ROHAS

The ROHAS Legal AI Benchmark

5 competencies. 10 questions. 2 automatic disqualifiers. ROHAS is a practical Legal AI screening benchmark that you can run against any AI model in minutes.

Leaderboard

Ranked by score on each model's most recent run. Disqualified models failed a hallucination/accuracy trap question and can never rank #1, however high their raw score.

Pass Partial Fail Ungraded
#1
xAI: Grok 4.5
x-ai/grok-4.5
Winner
95%
R 75%
O 100%
H 100%
A 100%
S 100%
9 pass 1 partial 0 fail
Answer cost $0.1216 Runtime 5m 55s
8 Jul 2026
View run →
#2
Anthropic: Claude Opus 4.8
anthropic/claude-opus-4.8
95%
R 75%
O 100%
H 100%
A 100%
S 100%
9 pass 1 partial 0 fail
Answer cost $0.2557 Runtime 3m 31s
8 Jul 2026
View run →
#3
Anthropic: Claude Fable 5
anthropic/claude-fable-5
95%
R 75%
O 100%
H 100%
A 100%
S 100%
9 pass 1 partial 0 fail
Answer cost $0.6753 Runtime 4m 26s
8 Jul 2026
View run →
#4
OpenAI: GPT-5.6 Sol Pro
openai/gpt-5.6-sol-pro
95%
R 75%
O 100%
H 100%
A 100%
S 100%
9 pass 1 partial 0 fail
Answer cost $1.2238 Runtime 10m 44s
20 Jul 2026
View run →
#5
OpenAI: GPT-5.6 Luna
openai/gpt-5.6-luna
90%
R 75%
O 75%
H 100%
A 100%
S 100%
8 pass 2 partial 0 fail
Answer cost $0.0665 Runtime 2m 9s
13 Jul 2026
View run →
#6
Anthropic: Claude Haiku 4.5
anthropic/claude-haiku-4.5
85%
R 75%
O 75%
H 100%
A 75%
S 100%
7 pass 3 partial 0 fail
Answer cost $0.0288 Runtime 1m 53s
8 Jul 2026
View run →
#7
Z.ai: GLM 5.2
z-ai/glm-5.2
80%
R 75%
O 75%
H 75%
A 75%
S 100%
6 pass 4 partial 0 fail
Answer cost $0.0210 Runtime 6m 27s
10 Jul 2026
View run →
#8
Qwen: Qwen3.7 Plus
qwen/qwen3.7-plus
80%
R 75%
O 75%
H 50%
A 100%
S 100%
7 pass 2 partial 1 fail
Answer cost $0.0389 Runtime 10m 28s
8 Jul 2026
View run →
#9
Google: Gemini 3.5 Flash
google/gemini-3.5-flash
75%
R 75%
O 75%
H 50%
A 75%
S 100%
6 pass 3 partial 1 fail
Answer cost $0.0842 Runtime 2m 24s
8 Jul 2026
View run →
#10
Anthropic: Claude Sonnet 5
anthropic/claude-sonnet-5
70%
R 100%
O 50%
H 75%
A 50%
S 75%
4 pass 6 partial 0 fail
Answer cost $0.1320 Runtime 4m 6s
8 Jul 2026
View run →
#11
Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
65%
R 75%
O 75%
H 50%
A 50%
S 75%
4 pass 5 partial 1 fail
Answer cost $0.0028 Runtime 2m 37s
8 Jul 2026
View run →
#12
DeepSeek: DeepSeek V4 Pro
deepseek/deepseek-v4-pro
65%
R 25%
O 75%
H 50%
A 75%
S 100%
5 pass 3 partial 2 fail
Answer cost $0.0131 Runtime 7m 56s
8 Jul 2026
View run →
#13
Amazon: Nova 2 Lite
amazon/nova-2-lite-v1
65%
R 75%
O 50%
H 50%
A 50%
S 100%
4 pass 5 partial 1 fail
Answer cost $0.0292 Runtime 1m 42s
18 Jul 2026
View run →
DQ
OpenAI: GPT-5.5
openai/gpt-5.5
Disqualified
75%
R 75%
O 50%
H 50%
A 100%
S 100%
7 pass 1 partial 2 fail
Answer cost $0.3933 Runtime 9m 55s
7 Jul 2026
View run →
DQ
Free Models Router
openrouter/free
Disqualified
50%
R 75%
O 25%
H 50%
A 50%
S 50%
3 pass 4 partial 3 fail
Answer cost $0.0000 Runtime 5m 14s
7 Jul 2026
View run →

Full data

RankModelScorePass/Partial/FailAnswer costRuntimeLatest run
#1 xAI: Grok 4.5
x-ai/grok-4.5
9.5 / 10 (95%) 9 / 1 / 0 $0.1216 5m 55s 2026-07-08 12:18:47
#2 Anthropic: Claude Opus 4.8
anthropic/claude-opus-4.8
9.5 / 10 (95%) 9 / 1 / 0 $0.2557 3m 31s 2026-07-08 11:26:44
#3 Anthropic: Claude Fable 5
anthropic/claude-fable-5
9.5 / 10 (95%) 9 / 1 / 0 $0.6753 4m 26s 2026-07-08 11:38:19
#4 OpenAI: GPT-5.6 Sol Pro
openai/gpt-5.6-sol-pro
9.5 / 10 (95%) 9 / 1 / 0 $1.2238 10m 44s 2026-07-20 10:11:26
#5 OpenAI: GPT-5.6 Luna
openai/gpt-5.6-luna
9 / 10 (90%) 8 / 2 / 0 $0.0665 2m 9s 2026-07-13 01:51:10
#6 Anthropic: Claude Haiku 4.5
anthropic/claude-haiku-4.5
8.5 / 10 (85%) 7 / 3 / 0 $0.0288 1m 53s 2026-07-08 11:30:52
#7 Z.ai: GLM 5.2
z-ai/glm-5.2
8 / 10 (80%) 6 / 4 / 0 $0.0210 6m 27s 2026-07-10 09:12:43
#8 Qwen: Qwen3.7 Plus
qwen/qwen3.7-plus
8 / 10 (80%) 7 / 2 / 1 $0.0389 10m 28s 2026-07-08 12:46:42
#9 Google: Gemini 3.5 Flash
google/gemini-3.5-flash
7.5 / 10 (75%) 6 / 3 / 1 $0.0842 2m 24s 2026-07-08 12:25:25
#10 Anthropic: Claude Sonnet 5
anthropic/claude-sonnet-5
7 / 10 (70%) 4 / 6 / 0 $0.1320 4m 6s 2026-07-08 11:17:30
#11 Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
6.5 / 10 (65%) 4 / 5 / 1 $0.0028 2m 37s 2026-07-08 12:29:17
#12 DeepSeek: DeepSeek V4 Pro
deepseek/deepseek-v4-pro
6.5 / 10 (65%) 5 / 3 / 2 $0.0131 7m 56s 2026-07-08 09:26:09
#13 Amazon: Nova 2 Lite
amazon/nova-2-lite-v1
6.5 / 10 (65%) 4 / 5 / 1 $0.0292 1m 42s 2026-07-18 09:45:43
DQ OpenAI: GPT-5.5
openai/gpt-5.5
7.5 / 10 (75%) 7 / 1 / 2 $0.3933 9m 55s 2026-07-07 13:54:29
DQ Free Models Router
openrouter/free
5 / 10 (50%) 3 / 4 / 3 $0.0000 5m 14s 2026-07-07 09:10:43