5.2 | 32.1% | 299.74 s | |
| 32.1% | 2,436 s | ||
| Claude Haiku 5.5 | 31.9% | 2,974 s | |
| GLM-5.3-Flash | 31.6% | 1,297 s | |
| GPT-5.6 Sol | 31.1% | 2,681 s | |
| 31.1% | 1,846 s | ||
| 30.9% | 1,334 s | ||
| 30.7% | 1,023 s | ||
| 30.4% | 3,438 s | ||
| GPT-5.6 Terra | 30% | 3,631 s | |
| Claude Opus 4.8 | 30% | 479.2 s | |
| Claude Sonnet 5 | 29.4% | 1,159 s | |
| MiMo-V2.6 Flash | 28.5% | 1,039 s | |
| 28.1% | 337.34 s | ||
| 27.3% | 1,289 s | ||
| 26.8% | 1,597 s | ||
| 26.6% | 349.08 s | ||
| 26.3% | 701.83 s | ||
| Claude Sonnet 4.6 | 25.8% | 707.31 s | |
| 25.2% | 1,245 s | ||
| Kimi K3.1 Pro | 24.9% | 3,519 s | |
| Grok 4.5 | 24.9% | 283.57 s | |
| GPT-6.2 Sol | 24.8% | 2,617 s | |
| GPT-5.6 Luna | 24.8% | 2,566 s | |
| Claude Opus 4.7 | 23.7% | 279.04 s | |
| 22.8% | 87.24 s | ||
| GPT-6.2 Astra | 21.8% | 3,693 s | |
| GPT-5.5 | 21.8% | 951.81 s | |
| GPT-6.1 Sol | 21.8% | 1,214 s | |
| 21.7% | 233 s | ||
| GPT-6 Astra | 20.7% | 900.59 s | |
| 20.6% | 333.83 s | ||
| 20.6% | 314.57 s | ||
| GPT-6 Luna | 20% | 1,996 s | |
| Mercury 3 | 18.2% | 269.27 s | |
| 18% | 105.32 s | ||
| GPT-6.1 Terra | 17.1% | 2,751 s | |
| 15.8% | 209.73 s | ||
| 15.4% | 385.25 s | ||
| 15.3% | 810.56 s | ||
| GPT-6 Sol | 15% | 1,052 s | |
| Kimi K2.6 | 12.4% | 924.42 s | |
| 11.8% | 100.62 s | ||
| 11.6% | 72.66 s | ||
| MiMo-V2.5-Pro | 11.5% | 376.51 s | |
| 10.5% | 310.26 s | ||
| 9.3% | 100.96 s | ||
| Beam 1.0 | 8.8% | 57.99 s | |
| GPT-5.4 Mini | 8.8% | 1,006 s | |
| MiMo-V2.5 | 7.8% | 500.83 s | |
| 7.7% | 378.16 s | ||
| 7.3% | 47.46 s | ||
| Grok 4.20 | reasoning | 7% | 89.26 s |
| 6.9% | 302.85 s | ||
| Grok 4.3 | 6.2% | 97.52 s | |
| Claude Haiku 4.5 | thinking | 5.9% | 155.02 s |
| GPT-5.4 Nano | 5% | 220.31 s | |
| 4.5% | 430.67 s | ||
| 3.1% | 18.74 s | ||
| 2.6% | 1,180 s | ||
| Mercury 2.5 | 2.5% | 29.67 s |
The best score, 52.3%, costs $3.87 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Tax Agent Bench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| 52.3% | $3.87 | 307,129 | |||
| 51.8% | $6.34 | 182,644 | |||
| Claude Fable 5.1 | 50.8% | $13 | 146,309 | ||
| 49.7% | $4.07 | 287,749 | |||
| 49.2% | $3.47 | 75,098 | |||
| Claude Opus 5 | 47.1% | $5.14 | 86,847 | ||
| Claude Opus 5.5 | 44.5% | $14 | 463,161 | ||
| 44.4% | $0.46 | 277,522 | |||
| GLM-5.3 | 43.3% | $1.80 | 245,685 | ||
| 43% | $2.15 | 51,650 | |||
| max | 42.4% | $0.39 | 31,585 | ||
| Claude Sonnet 5.5 | 42% | $8.73 | 565,600 | ||
| 40.4% | $1.03 | 97,273 | |||
| 38.9% | $0.14 | 72,443 | |||
| Claude Fable 5 | 38.3% | $6.70 | 73,091 | ||
| 38.2% | $0.03 | 32,504 | |||
| 37.9% | $0.32 | 24,548 | |||
| 36.3% | $1.88 | 45,444 | |||
| Grok 4.7 | 35.8% | $1.80 | 56,070 | ||
| 34.4% | $1.69 | 416,480 | |||
| Grok 4.6 | 33.7% | $0.98 | 39,758 | ||
| Kimi K3 | 33.4% | $2.79 | 79,342 | ||
| 32.8% | $0.27 | 19,763 | |||
| 32.6% | $0.59 | 149,760 | |||
| MiMo-V2.6 Pro | 32.4% | $0.13 | 64,880 | ||
| 32.1% | $0.32 | 364,312 | |||
| 32.1% | $0.86 | 36,335 | |||
| 32.1% | $1.55 | 107,611 | |||
| Claude Fable 5.2 | 32.1% | $3.31 | 33,788 | ||
| Claude Haiku 5.5 | 31.9% | $1.16 | 741,776 | ||
| GLM-5.3-Flash | 31.6% | $0.14 | 148,072 | ||
| GPT-5.6 Sol | 31.1% | $7.51 | 193,485 | ||
| 31.1% | $2.97 | 71,431 | |||
| 30.9% | $0.82 | 187,156 | |||
| 30.7% | $0.50 | 76,008 | |||
| 30.4% | $1.39 | 139,787 | |||
| GPT-5.6 Terra | 30% | $4.83 | 268,407 | ||
| Claude Opus 4.8 | 30% | $1.69 | 38,739 | ||
| Claude Sonnet 5 | 29.4% | $1.79 | 113,409 | ||
| MiMo-V2.6 Flash | 28.5% | $0.05 | 63,189 | ||
| 28.1% | $0.16 | 76,525 | |||
| 27.3% | $0.55 | 84,980 | |||
| 26.8% | $0.73 | 109,118 | |||
| 26.6% | $0.13 | 80,656 | |||
| 26.3% | $0.88 | 18,601 | |||
| Claude Sonnet 4.6 | 25.8% | $1.19 | 38,465 | ||
| 25.2% | $0.72 | 110,422 | |||
| Kimi K3.1 Pro | 24.9% | $3.64 | 180,052 | ||
| Grok 4.5 | 24.9% | $0.47 | 16,998 | ||
| GPT-6.2 Sol | 24.8% | $2.40 | 120,431 | ||
| GPT-5.6 Luna | 24.8% | $0.47 | 271,107 | ||
| Claude Opus 4.7 | 23.7% | $1.27 | 21,092 | ||
| 22.8% | $0.48 | 20,337 | |||
| GPT-6.2 Astra | 21.8% | $7.90 | 109,872 | ||
| GPT-5.5 | 21.8% | $4.07 | 66,972 | ||
| GPT-6.1 Sol | 21.8% | $1.32 | 65,893 | ||
| 21.6% | $0.86 | 30,433 | |||
| GPT-6 Astra | 20.7% | $5.80 | 62,346 | ||
| 20.6% | $0.03 | 43,263 | |||
| 20.6% | $0.16 | 24,976 | |||
| GPT-6 Luna | 19.9% | $0.19 | 214,022 | ||
| Mercury 3 | 18.2% | $0.05 | 73,519 | ||
| 18% | $0.36 | 16,362 | |||
| GPT-6.1 Terra | 17.1% | $2.16 | 239,078 | ||
| 15.8% | $0.44 | 18,741 | |||
| 15.4% | $0.09 | 38,499 | |||
| 15.3% | $0.35 | 37,668 | |||
| GPT-6 Sol | 15% | $2.28 | 97,209 | ||
| Kimi K2.6 | 12.4% | $0.57 | 45,053 | ||
| 11.8% | $0.10 | 16,306 | |||
| 11.6% | $0.05 | 30,297 | |||
| MiMo-V2.5-Pro | 11.5% | $0.04 | 12,625 | ||
| 10.5% | $0.09 | 22,236 | |||
| 9.29% | $0.30 | 9,861 | |||
| GPT-5.4 Mini | 8.81% | $0.81 | 137,206 | ||
| Beam 1.0 | 8.81% | 20,848 | |||
| MiMo-V2.5 | 7.77% | $0.02 | 15,557 | ||
| 7.68% | $0.30 | 17,531 | |||
| 7.25% | $0.08 | 9,682 | |||
| Grok 4.20 | reasoning | 6.95% | $0.12 | 8,326 | |
| 6.87% | $0.12 | 14,118 | |||
| Grok 4.3 | 6.18% | $0.12 | 9,232 | ||
| Claude Haiku 4.5 | thinking | 5.86% | $0.23 | 14,371 | |
| GPT-5.4 Nano | 4.97% | $0.07 | 23,086 | ||
| 4.48% | $1.44 | 36,331 | |||
| 3.11% | $0.01 | 4,699 | |||
| 2.59% | $0.03 | 116,422 | |||
| Mercury 2.5 | 2.49% | $0.02 | 8,007 |
The best score, 52.3%, costs $3.87 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Tax Agent Bench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| 52.3% | $3.87 | 307,129 | |||
| 51.8% | $6.34 | 182,644 | |||
| Claude Fable 5.1 | 50.8% | $13 | 146,309 | ||
| 49.7% | $4.07 | 287,749 | |||
| 49.2% | $3.47 | 75,098 | |||
| Claude Opus 5 | 47.1% | $5.14 | 86,847 | ||
| Claude Opus 5.5 | 44.5% | $14 | 463,161 | ||
| 44.4% | $0.46 | 277,522 | |||
| GLM-5.3 | 43.3% | $1.80 | 245,685 | ||
| 43% | $2.15 | 51,650 | |||
| max | 42.4% | $0.39 | 31,585 | ||
| Claude Sonnet 5.5 | 42% | $8.73 | 565,600 | ||
| 40.4% | $1.03 | 97,273 | |||
| 38.9% | $0.14 | 72,443 | |||
| Claude Fable 5 | 38.3% | $6.70 | 73,091 | ||
| 38.2% | $0.03 | 32,504 | |||
| 37.9% | $0.32 | 24,548 | |||
| 36.3% | $1.88 | 45,444 | |||
| Grok 4.7 | 35.8% | $1.80 | 56,070 | ||
| 34.4% | $1.69 | 416,480 | |||
| Grok 4.6 | 33.7% | $0.98 | 39,758 | ||
| Kimi K3 | 33.4% | $2.79 | 79,342 | ||
| 32.8% | $0.27 | 19,763 | |||
| 32.6% | $0.59 | 149,760 | |||
| MiMo-V2.6 Pro | 32.4% | $0.13 | 64,880 | ||
| 32.1% | $0.32 | 364,312 | |||
| 32.1% | $0.86 | 36,335 | |||
| 32.1% | $1.55 | 107,611 | |||
| Claude Fable 5.2 | 32.1% | $3.31 | 33,788 | ||
| Claude Haiku 5.5 | 31.9% | $1.16 | 741,776 | ||
| GLM-5.3-Flash | 31.6% | $0.14 | 148,072 | ||
| GPT-5.6 Sol | 31.1% | $7.51 | 193,485 | ||
| 31.1% | $2.97 | 71,431 | |||
| 30.9% | $0.82 | 187,156 | |||
| 30.7% | $0.50 | 76,008 | |||
| 30.4% | $1.39 | 139,787 | |||
| GPT-5.6 Terra | 30% | $4.83 | 268,407 | ||
| Claude Opus 4.8 | 30% | $1.69 | 38,739 | ||
| Claude Sonnet 5 | 29.4% | $1.79 | 113,409 | ||
| MiMo-V2.6 Flash | 28.5% | $0.05 | 63,189 | ||
| 28.1% | $0.16 | 76,525 | |||
| 27.3% | $0.55 | 84,980 | |||
| 26.8% | $0.73 | 109,118 | |||
| 26.6% | $0.13 | 80,656 | |||
| 26.3% | $0.88 | 18,601 | |||
| Claude Sonnet 4.6 | 25.8% | $1.19 | 38,465 | ||
| 25.2% | $0.72 | 110,422 | |||
| Kimi K3.1 Pro | 24.9% | $3.64 | 180,052 | ||
| Grok 4.5 | 24.9% | $0.47 | 16,998 | ||
| GPT-6.2 Sol | 24.8% | $2.40 | 120,431 | ||
| GPT-5.6 Luna | 24.8% | $0.47 | 271,107 | ||
| Claude Opus 4.7 | 23.7% | $1.27 | 21,092 | ||
| 22.8% | $0.48 | 20,337 | |||
| GPT-6.2 Astra | 21.8% | $7.90 | 109,872 | ||
| GPT-5.5 | 21.8% | $4.07 | 66,972 | ||
| GPT-6.1 Sol | 21.8% | $1.32 | 65,893 | ||
| 21.6% | $0.86 | 30,433 | |||
| GPT-6 Astra | 20.7% | $5.80 | 62,346 | ||
| 20.6% | $0.03 | 43,263 | |||
| 20.6% | $0.16 | 24,976 | |||
| GPT-6 Luna | 19.9% | $0.19 | 214,022 | ||
| Mercury 3 | 18.2% | $0.05 | 73,519 | ||
| 18% | $0.36 | 16,362 | |||
| GPT-6.1 Terra | 17.1% | $2.16 | 239,078 | ||
| 15.8% | $0.44 | 18,741 | |||
| 15.4% | $0.09 | 38,499 | |||
| 15.3% | $0.35 | 37,668 | |||
| GPT-6 Sol | 15% | $2.28 | 97,209 | ||
| Kimi K2.6 | 12.4% | $0.57 | 45,053 | ||
| 11.8% | $0.10 | 16,306 | |||
| 11.6% | $0.05 | 30,297 | |||
| MiMo-V2.5-Pro | 11.5% | $0.04 | 12,625 | ||
| 10.5% | $0.09 | 22,236 | |||
| 9.29% | $0.30 | 9,861 | |||
| GPT-5.4 Mini | 8.81% | $0.81 | 137,206 | ||
| Beam 1.0 | 8.81% | 20,848 | |||
| MiMo-V2.5 | 7.77% | $0.02 | 15,557 | ||
| 7.68% | $0.30 | 17,531 | |||
| 7.25% | $0.08 | 9,682 | |||
| Grok 4.20 | reasoning | 6.95% | $0.12 | 8,326 | |
| 6.87% | $0.12 | 14,118 | |||
| Grok 4.3 | 6.18% | $0.12 | 9,232 | ||
| Claude Haiku 4.5 | thinking | 5.86% | $0.23 | 14,371 | |
| GPT-5.4 Nano | 4.97% | $0.07 | 23,086 | ||
| 4.48% | $1.44 | 36,331 | |||
| 3.11% | $0.01 | 4,699 | |||
| 2.59% | $0.03 | 116,422 | |||
| Mercury 2.5 | 2.49% | $0.02 | 8,007 |
3 models have held number one on the official leaderboard since its release in September 2026 3 models have held number one with claims included since its release in September 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Tax Agent Bench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official Tax Agent Bench leaderboard and labs’ model cards
2 labs put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 12, 2026 | 52.3 | Vals Tax Agent Bench (#1 overall) | |
| Nov 5, 2026 | 65.8 | Tax Agent Bench, 65.8% |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 20, 2026 | | 14.1 | Tax Agent Bench | Capabilities |
2 lab claims next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 2 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| | 65.8% Tax Agent Bench, 65.8% | 65.8% Leaderboard | Same |
| | 52.3% Vals Tax Agent Bench (#1 overall) | 52.3% Leaderboard | Same |
More 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%
- 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. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
All 12 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (88 entries), launch posts (2 scores) and system cards (1 score).
- Pass Models scored 88 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from November 2026, for Inkling 2 Mini.
- Pass Frontier models 10 of the top 10 have a score, led by GPT-6.2 Astra (#1).
- Pass Headroom The best is 52.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on vals.ai: 88 rows for models we track and 1 other entry at the last read.
- Pass Last read November 18th, 2026.
- Pass Read worked The last read worked.
Consistency 2 pass
- Pass Lab claims Both pairs agree within 10 points.
- Pass Known issues No published audit found problems.