AgMoDB
ModelsAgentsOrchestratorsEvalsCompositesVisualizeIndustry
AgMoDB by @mistakeknot
All Benchmarks

LegalBench

LegalBench measures legal reasoning across tasks such as rule recall, interpretation, argumentation, and rhetoric. It is useful for comparing legal-assistant potential before domain-specific validation.

knowledgelegalbench

Strengths

Large multi-task suite provides broad coverage of legal reasoning behaviors; regularly updated leaderboard supports current frontier comparisons.

Caveats

Task design is primarily US-centric, so transfer to other jurisdictions is limited; some subtasks reward statute recall more than practical legal judgment.

How to interpret scores

Contamination risk: highFreshness: static

Higher is better. Accuracy percentage across all 162 tasks.

Max score: 100

Relevant use cases

Legal researchContract analysisRegulatory compliance

Caveat to keep in mind

Task design is primarily US-centric, so transfer to other jurisdictions is limited.

Leaderboard

Last synced: Nov 22, 2026, 12:18 PM
#ModelProviderScorePrice/M
1
Nemotron 3 Super 120B A12B (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
NVIDIA97.0$0.45
2
Sao10K: Llama 3.1 70B Hanami x1
source benchpress
Evidence observed Apr 13, 2026
Sao10k96.9$3.00
3
Grok 4.20 0309 (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
SpaceXAI96.1$3.00
4
gpt-oss-20b (High)
source benchpress
Evidence observed Apr 13, 2026
OpenAI94.3$0.09
5
Google: Gemma 2 27B
source benchpress
Evidence observed Apr 13, 2026
Google94.3$0.65
6
Google: Gemma 2 9B
source benchpress
Evidence observed Apr 13, 2026
Google93.8$0.04
7
Qwen: Qwen3 235B A22B
source benchpress
Evidence observed Apr 13, 2026
Alibaba93.5$0.39
8
gpt-oss-20b (Low)
source benchpress
Evidence observed Apr 13, 2026
OpenAI93.4$0.13
9
xAI: Grok 3 Beta
source benchpress
Evidence observed Apr 13, 2026
SpaceXAI93.2$6.00
10
Meta: Llama 3.1 405B (base)
source benchpress
Evidence observed Apr 13, 2026
Meta93.2$4.00
11
Arctic Instruct
source benchpress
Evidence observed Apr 13, 2026
Snowflake93.2$0.00
12
GPT-5 nano (High)
source benchpress
Evidence observed Apr 13, 2026
OpenAI92.9$0.14
13
Google: Gemma 3 12B (free)
source benchpress
Evidence observed Apr 13, 2026
Google92.9$0.00
14
gpt-oss-120b (High)
source benchpress
Evidence observed Apr 13, 2026
OpenAI92.7$0.26
15
OpenAI: GPT-5.4
source benchpress
Evidence observed Apr 13, 2026
OpenAI92.7$5.63
16
Grok 4.20 0309 (Non-reasoning)
source benchpress
Evidence observed Apr 13, 2026
SpaceXAI92.7$3.00
17
GPT-4.1 nano
source benchpress
Evidence observed Apr 13, 2026
OpenAI92.6$0.18
18
ERNIE 4.5 300B A47B
source benchpress
Evidence observed Apr 13, 2026
Baidu92.3$0.00
19
GLM-4.5 (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
Z AI92.2$0.00
20
DeepSeek V3.1 (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
DeepSeek92.0$0.85
21
Qwen3 235B A22B 2507 Instruct
source benchpress
Evidence observed Apr 13, 2026
Alibaba91.9$0.39
22
Grok 3 mini Reasoning (High)
source benchpress
Evidence observed Apr 13, 2026
SpaceXAI91.6$0.35
23
Llama Nemotron Super 49B v1.5 (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
NVIDIA91.5$0.00
24
NVIDIA Nemotron Nano 9B V2 (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
NVIDIA91.4$0.07
25
Claude 3.7 Sonnet (Non-reasoning)
source benchpress
Evidence observed Apr 13, 2026
Anthropic91.3$6.00
26
WizardLM-2 8x22B
source benchpress
Evidence observed Apr 13, 2026
Microsoft91.2$0.62
27
INTELLECT-3 (Based on GLM-4.5-Air)
source benchpress
Evidence observed Apr 13, 2026
Prime Intellect91.1$0.00
28
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
source benchpress
Evidence observed Apr 13, 2026
NVIDIA91.0$0.09
29
GPT-4.1 mini
source benchpress
Evidence observed Apr 13, 2026
OpenAI91.0$0.70
30
OpenAI: o4 Mini High
source benchpress
Evidence observed Apr 13, 2026
OpenAI90.8$1.93
31
Grok 4
source benchpress
Evidence observed Apr 13, 2026
SpaceXAI90.7$6.00
32
DeepSeek-V2-Chat
source benchpress
Evidence observed Apr 13, 2026
DeepSeek90.6$0.00
33
GLM-4.7 (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
Z AI90.4$0.92
34
o4-mini (High)
source benchpress
Evidence observed Apr 13, 2026
OpenAI90.4$1.93
35
MiniMax-M2.7
source benchpress
Evidence observed Apr 13, 2026
MiniMax90.3$0.53
36
Qwen3 235B A22B (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
Alibaba90.3$0.00
37
Qwen: Qwen3 14B
source benchpress
Evidence observed Apr 13, 2026
Alibaba90.2$0.09
38
Qwen3 235B A22B 2507 (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
Alibaba90.2$0.75
39
MiniMax-M2.5
source benchpress
Evidence observed Apr 13, 2026
MiniMax90.2$0.52
40
Grok 3
source benchpress
Evidence observed Apr 13, 2026
SpaceXAI90.2$6.00
41
GPT-4.1
source benchpress
Evidence observed Apr 13, 2026
OpenAI90.2$3.50
42
EXAONE 4.0 32B (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
LG AI Research90.1$0.00
43
Llama 4 Maverick
source benchpress
Evidence observed Apr 13, 2026
Meta90.1$0.42
44
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1
source benchpress
Evidence observed Apr 13, 2026
NVIDIA90.1$0.90
45
AI21: Jamba Large 1.7
source benchpress
Evidence observed Apr 13, 2026
AI21 Labs90.1$3.50
46
QwQ 32B
source benchpress
Evidence observed Apr 13, 2026
Alibaba90.0$0.00
47
R1 1776
source benchpress
Evidence observed Apr 13, 2026
Perplexity89.9$0.00
48
DeepSeek V3.2 Exp (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
DeepSeek89.8$0.32
49
Google: Gemini 2.5 Pro Preview 06-05
source benchpress
Evidence observed Apr 13, 2026
Google89.8$3.44
50
MiniMax-M2
source benchpress
Evidence observed Apr 13, 2026
MiniMax89.8$0.52