Benchmark Almanac

CaseLaw v2

Grok 4.3 79.3% leads since April 2026
Not in model cards

Models answer private questions over recent Canadian court decisions, such as finding key cases and answering across several documents.

Replaced the original CaseLaw benchmark after models neared 90% on it. Updated March 2nd, 2026 and archived as saturated, last run May 4th, 2026 with 54 models.

Released
August 2025
Kind
Law
Level
Expert
Scored
Graded by a model
Answers
Open-ended
Tasks
Kept private
Strongest model tested
GPT-5.5 #20 on the capability index
Last model added
April 2026
Scores refreshed
November 12th, 2026
53
Models scored on its own leaderboard

Grok 4.3 leads with 79.3% among models released by April 2026

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.

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

53 models. Scroll sideways for the rest.

  1. 79.3 Grok 4.3
  2. 73.4 GPT-5.1
  3. 69.9 GPT-4.1
  4. 68.5 GPT-5 mini
  5. 68.4 Claude Opus 4.7
  6. 66.5 GPT-5
  7. 66.2 GPT-5.5
  8. 66.0 GPT-5.2
  9. 65.8 Grok 4
  10. 65.7 Grok 4 Fast
  11. 65.7 Kimi K2 Thinking
  12. 64.8 Gemini 3.1 Pro
  13. 64.5 Cohere Command A
  14. 64.0 Claude Sonnet 4.6
  15. 63.9 Gemini 2.5 Pro
  16. 63.8 GPT-5.4
  17. 63.1 Muse Spark
  18. 62.6 Claude Opus 4.5
  19. 62.2 Claude Sonnet 4.5
  20. 62.1 Claude Opus 4.6
  21. 61.4 Mistral Large 3
  22. 61.2 Kimi K2.6
  23. 60.9 MiniMax-M2.7
  24. 60.5 Grok 4.1 Fast
  25. 59.7 GPT-4o
  26. 59.7 Qwen 3.5 Plus (hosted 397B-A17B)
  27. 59.4 DeepSeek-V4-Pro
  28. 58.7 Kimi K2.5
  29. 57.9 Trinity Large Thinking
  30. 56.5 Claude Haiku 4.5
  31. 56.0 Qwen 3.5 Flash (hosted 35B-A3B)
  32. 55.8 Gemini 3 Flash
  33. 55.8 MiniMax-M2.1
  34. 55.4 DeepSeek-V3.2
  35. 55.0 Qwen3-Max
  36. 55.0 Gemini 3.1 Flash-Lite
  37. 54.9 GLM-4.7
  38. 54.5 Grok 4.20
  39. 53.9 DeepSeek-V3.1
  40. 53.5 MiniMax-M2.5
  41. 53.2 Qwen3.6 27B
  42. 53.0 Gemini 3 Pro
  43. 52.6 GPT-5 nano
  44. 52.6 Gemma 4 31B IT
  45. 52.5 GLM-5
  46. 51.9 GPT-5.4 Nano
  47. 51.7 GPT-5.4 Mini
  48. 51.5 GLM-5.1
  49. 51.5 Qwen 3.6 Plus
  50. 48.8 gpt-oss-120b
  51. 47.9 Qwen 3.6 Max (Preview)
  52. 44.2 Mistral Medium 3.5
  53. 43.8 gpt-oss-20b
  1. 1 Grok 4.3 79.3%
  2. 2 GPT-5.1 73.4%
  3. 3 GPT-4.1 69.9%
  4. 4 GPT-5 mini 68.5%
  5. 5 Claude Opus 4.7 68.4%
  6. 6 GPT-5 66.5%
  7. 7 GPT-5.5 66.2%
  8. 8 GPT-5.2 66%
  9. 9 Grok 4 65.8%
  10. 10 Grok 4 Fast reasoning 65.7%
  11. 11 Kimi K2 Thinking 65.7%
  12. 12 Gemini 3.1 Pro 64.8%
  13. 13 Cohere Command A 64.5%
  14. 14 Claude Sonnet 4.6 64%
  15. 15 Gemini 2.5 Pro Jun 2025 63.9%
  16. 16 GPT-5.4 xhigh 63.8%
  17. 17 Muse Spark 63.1%
  18. 18 Claude Opus 4.5 thinking 62.6%
  19. 19 Claude Sonnet 4.5 thinking 62.2%
  20. 20 Claude Opus 4.6 thinking 62.1%
  21. 21 Mistral Large 3 61.4%
  22. 22 Kimi K2.6 61.2%
  23. 23 MiniMax-M2.7 60.9%
  24. 24 Grok 4.1 Fast reasoning 60.5%
  25. 25 GPT-4o Aug 2024 59.7%
  26. 26 Qwen 3.5 Plus (hosted 397B-A17B) thinking 59.7%
  27. 27 DeepSeek-V4-Pro 59.4%
  28. 28 Kimi K2.5 thinking 58.7%
  29. 29 Trinity Large Thinking 57.9%
  30. 30 Claude Haiku 4.5 thinking 56.5%
  31. 31 Qwen 3.5 Flash (hosted 35B-A3B) 56%
  32. 32 Gemini 3 Flash 55.8%
  33. 33 MiniMax-M2.1 55.8%
  34. 34 DeepSeek-V3.2 thinking 55.4%
  35. 35 Qwen3-Max 55%
  36. 36 Gemini 3.1 Flash-Lite 55%
  37. 37 GLM-4.7 54.9%
  38. 38 Grok 4.20 reasoning 54.5%
  39. 39 DeepSeek-V3.1 53.9%
  40. 40 MiniMax-M2.5 53.5%
  41. 41 Qwen3.6 27B 53.2%
  42. 42 Gemini 3 Pro 53%
  43. 43 GPT-5 nano 52.6%
  44. 44 Gemma 4 31B IT 52.6%
  45. 45 GLM-5 thinking 52.5%
  46. 46 GPT-5.4 Nano 51.9%
  47. 47 GPT-5.4 Mini 51.7%
  48. 48 GLM-5.1 51.5%
  49. 49 Qwen 3.6 Plus 51.5%
  50. 50 gpt-oss-120b 48.8%
  51. 51 Qwen 3.6 Max (Preview) 47.9%
  52. 52 Mistral Medium 3.5 44.2%
  53. 53 gpt-oss-20b 43.8%

Source: Official CaseLaw v2 leaderboard

#ModelScoreSettingDateSource
1 Grok 4.3 79.3% Apr 2026 Official leaderboard
2 GPT-5.1 73.4% Nov 2025 Official leaderboard
3 GPT-4.1 69.9% Apr 2025 Official leaderboard
4 GPT-5 mini 68.5% Aug 2025 Official leaderboard
5 Claude Opus 4.7 68.4% Apr 2026 Official leaderboard
6 GPT-5 66.5% Aug 2025 Official leaderboard
7 GPT-5.5 66.2% Apr 2026 Official leaderboard
8 GPT-5.2 66% Dec 2025 Official leaderboard
9 Grok 4 65.8% Jul 2025 Official leaderboard
10 Grok 4 Fast 65.7% reasoning Sep 2025 Official leaderboard
11 Kimi K2 Thinking 65.7% Nov 2025 Official leaderboard
12 Gemini 3.1 Pro 64.8% Feb 2026 Official leaderboard
13 Cohere Command A 64.5% Mar 2025 Official leaderboard
14 Claude Sonnet 4.6 64% Feb 2026 Official leaderboard
15 Gemini 2.5 Pro Jun 2025 63.9% Jun 2025 Official leaderboard
16 GPT-5.4 63.8% xhigh Mar 2026 Official leaderboard
17 Muse Spark 63.1% Apr 2026 Official leaderboard
18 Claude Opus 4.5 62.6% thinking Nov 2025 Official leaderboard
19 Claude Sonnet 4.5 62.2% thinking Sep 2025 Official leaderboard
20 Claude Opus 4.6 62.1% thinking Feb 2026 Official leaderboard
21 Mistral Large 3 61.4% Dec 2025 Official leaderboard
22 Kimi K2.6 61.2% Apr 2026 Official leaderboard
23 MiniMax-M2.7 60.9% Mar 2026 Official leaderboard
24 Grok 4.1 Fast 60.5% reasoning Nov 2025 Official leaderboard
25 GPT-4o Aug 2024 59.7% Aug 2024 Official leaderboard
26 Qwen 3.5 Plus (hosted 397B-A17B) 59.7% thinking Feb 2026 Official leaderboard
27 DeepSeek-V4-Pro 59.4% Apr 2026 Official leaderboard
28 Kimi K2.5 58.7% thinking Jan 2026 Official leaderboard
29 Trinity Large Thinking 57.9% Apr 2026 Official leaderboard
30 Claude Haiku 4.5 56.5% thinking Oct 2025 Official leaderboard
31 Qwen 3.5 Flash (hosted 35B-A3B) 56% Feb 2026 Official leaderboard
32 Gemini 3 Flash 55.8% Dec 2025 Official leaderboard
33 MiniMax-M2.1 55.8% Dec 2025 Official leaderboard
34 DeepSeek-V3.2 55.4% thinking Dec 2025 Official leaderboard
35 Qwen3-Max 55% Sep 2025 Official leaderboard
36 Gemini 3.1 Flash-Lite 55% Mar 2026 Official leaderboard
37 GLM-4.7 54.9% Dec 2025 Official leaderboard
38 Grok 4.20 54.5% reasoning Feb 2026 Official leaderboard
39 DeepSeek-V3.1 53.9% Aug 2025 Official leaderboard
40 MiniMax-M2.5 53.5% Feb 2026 Official leaderboard
41 Qwen3.6 27B 53.2% Apr 2026 Official leaderboard
42 Gemini 3 Pro 53% Nov 2025 Official leaderboard
43 GPT-5 nano 52.6% Aug 2025 Official leaderboard
44 Gemma 4 31B IT 52.6% Apr 2026 Official leaderboard
45 GLM-5 52.5% thinking Feb 2026 Official leaderboard
46 GPT-5.4 Nano 51.9% Mar 2026 Official leaderboard
47 GPT-5.4 Mini 51.7% Mar 2026 Official leaderboard
48 GLM-5.1 51.5% Apr 2026 Official leaderboard
49 Qwen 3.6 Plus 51.5% Mar 2026 Official leaderboard
50 gpt-oss-120b 48.8% Aug 2025 Official leaderboard
51 Qwen 3.6 Max (Preview) 47.9% Apr 2026 Official leaderboard
52 Mistral Medium 3.5 44.2% Apr 2026 Official leaderboard
53 gpt-oss-20b 43.8% Aug 2025 Official leaderboard

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.

40% 60% 80% 100% 1101001,000 Latency (mean per test) (s), log scale, lower is better Accuracy GPT-4o: Accuracy 59.7%, latency (mean per test) 40.9 s Cohere Command A: Accuracy 64.5%, latency (mean per test) 41.6 s Gemini 2.5 Pro: Accuracy 63.9%, latency (mean per test) 44 s Grok 4: Accuracy 65.8%, latency (mean per test) 32.3 s gpt-oss-120b: Accuracy 48.8%, latency (mean per test) 68.3 s gpt-oss-20b: Accuracy 43.8%, latency (mean per test) 85.7 s GPT-5: Accuracy 66.5%, latency (mean per test) 123 s GPT-5 mini: Accuracy 68.5%, latency (mean per test) 42.5 s GPT-5 nano: Accuracy 52.6%, latency (mean per test) 56.5 s DeepSeek-V3.1: Accuracy 53.9%, latency (mean per test) 40.7 s Grok 4 Fast (reasoning): Accuracy 65.7%, latency (mean per test) 23.7 s Qwen3-Max: Accuracy 55%, latency (mean per test) 134 s Qwen3-Max: Accuracy 47.5%, latency (mean per test) 84.7 s Claude Sonnet 4.5 (thinking): Accuracy 62.2%, latency (mean per test) 25.4 s Claude Haiku 4.5 (thinking): Accuracy 56.5%, latency (mean per test) 32.9 s Kimi K2 Thinking: Accuracy 65.7%, latency (mean per test) 91 s Gemini 3 Pro: Accuracy 53%, latency (mean per test) 32.3 s Grok 4.1 Fast (reasoning): Accuracy 60.5%, latency (mean per test) 19.1 s Claude Opus 4.5 (thinking): Accuracy 62.6%, latency (mean per test) 16.8 s DeepSeek-V3.2 (thinking): Accuracy 55.4%, latency (mean per test) 66.1 s Mistral Large 3: Accuracy 61.4%, latency (mean per test) 40.8 s GPT-5.2: Accuracy 66%, latency (mean per test) 86.2 s Gemini 3 Flash: Accuracy 55.8%, latency (mean per test) 261 s GLM-4.7: Accuracy 54.9%, latency (mean per test) 59.6 s MiniMax-M2.1: Accuracy 55.8%, latency (mean per test) 37.4 s Kimi K2.5 (thinking): Accuracy 58.7%, latency (mean per test) 241 s Claude Opus 4.6 (thinking): Accuracy 62.1%, latency (mean per test) 32.3 s GLM-5 (thinking): Accuracy 52.5%, latency (mean per test) 118 s MiniMax-M2.5: Accuracy 53.5%, latency (mean per test) 30.9 s Qwen 3.5 Plus (hosted 397B-A17B) (thinking): Accuracy 59.7%, latency (mean per test) 94.7 s Claude Sonnet 4.6: Accuracy 64%, latency (mean per test) 36.2 s Grok 4.20 (reasoning): Accuracy 54.5%, latency (mean per test) 10.7 s Gemini 3.1 Pro: Accuracy 64.8%, latency (mean per test) 56.8 s Qwen 3.5 Flash (hosted 35B-A3B): Accuracy 56%, latency (mean per test) 43.5 s GPT-5.4 (xhigh): Accuracy 63.8%, latency (mean per test) 56.8 s GPT-5.4 Mini: Accuracy 51.7%, latency (mean per test) 57.7 s GPT-5.4 Nano: Accuracy 51.9%, latency (mean per test) 7.62 s MiniMax-M2.7: Accuracy 60.9%, latency (mean per test) 21.6 s Qwen 3.6 Plus: Accuracy 51.5%, latency (mean per test) 43.9 s Trinity Large Thinking: Accuracy 57.9%, latency (mean per test) 14.6 s Gemma 4 31B IT: Accuracy 52.6%, latency (mean per test) 28.7 s GLM-5.1: Accuracy 51.5%, latency (mean per test) 49 s Muse Spark: Accuracy 63.1%, latency (mean per test) 61.9 s Claude Opus 4.7: Accuracy 68.4%, latency (mean per test) 17.7 s Kimi K2.6: Accuracy 61.2%, latency (mean per test) 46.1 s Qwen 3.6 Max (Preview): Accuracy 47.9%, latency (mean per test) 42.9 s Qwen3.6 27B: Accuracy 53.2%, latency (mean per test) 42.5 s GPT-5.5: Accuracy 66.2%, latency (mean per test) 25.2 s DeepSeek-V4-Pro: Accuracy 59.4%, latency (mean per test) 48.4 s Mistral Medium 3.5: Accuracy 44.2%, latency (mean per test) 64.6 s GPT-4.1: Accuracy 69.9%, latency (mean per test) 6.66 s GPT-5.1: Accuracy 73.4%, latency (mean per test) 23.6 s Gemini 3.1 Flash-Lite: Accuracy 55%, latency (mean per test) 4.64 s Grok 4.3: Accuracy 79.3%, latency (mean per test) 42.8 s Grok 4.3GPT-5.1GPT-4.1Gemini 3.1 Flash-Lite 40% 60% 80% 100% 1101001,000 Latency (mean per test) (s), log scale, lower is better Accuracy GPT-4o: Accuracy 59.7%, latency (mean per test) 40.9 s Cohere Command A: Accuracy 64.5%, latency (mean per test) 41.6 s Gemini 2.5 Pro: Accuracy 63.9%, latency (mean per test) 44 s Grok 4: Accuracy 65.8%, latency (mean per test) 32.3 s gpt-oss-120b: Accuracy 48.8%, latency (mean per test) 68.3 s gpt-oss-20b: Accuracy 43.8%, latency (mean per test) 85.7 s GPT-5: Accuracy 66.5%, latency (mean per test) 123 s GPT-5 mini: Accuracy 68.5%, latency (mean per test) 42.5 s GPT-5 nano: Accuracy 52.6%, latency (mean per test) 56.5 s DeepSeek-V3.1: Accuracy 53.9%, latency (mean per test) 40.7 s Grok 4 Fast (reasoning): Accuracy 65.7%, latency (mean per test) 23.7 s Qwen3-Max: Accuracy 55%, latency (mean per test) 134 s Qwen3-Max: Accuracy 47.5%, latency (mean per test) 84.7 s Claude Sonnet 4.5 (thinking): Accuracy 62.2%, latency (mean per test) 25.4 s Claude Haiku 4.5 (thinking): Accuracy 56.5%, latency (mean per test) 32.9 s Kimi K2 Thinking: Accuracy 65.7%, latency (mean per test) 91 s Gemini 3 Pro: Accuracy 53%, latency (mean per test) 32.3 s Grok 4.1 Fast (reasoning): Accuracy 60.5%, latency (mean per test) 19.1 s Claude Opus 4.5 (thinking): Accuracy 62.6%, latency (mean per test) 16.8 s DeepSeek-V3.2 (thinking): Accuracy 55.4%, latency (mean per test) 66.1 s Mistral Large 3: Accuracy 61.4%, latency (mean per test) 40.8 s GPT-5.2: Accuracy 66%, latency (mean per test) 86.2 s Gemini 3 Flash: Accuracy 55.8%, latency (mean per test) 261 s GLM-4.7: Accuracy 54.9%, latency (mean per test) 59.6 s MiniMax-M2.1: Accuracy 55.8%, latency (mean per test) 37.4 s Kimi K2.5 (thinking): Accuracy 58.7%, latency (mean per test) 241 s Claude Opus 4.6 (thinking): Accuracy 62.1%, latency (mean per test) 32.3 s GLM-5 (thinking): Accuracy 52.5%, latency (mean per test) 118 s MiniMax-M2.5: Accuracy 53.5%, latency (mean per test) 30.9 s Qwen 3.5 Plus (hosted 397B-A17B) (thinking): Accuracy 59.7%, latency (mean per test) 94.7 s Claude Sonnet 4.6: Accuracy 64%, latency (mean per test) 36.2 s Grok 4.20 (reasoning): Accuracy 54.5%, latency (mean per test) 10.7 s Gemini 3.1 Pro: Accuracy 64.8%, latency (mean per test) 56.8 s Qwen 3.5 Flash (hosted 35B-A3B): Accuracy 56%, latency (mean per test) 43.5 s GPT-5.4 (xhigh): Accuracy 63.8%, latency (mean per test) 56.8 s GPT-5.4 Mini: Accuracy 51.7%, latency (mean per test) 57.7 s GPT-5.4 Nano: Accuracy 51.9%, latency (mean per test) 7.62 s MiniMax-M2.7: Accuracy 60.9%, latency (mean per test) 21.6 s Qwen 3.6 Plus: Accuracy 51.5%, latency (mean per test) 43.9 s Trinity Large Thinking: Accuracy 57.9%, latency (mean per test) 14.6 s Gemma 4 31B IT: Accuracy 52.6%, latency (mean per test) 28.7 s GLM-5.1: Accuracy 51.5%, latency (mean per test) 49 s Muse Spark: Accuracy 63.1%, latency (mean per test) 61.9 s Claude Opus 4.7: Accuracy 68.4%, latency (mean per test) 17.7 s Kimi K2.6: Accuracy 61.2%, latency (mean per test) 46.1 s Qwen 3.6 Max (Preview): Accuracy 47.9%, latency (mean per test) 42.9 s Qwen3.6 27B: Accuracy 53.2%, latency (mean per test) 42.5 s GPT-5.5: Accuracy 66.2%, latency (mean per test) 25.2 s DeepSeek-V4-Pro: Accuracy 59.4%, latency (mean per test) 48.4 s Mistral Medium 3.5: Accuracy 44.2%, latency (mean per test) 64.6 s GPT-4.1: Accuracy 69.9%, latency (mean per test) 6.66 s GPT-5.1: Accuracy 73.4%, latency (mean per test) 23.6 s Gemini 3.1 Flash-Lite: Accuracy 55%, latency (mean per test) 4.64 s Grok 4.3: Accuracy 79.3%, latency (mean per test) 42.8 s Grok 4.3GPT-5.1GPT-4.1Gemini 3.1 Flash-Lite
ModelSettingAccuracyLatency (mean per test)
Grok 4.3 79.3% 42.81 s
GPT-5.1 73.4% 23.59 s
GPT-4.1 69.9% 6.66 s
GPT-5 mini 68.5% 42.51 s
Claude Opus 4.7 68.4% 17.68 s
GPT-5 66.5% 123.42 s
GPT-5.5 66.2% 25.2 s
GPT-5.2 66% 86.23 s
Grok 4 65.8% 32.34 s
Grok 4 Fast reasoning 65.7% 23.71 s
Kimi K2 Thinking 65.7% 91.05 s
Gemini 3.1 Pro 64.8% 56.79 s
Cohere Command A 64.5% 41.56 s
Claude Sonnet 4.6 64% 36.2 s
Gemini 2.5 Pro Jun 2025 63.9% 44.02 s
GPT-5.4 xhigh 63.8% 56.8 s
Muse Spark 63.1% 61.87 s
Claude Opus 4.5 thinking 62.6% 16.82 s
Claude Sonnet 4.5 thinking 62.2% 25.42 s
Claude Opus 4.6 thinking 62.1% 32.27 s
Mistral Large 3 61.4% 40.84 s
Kimi K2.6 61.2% 46.09 s
MiniMax-M2.7 60.9% 21.64 s
Grok 4.1 Fast reasoning 60.5% 19.09 s
GPT-4o Aug 2024 59.7% 40.87 s
Qwen 3.5 Plus (hosted 397B-A17B) thinking 59.7% 94.69 s
DeepSeek-V4-Pro 59.4% 48.44 s
Kimi K2.5 thinking 58.7% 241.28 s
Trinity Large Thinking 57.9% 14.55 s
Claude Haiku 4.5 thinking 56.5% 32.92 s
Qwen 3.5 Flash (hosted 35B-A3B) 56% 43.54 s
MiniMax-M2.1 55.8% 37.36 s
Gemini 3 Flash 55.8% 260.5 s
DeepSeek-V3.2 thinking 55.4% 66.08 s
Gemini 3.1 Flash-Lite 55% 4.64 s
Qwen3-Max 55% 133.87 s
GLM-4.7 54.9% 59.64 s
Grok 4.20 reasoning 54.5% 10.66 s
DeepSeek-V3.1 53.9% 40.68 s
MiniMax-M2.5 53.5% 30.88 s
Qwen3.6 27B 53.2% 42.49 s
Gemini 3 Pro 53.1% 32.35 s
Gemma 4 31B IT 52.6% 28.72 s
GPT-5 nano 52.6% 56.48 s
GLM-5 thinking 52.5% 117.98 s
GPT-5.4 Nano 51.9% 7.62 s
GPT-5.4 Mini 51.7% 57.68 s
GLM-5.1 51.6% 48.96 s
Qwen 3.6 Plus 51.5% 43.91 s
gpt-oss-120b 48.8% 68.35 s
Qwen 3.6 Max (Preview) 47.9% 42.93 s
Qwen3-Max 47.5% 84.73 s
Mistral Medium 3.5 44.2% 64.64 s
gpt-oss-20b 43.8% 85.7 s

The best score, 79.3%, costs $0.04 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.

OpenAI xAI MiniMax Meta Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Grok 4.3 GPT-5 mini Muse Spark MiniMax-M2.7 GPT-5.4 Nano 0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Grok 4.3 GPT-5 mini

Source: Official CaseLaw v2 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Grok 4.3 79.3% $0.04 2,134
GPT-5.1 73.4% $0.04 1,264
GPT-4.1 69.9% $0.05 301
GPT-5 mini 68.5% $0.01 2,641
Claude Opus 4.7 68.4% $0.16 1,315
GPT-5 66.5% $0.07 2,332
GPT-5.5 66.2% $0.15 1,183
GPT-5.2 66% $0.10 3,269
Grok 4 65.8% $0.16 1,071
Grok 4 Fast reasoning 65.7% $0.007 951
Kimi K2 Thinking 65.7% $0.02 2,139
Gemini 3.1 Pro 64.8% $0.14 1,789
Cohere Command A 64.5% $0.10 361
Claude Sonnet 4.6 64% $0.14 1,358
Gemini 2.5 Pro Jun 2025 63.9% $0.26 1,447
GPT-5.4 xhigh 63.8% $0.10 2,142
Muse Spark 63.1% $0.007
Claude Opus 4.5 thinking 62.6% $0.23 963
Claude Sonnet 4.5 thinking 62.2% $0.26 1,373
Claude Opus 4.6 thinking 62.1% $0.23 946
Mistral Large 3 61.4% $0.02 397
Kimi K2.6 61.2% $0.03 2,325
MiniMax-M2.7 60.9% $0.003 691
Grok 4.1 Fast reasoning 60.5% $0.01 962
GPT-4o Aug 2024 59.7% $0.07 248
Qwen 3.5 Plus (hosted 397B-A17B) thinking 59.7% $0.03 4,187
DeepSeek-V4-Pro 59.4% $0.01 2,229
Kimi K2.5 thinking 58.7% $0.02 1,555
Trinity Large Thinking 57.9% $0.009 1,061
Claude Haiku 4.5 thinking 56.5% $0.05 1,635
Qwen 3.5 Flash (hosted 35B-A3B) 56% $0.005 4,206
Gemini 3 Flash 55.8% $0.03 2,091
MiniMax-M2.1 55.8% $0.008 981
DeepSeek-V3.2 thinking 55.4% $0.02 1,004
Qwen3-Max 55% $0.09 3,966
Gemini 3.1 Flash-Lite 55% $0.009 1,498
GLM-4.7 54.9% $0.02 2,201
Grok 4.20 reasoning 54.5% $0.07 1,420
DeepSeek-V3.1 53.9% $0.02 201
MiniMax-M2.5 53.5% $0.01 958
Qwen3.6 27B 53.2% $0.02 2,368
Gemini 3 Pro 53% $0.14 1,919
GPT-5 nano 52.6% $0.004 6,003
Gemma 4 31B IT 52.6% 1,052
GLM-5 thinking 52.5% $0.03 2,360
GPT-5.4 Nano 51.9% $0.001 641
GPT-5.4 Mini 51.7% $0.04 6,319
GLM-5.1 51.5% $0.03 2,114
Qwen 3.6 Plus 51.5% $0.05 2,343
gpt-oss-120b 48.8% $0.004 683
Qwen 3.6 Max (Preview) 47.9% $0.05 1,997
Qwen3-Max 47.5% $0.05 202
Mistral Medium 3.5 44.2% $0.08 4,096
gpt-oss-20b 43.8% $0.002 1,106

3 models have held number one on the official leaderboard since its release in August 2025

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

OpenAI xAI
Own leaderboard Not tested since Apr 2026
Grok 4.3 79.3%

Source: Official CaseLaw v2 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% 2025 2026 Near the ceiling (85%) Grok 4.3 GPT-5.1 GPT-4.1 Cohere Command A GPT-4o 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Grok 4.3 GPT-4.1

Source: Official CaseLaw v2 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%