Benchmark Almanac

Immigration Bench

Claude Fable 5.1 75.4% leads since October 2026
Not in model cards

Models answer expert-written US immigration law questions from seven personas, such as F-1 students, employers and DACA recipients. An AI grader checks each answer against an expert rubric.

Experts wrote 519 questions. Vals reports on a private 262-question test set and reserves the other 257 for labs to license. Score is the share of rubric items met.

Released
October 2026
Kind
Law
Level
Expert
Scored
Graded by a model
Answers
Open-ended
Tasks
Kept private
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last model added
November 2026
Scores refreshed
November 12th, 2026
25
Models scored on its own leaderboard

Claude Fable 5.1 leads with 75.4%

Best score per model 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.

25 models. Scroll sideways for the rest.

  1. 75.4 Claude Fable 5.1
  2. 74.0 Claude Fable 5.2
  3. 72.1 Claude Opus 5.5
  4. 71.2 Muse Wonder Full
  5. 70.1 Qwen 3.8 Max
  6. 69.6 Muse Wonder
  7. 69.0 Claude Sonnet 5.5
  8. 68.3 Kimi K3
  9. 68.1 Gemini 4 Argon
  10. 68.0 Grok 4.7
  11. 67.8 GPT-6.1 Sol
  12. 67.7 GPT-6 Astra
  13. 67.5 MiMo-V2.6 Pro
  14. 66.7 GLM-5.3
  15. 66.5 Muse Spark 1.2
  16. 66.0 Grok 4.6
  17. 65.6 DeepSeek V4.1 Flash
  18. 65.0 Muse Spark 1.3
  19. 63.7 Mistral Large 4 Preview
  20. 63.4 Gemini 3.8 Flash
  21. 62.5 GPT-6 Luna
  22. 61.8 Claude Haiku 5.5
  23. 61.7 DeepSeek V4 Pro 0813
  24. 57.5 MiniMax-M3
  25. 55.7 Gemini 3.5 Flash-Lite
  1. 1 Claude Fable 5.1 75.4%
  2. 2 Claude Fable 5.2 74%
  3. 3 Claude Opus 5.5 72.1%
  4. 4 Muse Wonder Full 71.2%
  5. 5 Qwen 3.8 Max 70.1%
  6. 6 Muse Wonder 69.6%
  7. 7 Claude Sonnet 5.5 69%
  8. 8 Kimi K3 68.3%
  9. 9 Gemini 4 Argon 68.1%
  10. 10 Grok 4.7 68%
  11. 11 GPT-6.1 Sol 67.8%
  12. 12 GPT-6 Astra 67.7%
  13. 13 MiMo-V2.6 Pro 67.5%
  14. 14 GLM-5.3 66.7%
  15. 15 Muse Spark 1.2 66.5%
  16. 16 Grok 4.6 66%
  17. 17 DeepSeek V4.1 Flash 65.6%
  18. 18 Muse Spark 1.3 65%
  19. 19 Mistral Large 4 Preview 63.7%
  20. 20 Gemini 3.8 Flash 63.4%
  21. 21 GPT-6 Luna 62.5%
  22. 22 Claude Haiku 5.5 61.8%
  23. 23 DeepSeek V4 Pro 0813 61.7%
  24. 24 MiniMax-M3 57.5%
  25. 25 Gemini 3.5 Flash-Lite 55.7%

Source: Official Immigration Bench leaderboard

#ModelScoreSettingDateSource
1 Claude Fable 5.1 75.4% Sep 2026 Official leaderboard
2 Claude Fable 5.2 74% Nov 2026 Official leaderboard
3 Claude Opus 5.5 72.1% Sep 2026 Official leaderboard
4 Muse Wonder Full 71.2% Oct 2026 Official leaderboard
5 Qwen 3.8 Max 70.1% Aug 2026 Official leaderboard
6 Muse Wonder 69.6% Oct 2026 Official leaderboard
7 Claude Sonnet 5.5 69% Sep 2026 Official leaderboard
8 Kimi K3 68.3% Jul 2026 Official leaderboard
9 Gemini 4 Argon 68.1% Sep 2026 Official leaderboard
10 Grok 4.7 68% Sep 2026 Official leaderboard
11 GPT-6.1 Sol 67.8% Sep 2026 Official leaderboard
12 GPT-6 Astra 67.7% Sep 2026 Official leaderboard
13 MiMo-V2.6 Pro 67.5% Sep 2026 Official leaderboard
14 GLM-5.3 66.7% Aug 2026 Official leaderboard
15 Muse Spark 1.2 66.5% Aug 2026 Official leaderboard
16 Grok 4.6 66% Aug 2026 Official leaderboard
17 DeepSeek V4.1 Flash 65.6% Sep 2026 Official leaderboard
18 Muse Spark 1.3 65% Sep 2026 Official leaderboard
19 Mistral Large 4 Preview 63.7% Oct 2026 Official leaderboard
20 Gemini 3.8 Flash 63.4% Sep 2026 Official leaderboard
21 GPT-6 Luna 62.5% Sep 2026 Official leaderboard
22 Claude Haiku 5.5 61.8% Oct 2026 Official leaderboard
23 DeepSeek V4 Pro 0813 61.7% Aug 2026 Official leaderboard
24 MiniMax-M3 57.5% Jun 2026 Official leaderboard
25 Gemini 3.5 Flash-Lite 55.7% Jul 2026 Official leaderboard

The best score, 75.4%, costs $2.11 a task

Runs on the cost frontier score higher than any run that's cheaper. Muse Wonder Full comes within 4.2 points of the best for $0.39 a task, 5 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Qwen Anthropic Xiaomi Corp OpenAI Meta Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 Cost per task, log scale Claude Fable 5.1 Claude Fable 5.2 Qwen 3.8 Max MiMo-V2.6 Pro GPT-6 Luna 0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 Cost per task, log scale Claude Fable 5.1 Qwen 3.8 Max

Source: Official Immigration Bench leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5.1 75.4% $2.11
Claude Fable 5.2 74% $0.64
Claude Opus 5.5 72.1% $2.16
Muse Wonder Full 71.2% $0.39
Qwen 3.8 Max 70.1% $0.12
Muse Wonder 69.6% $0.30
Claude Sonnet 5.5 69% $1.16
Kimi K3 68.3% $0.18
Gemini 4 Argon 68.1% $0.51
Grok 4.7 68% $0.24
GPT-6.1 Sol 67.8% $0.23
GPT-6 Astra 67.7% $1.37
MiMo-V2.6 Pro 67.5% $0.02
GLM-5.3 66.7% $0.12
Muse Spark 1.2 66.5% $0.04
Grok 4.6 66% $0.10
DeepSeek V4.1 Flash 65.6% $0.05
Muse Spark 1.3 65% $0.05
Muse Spark 1.3 max 64.9% $0.06
Mistral Large 4 Preview 63.7% $0.15
Gemini 3.8 Flash 63.4% $0.17
GPT-6 Luna 62.5% $0.01
Claude Haiku 5.5 61.8% $0.09
DeepSeek V4 Pro 0813 61.7% $0.05
MiniMax-M3 57.5% $0.04
Gemini 3.5 Flash-Lite 55.7% $0.02

Number one over time

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

Anthropic
Own leaderboard 1 leader
Claude Fable 5.1 75.4%

Source: Official Immigration Bench 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% 2026 2027 Near the ceiling (85%) Claude Fable 5.1 Qwen 3.8 Max MiniMax-M3 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5.1 Kimi K3

Source: Official Immigration Bench 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%