Benchmark Almanac

GPBam

Claude Opus 5 76.4 leads since November 2026
Not in model cards

Models write legal opinions on German public law cases and retrieve the statutes they need. Three judges grade essays against reference solutions.

Released
November 2026
Kind
Law
Level
Expert
Scored
Graded by a model
Answers
Open-ended
Tasks
Public, plus a private test set
Measures
Capability
Subject
Law
Language
German
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
In views
Law and finance
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
August 2026
Scores refreshed
November 20th, 2026
32
Entries in its paper, 24 models we track

Claude Opus 5 leads with 76.4 among models released by August 2026 Claude Opus 5 leads with 76.4 among models released by August 2026

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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.

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

  1. 1 Claude Opus 5 No retrieval 76.4
  2. 2 Gemini 3.7 Flash No retrieval 67.1
  3. 3 DeepSeek-V4-Flash cite+LS+RRF k=50 47.9
  4. 4 Qwen3.5 397B-A17B No retrieval 41.5
  5. 5 Mistral Large 3 No retrieval 37.8
  6. 6 Mistral Medium 3.5 No retrieval 37.4
  7. 7 DeepSeek-V3.2 No retrieval 36.8
  8. 8 RedHatAI/gemma-4-31B-it-FP8-block cite+RRF 36.3
  9. 9 Gemini 2.5 Flash-Lite Sep 2025, No retrieval 35.2
  10. 10 GPT-5 mini No retrieval 34.8
  11. 11 Claude Haiku 4.5 No retrieval 34.8
  12. 12 DeepSeek-R1 May 2025, No retrieval 33.2
  13. 13 Qwen 3.6 35B-A3B cite+RRF k=50 33.1
  14. 14 Qwen3.5-122B-A10B No retrieval 33.0
  15. 15 Qwen3-Next-80B-A3B-Instruct cite-only 32.6
  16. 16 gpt-oss-120b cite-only 32.4
  17. 17 Qwen3-235B-A22B-Thinking Jul 2025, No retrieval 31.1
  18. 18 DeepSeek-V3 Mar 2025, No retrieval 26.4
  19. 19 soofi-s-isar-preview No retrieval 26.1
  20. 20 Llama 4 Maverick No retrieval 24.4
  21. 21 GaleneAI/Magistral-Small-2509-FP8-Dynamic No retrieval 23.3
  22. 22 RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-FP8 LS text 22.9
  23. 23 GPT-5 nano No retrieval 21.5
  24. 24 GPT-4o mini No retrieval 19.5
  25. 25 windprak/open_steuerllm No retrieval 17.8
  26. 26 Llama 3.3 70B Instruct No retrieval 16.8
  27. 27 Qwen3-32B No retrieval 13.2
  28. 28 utter-project/EuroLLM-22B-Instruct-2512 No retrieval 9.26
  29. 29 Ministral 3 14B No retrieval 8.77
  30. 30 ibm-granite/granite-4.1-3b No retrieval 7.53
  31. 31 Phi-4 Mini No retrieval 5.43
  32. 32 meta-llama/llama-3.1-8b-instruct No retrieval 4.81

Source: The GPBam paper

Source: The GPBam paper

#EntryScoreSettingDateSource
1 Claude Opus 5 76.4 No retrieval, Claude Code Jul 2026 Official leaderboard
2 Gemini 3.7 Flash 67.1 No retrieval Aug 2026 Official leaderboard
3 DeepSeek-V4-Flash 47.9 cite+LS+RRF k=50 Apr 2026 Official leaderboard
4 Qwen3.5 397B-A17B 41.5 No retrieval Feb 2026 Official leaderboard
5 Mistral Large 3 37.8 No retrieval Dec 2025 Official leaderboard
6 Mistral Medium 3.5 37.4 No retrieval Apr 2026 Official leaderboard
7 DeepSeek-V3.2 36.8 No retrieval Dec 2025 Official leaderboard
8 RedHatAI/gemma-4-31B-it-FP8-block 36.3 cite+RRF Official leaderboard
9 Gemini 2.5 Flash-Lite Sep 2025 35.2 No retrieval Sep 2025 Official leaderboard
10 GPT-5 mini 34.8 No retrieval Aug 2025 Official leaderboard
11 Claude Haiku 4.5 34.8 No retrieval Oct 2025 Official leaderboard
12 DeepSeek-R1 May 2025 33.2 No retrieval May 2025 Official leaderboard
13 Qwen 3.6 35B-A3B 33.1 cite+RRF k=50 Apr 2026 Official leaderboard
14 Qwen3.5-122B-A10B 33.0 No retrieval Feb 2026 Official leaderboard
15 Qwen3-Next-80B-A3B-Instruct 32.6 cite-only Sep 2025 Official leaderboard
16 gpt-oss-120b 32.4 cite-only Aug 2025 Official leaderboard
17 Qwen3-235B-A22B-Thinking Jul 2025 31.1 No retrieval Jul 2025 Official leaderboard
18 DeepSeek-V3 Mar 2025 26.4 No retrieval Mar 2025 Official leaderboard
19 soofi-s-isar-preview 26.1 No retrieval Official leaderboard
20 Llama 4 Maverick 24.4 No retrieval Apr 2025 Official leaderboard
21 GaleneAI/Magistral-Small-2509-FP8-Dynamic 23.3 No retrieval Official leaderboard
22 RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-FP8 22.9 LS text Official leaderboard
23 GPT-5 nano 21.5 No retrieval Aug 2025 Official leaderboard
24 GPT-4o mini 19.5 No retrieval Jul 2024 Official leaderboard
25 windprak/open_steuerllm 17.8 No retrieval Official leaderboard
26 Llama 3.3 70B Instruct 16.8 No retrieval Dec 2024 Official leaderboard
27 Qwen3-32B 13.2 No retrieval Apr 2025 Official leaderboard
28 utter-project/EuroLLM-22B-Instruct-2512 9.26 No retrieval Official leaderboard
29 Ministral 3 14B 8.77 No retrieval Dec 2025 Official leaderboard
30 ibm-granite/granite-4.1-3b 7.53 No retrieval Official leaderboard
31 Phi-4 Mini 5.43 No retrieval Feb 2025 Official leaderboard
32 meta-llama/llama-3.1-8b-instruct 4.81 No retrieval Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 5 76.4 No retrieval, Claude Code Jul 2026 Official leaderboard
2 Gemini 3.7 Flash 67.1 No retrieval Aug 2026 Official leaderboard
3 DeepSeek-V4-Flash 47.9 cite+LS+RRF k=50 Apr 2026 Official leaderboard
4 Qwen3.5 397B-A17B 41.5 No retrieval Feb 2026 Official leaderboard
5 Mistral Large 3 37.8 No retrieval Dec 2025 Official leaderboard
6 Mistral Medium 3.5 37.4 No retrieval Apr 2026 Official leaderboard
7 DeepSeek-V3.2 36.8 No retrieval Dec 2025 Official leaderboard
8 Gemini 2.5 Flash-Lite Sep 2025 35.2 No retrieval Sep 2025 Official leaderboard
9 GPT-5 mini 34.8 No retrieval Aug 2025 Official leaderboard
10 Claude Haiku 4.5 34.8 No retrieval Oct 2025 Official leaderboard
11 DeepSeek-R1 May 2025 33.2 No retrieval May 2025 Official leaderboard
12 Qwen 3.6 35B-A3B 33.1 cite+RRF k=50 Apr 2026 Official leaderboard
13 Qwen3.5-122B-A10B 33.0 No retrieval Feb 2026 Official leaderboard
14 Qwen3-Next-80B-A3B-Instruct 32.6 cite-only Sep 2025 Official leaderboard
15 gpt-oss-120b 32.4 cite-only Aug 2025 Official leaderboard
16 Qwen3-235B-A22B-Thinking Jul 2025 31.1 No retrieval Jul 2025 Official leaderboard
17 DeepSeek-V3 Mar 2025 26.4 No retrieval Mar 2025 Official leaderboard
18 Llama 4 Maverick 24.4 No retrieval Apr 2025 Official leaderboard
19 GPT-5 nano 21.5 No retrieval Aug 2025 Official leaderboard
20 GPT-4o mini 19.5 No retrieval Jul 2024 Official leaderboard
21 Llama 3.3 70B Instruct 16.8 No retrieval Dec 2024 Official leaderboard
22 Qwen3-32B 13.2 No retrieval Apr 2025 Official leaderboard
23 Ministral 3 14B 8.77 No retrieval Dec 2025 Official leaderboard
24 Phi-4 Mini 5.43 No retrieval Feb 2025 Official leaderboard

The best score, 76.4, costs $63 for the full run

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.

OpenAI Meta DeepSeek Mistral AI Anthropic Google DeepMind Cost frontier One model at each effort level
0.00 20.0 40.0 60.0 80.0 $0.01 $0.10 $1.00 $10 $100 Cost of the full run, log scale Claude Opus 5, No retrieval Gemini 3.7 Flash, No retrieval Mistral Large 3, No retrieval gpt-oss-120b, No retrieval DeepSeek-V3, No retrieval GPT-4o mini, No retrieval Llama 3.3 70B Instruct, No retrieval 0.00 20.0 40.0 60.0 80.0 $0.01 $0.10 $1.00 $10 $100 Cost of the full run, log scale Claude Opus 5, No retrieval Gemini 3.7 Flash, No retrieval

Source: The GPBam paper

ModelEffortHarnessScoreCost of the full runOutput tokens
Claude Opus 5 No retrieval Claude Code 76.4 $63
Gemini 3.7 Flash No retrieval 67.1 $2.12
DeepSeek-V4-Flash cite+LS+RRF k=50 47.9
DeepSeek-V4-Flash RRF 45.1
DeepSeek-V4-Flash RRF k=50 44.8
DeepSeek-V4-Flash cite-only 44.4
DeepSeek-V4-Flash rerank 43.8
DeepSeek-V4-Flash No retrieval 43.8
DeepSeek-V4-Flash cite+RRF k=50 43.1
DeepSeek-V4-Flash LS text 43.0
DeepSeek-V4-Flash cite+RRF 42.8
Qwen3.5 397B-A17B No retrieval 41.5 $2.33
Mistral Large 3 No retrieval 37.8 $0.60
Mistral Medium 3.5 No retrieval 37.4 $10
DeepSeek-V3.2 No retrieval 36.8 $0.26
Gemini 2.5 Flash-Lite Sep 2025 No retrieval 35.2 $0.51
GPT-5 mini No retrieval 34.8 $3.32
Claude Haiku 4.5 No retrieval 34.8 $8.23
DeepSeek-R1 May 2025 No retrieval 33.2 $1.14
Qwen 3.6 35B-A3B cite+RRF k=50 33.1
Qwen 3.6 35B-A3B cite+LS+RRF k=50 33.1
Qwen3.5-122B-A10B No retrieval 33.0 $1.77
Qwen 3.6 35B-A3B cite-only 33.0
Qwen 3.6 35B-A3B rerank 32.7
Qwen3-Next-80B-A3B-Instruct cite-only 32.6
Qwen 3.6 35B-A3B RRF k=50 32.6
gpt-oss-120b cite-only 32.4
gpt-oss-120b cite+RRF 32.4
Qwen 3.6 35B-A3B LS text 32.0
Qwen3-Next-80B-A3B-Instruct cite+RRF 31.6
Qwen 3.6 35B-A3B RRF 31.5
Qwen3-Next-80B-A3B-Instruct cite+LS+RRF k=50 31.2
Qwen3-235B-A22B-Thinking Jul 2025 No retrieval 31.1 $1.75
Qwen 3.6 35B-A3B cite+RRF 31.1
Qwen3-Next-80B-A3B-Instruct LS text 31.0
gpt-oss-120b cite+LS+RRF k=50 30.6
Qwen3-Next-80B-A3B-Instruct No retrieval 30.6 $0.53
Qwen3-Next-80B-A3B-Instruct cite+RRF k=50 30.6
Qwen 3.6 35B-A3B No retrieval 30.6 $0.75
gpt-oss-120b cite+RRF k=50 30.5
gpt-oss-120b LS text 30.3
gpt-oss-120b No retrieval 29.8 $0.19
Qwen3-Next-80B-A3B-Instruct rerank 29.7
Qwen3-Next-80B-A3B-Instruct RRF k=50 29.5
gpt-oss-120b RRF 29.3
gpt-oss-120b rerank 28.9
Qwen3-Next-80B-A3B-Instruct RRF 28.5
gpt-oss-120b RRF k=50 28.5
DeepSeek-V3 Mar 2025 No retrieval 26.4 $0.18
Llama 4 Maverick No retrieval 24.4 $0.16
GPT-5 nano No retrieval 21.5 $0.43
GPT-4o mini No retrieval 19.5 $0.09
Llama 3.3 70B Instruct No retrieval 16.8 $0.09
Qwen3-32B No retrieval 13.2 $0.15
Ministral 3 14B No retrieval 8.77 $0.12
Phi-4 Mini No retrieval 5.43

The best score, 76.4, costs $63 for the full run

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.

OpenAI Meta DeepSeek Mistral AI Anthropic Google DeepMind Cost frontier One model at each effort level
0.00 20.0 40.0 60.0 80.0 $0.01 $0.10 $1.00 $10 $100 Cost of the full run, log scale Claude Opus 5, No retrieval Gemini 3.7 Flash, No retrieval Mistral Large 3, No retrieval gpt-oss-120b, No retrieval DeepSeek-V3, No retrieval GPT-4o mini, No retrieval Llama 3.3 70B Instruct, No retrieval 0.00 20.0 40.0 60.0 80.0 $0.01 $0.10 $1.00 $10 $100 Cost of the full run, log scale Claude Opus 5, No retrieval Gemini 3.7 Flash, No retrieval

Source: The GPBam paper

ModelEffortHarnessScoreCost of the full runOutput tokens
Claude Opus 5 No retrieval Claude Code 76.4 $63
Gemini 3.7 Flash No retrieval 67.1 $2.12
DeepSeek-V4-Flash cite+LS+RRF k=50 47.9
DeepSeek-V4-Flash RRF 45.1
DeepSeek-V4-Flash RRF k=50 44.8
DeepSeek-V4-Flash cite-only 44.4
DeepSeek-V4-Flash rerank 43.8
DeepSeek-V4-Flash No retrieval 43.8
DeepSeek-V4-Flash cite+RRF k=50 43.1
DeepSeek-V4-Flash LS text 43.0
DeepSeek-V4-Flash cite+RRF 42.8
Qwen3.5 397B-A17B No retrieval 41.5 $2.33
Mistral Large 3 No retrieval 37.8 $0.60
Mistral Medium 3.5 No retrieval 37.4 $10
DeepSeek-V3.2 No retrieval 36.8 $0.26
Gemini 2.5 Flash-Lite Sep 2025 No retrieval 35.2 $0.51
GPT-5 mini No retrieval 34.8 $3.32
Claude Haiku 4.5 No retrieval 34.8 $8.23
DeepSeek-R1 May 2025 No retrieval 33.2 $1.14
Qwen 3.6 35B-A3B cite+RRF k=50 33.1
Qwen 3.6 35B-A3B cite+LS+RRF k=50 33.1
Qwen3.5-122B-A10B No retrieval 33.0 $1.77
Qwen 3.6 35B-A3B cite-only 33.0
Qwen 3.6 35B-A3B rerank 32.7
Qwen3-Next-80B-A3B-Instruct cite-only 32.6
Qwen 3.6 35B-A3B RRF k=50 32.6
gpt-oss-120b cite-only 32.4
gpt-oss-120b cite+RRF 32.4
Qwen 3.6 35B-A3B LS text 32.0
Qwen3-Next-80B-A3B-Instruct cite+RRF 31.6
Qwen 3.6 35B-A3B RRF 31.5
Qwen3-Next-80B-A3B-Instruct cite+LS+RRF k=50 31.2
Qwen3-235B-A22B-Thinking Jul 2025 No retrieval 31.1 $1.75
Qwen 3.6 35B-A3B cite+RRF 31.1
Qwen3-Next-80B-A3B-Instruct LS text 31.0
gpt-oss-120b cite+LS+RRF k=50 30.6
Qwen3-Next-80B-A3B-Instruct No retrieval 30.6 $0.53
Qwen3-Next-80B-A3B-Instruct cite+RRF k=50 30.6
Qwen 3.6 35B-A3B No retrieval 30.6 $0.75
gpt-oss-120b cite+RRF k=50 30.5
gpt-oss-120b LS text 30.3
gpt-oss-120b No retrieval 29.8 $0.19
Qwen3-Next-80B-A3B-Instruct rerank 29.7
Qwen3-Next-80B-A3B-Instruct RRF k=50 29.5
gpt-oss-120b RRF 29.3
gpt-oss-120b rerank 28.9
Qwen3-Next-80B-A3B-Instruct RRF 28.5
gpt-oss-120b RRF k=50 28.5
DeepSeek-V3 Mar 2025 No retrieval 26.4 $0.18
Llama 4 Maverick No retrieval 24.4 $0.16
GPT-5 nano No retrieval 21.5 $0.43
GPT-4o mini No retrieval 19.5 $0.09
Llama 3.3 70B Instruct No retrieval 16.8 $0.09
Qwen3-32B No retrieval 13.2 $0.15
Ministral 3 14B No retrieval 8.77 $0.12
Phi-4 Mini No retrieval 5.43

Number one over time

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

Anthropic
Benchmark paper 1 leader

Source: The GPBam paper

Scores over time

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

Plot with other benchmarks
In the benchmark’s paper
0.00 20.0 40.0 60.0 80.0 2025 2026 0.00 20.0 40.0 60.0 80.0 2025 2026

Source: Official GPBam leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Law, finance and medicine

All 637 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 9 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 3 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (32 entries).
  • Pass Models scored 24 models we track, plus 8 other entries on its leaderboard.
  • Pass Newest score The newest is from August 2026, for Gemini 3.7 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 56 rows for models we track and 8 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check