BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases7

CaseLaw v2 leaderboard

As of 6 Nov 2026, the top score on CaseLaw v2 is 79.3% by Grok 4.3 (SpaceXAI), ahead of GPT-5.1 at 73.4%, across 52 model configurations with a published result (Vals AI, result dated 4 May 2026). Questions about Canadian court decisions that require reading the case and applying it, written by lawyers. CaseLaw v2 is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 6 Nov 2026)

  • Grok 4.3 holds the top CaseLaw v2 score at 79.3% (Vals AI, 4 May 2026).
  • GPT-5.1 is second on CaseLaw v2 at 73.4% (Vals AI, 4 May 2026).
  • CaseLaw v2: Questions over Canadian court cases. Run by Vals AI (Vals AI).
  • 52 model configurations have a published CaseLaw v2 result on BenchLeader (BenchLeader, 6 Nov 2026).
  • CaseLaw v2 does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Questions over Canadian court cases. Run by Vals AI.

Published by
Vals AI
Category
Knowledge
Index weight
Reference only
Models
52
Data as of
6 Nov 2026

Vals AI (vals.ai).

What the test looks like

Questions about Canadian court decisions that require reading the case and applying it, written by lawyers.

How it is scored

Accuracy, run by Vals AI.

What to keep in mind

Canada-specific; complements the US-centric LegalBench.

Top 15
  1. 1Grok 4.379.3%
  2. 2GPT-5.1 (high)73.4%
  3. 3GPT-4.1 (high)69.9%
  4. 4GPT-5 mini (high)68.5%
  5. 5Claude Opus 4.768.4%
  6. 6GPT-5 (high)66.5%
  7. 7GPT-5.5 (xhigh)66.2%
  8. 8GPT-5.2 (xhigh)66.0%
  9. 9Grok 465.8%
  10. 10Kimi K2 Thinking (thinking)65.7%
  11. 11Grok 4 Fast (thinking)65.7%
  12. 12Gemini 3.1 Pro (high)64.8%
  13. 13Command A64.5%
  14. 14Claude Sonnet 4.664.0%
  15. 15Gemini 2.5 Pro63.9%
52 of 52
#
1Grok 4.379.3%54.5$0.0402026-05-04
2GPT-5.1high73.4%57.7$0.0432026-05-04
3GPT-4.1high69.9%46.6$0.0472026-05-04
4GPT-5 minihigh68.5%54.6$0.0112026-05-04
5Claude Opus 4.768.4%63.1$0.1622026-05-04
6GPT-5high66.5%57.9$0.0672026-05-04
7GPT-5.5xhigh66.2%64.3$0.1552026-05-04
8GPT-5.2xhigh66.0%60.0$0.1042026-05-04
9Grok 465.8%58.3$0.1592026-05-04
10Kimi K2 Thinkingthinking65.7%53.2$0.0152026-05-04
11Grok 4 Fastthinking65.7%51.6$0.00732026-05-04
12Gemini 3.1 Prohigh64.8%60.1$0.1362026-05-04
13Command A64.5%42.2$0.0982026-05-04
14Claude Sonnet 4.664.0%58.2$0.1452026-05-04
15Gemini 2.5 Pro63.9%54.5$0.2572026-05-04
16GPT-5.4xhigh63.8%63.2$0.1012026-05-04
17Muse Spark63.1%64.1$0.00652026-05-04
18Claude Opus 4.5thinking62.6%59.6$0.2292026-05-04
19Claude Sonnet 4.5thinking62.2%52.2$0.2562026-05-04
20Claude Opus 4.6thinking62.1%62.4$0.2312026-05-04
21Mistral Large 361.4%45.7$0.0192026-05-04
22Kimi K2.661.2%55.2$0.0262026-05-04
23MiniMax M2.760.9%56.5$0.00312026-05-04
24Grok 4.1 Fastthinking60.5%55.6$0.0112026-05-04
25Qwen3.5 Plusthinking59.7%57.3$0.0302026-05-04
26GPT-4ohigh59.7%41.6$0.0672026-05-04
27DeepSeek V4 Promax59.4%57.0$0.0132026-05-04
28Kimi K2.5thinking58.7%58.7$0.0252026-05-04
29Trinity Largethinking57.9%47.1$0.00892026-05-04
30Claude Haiku 4.5thinking56.5%45.4$0.0502026-05-04
31Qwen3.5 Flash56.0%51.8$0.00492026-05-04
32Gemini 3 Flashhigh55.8%58.3$0.0252026-05-04
33MiniMax-M2.155.8%55.0$0.00802026-05-04
34DeepSeek V3.2high55.4%–$0.0182026-05-04
35Qwen3 Maxmax55.0%54.3$0.0852026-05-04
36Gemini 3.1 Flash Litehigh55.0%48.5$0.00932026-05-04
37GLM 4.754.9%51.7$0.0212026-05-04
38Grok 4.20thinking54.5%58.4$0.0682026-05-04
39MiniMax M2.553.5%53.6$0.0122026-05-04
40Qwen3.6 27B53.2%48.0$0.0242026-05-04
41Gemini 3 Prohigh53.1%60.1$0.1382026-05-04
42GPT-5 nanohigh52.6%47.4$0.00422026-05-04
43Gemma 4 31Bhigh52.6%––2026-05-04
44GLM-5thinking52.5%60.2$0.0342026-05-04
45GPT-5.4 Nanohigh51.9%48.3$0.00112026-05-04
46GPT-5.4 Minixhigh51.7%56.0$0.0412026-05-04
47GLM 5.151.5%55.7$0.0342026-05-04
48Qwen3.6 Plus51.5%59.1$0.0472026-05-04
49gpt-oss-120b48.8%45.5$0.00432026-05-04
50Qwen3.6 Maxmax47.9%62.4$0.0522026-05-04
51Mistral Medium 3.5high44.2%–$0.0852026-05-04
52gpt-oss-20b43.8%44.0$0.00222026-05-04

More knowledge benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on CaseLaw v2

Cite as: BenchLeader, “CaseLaw v2 leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/vals_caselaw.

CaseLaw v2: questions

What does CaseLaw v2 measure?
Questions about Canadian court decisions that require reading the case and applying it, written by lawyers. Scores are reported in percent of tasks solved; higher is better.
What is the top score on CaseLaw v2?
As of 6 Nov 2026, the highest score on CaseLaw v2 is 79.3% by Grok 4.3 (result dated 4 May 2026), ahead of GPT-5.1 at 73.4%. Scores come from Vals AI and are re-read daily.
Which AI model leads CaseLaw v2?
Grok 4.3 leads CaseLaw v2 with 79.3% as of 6 Nov 2026 (result dated 4 May 2026), ahead of GPT-5.1 at 73.4%.
How many models have CaseLaw v2 results?
52 model configurations have a CaseLaw v2 result on BenchLeader, all taken from Vals AI.
Who runs CaseLaw v2 and how often is it updated?
CaseLaw v2 is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
Does CaseLaw v2 count toward the BenchLeader Index?
No. CaseLaw v2 is shown for reference but left out of the composite index.