BasedAGIBasedAGI
Menu
Rankings live

risk_eval

Prompt injection resistance (eval)

Measure resistance to prompt injection in RAG and tool settings.

#1 Recommendation

gemini-2.5-pro

Strong on FACTS Benchmark Suite facts_grounding_score_pct (100%) and Vectara HHEM Leaderboard overall_hallucination_error_pct (76%)

external/google/gemini-2-5-pro

25.6%

Score

37.2%

Confidence

Limited benchmark evidence for this use case.

53 ranked models with average evidence of 14.5 points. Rankings may shift as more benchmark data is ingested.

Ranked Models

30

Evidence Quality

82%

Scoring

Benchmark-backed

Top Signal

FACTS Benchmark Suite: facts_grounding_score_pct

All Ranked Models

Max params:
Min confidence:
30 of 30
RankModelScore
#1gemini-2.5-pro

Strong on FACTS Benchmark Suite facts_grounding_score_pct (100%) and Vectara HHEM Leaderboard overall_hallucination_error_pct (76%)

25.6%
#2gemini-3-pro-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct (88%) and FACTS Benchmark Suite facts_search_score_pct (100%)

25.2%
#3anthropic/claude-sonnet-4.6

Strong on Vals Finance Agent overall_accuracy_pct (100%) and Vals CorpFin v2 overall_accuracy_pct (91%)

21.6%
#4Grok-4-0709
21.6%
#5gpt-4.1-20250414
21.4%
#6claude-sonnet-4-20250514
18.7%
#7gpt-5-mini-2025-08-07
18.4%
#8gpt-5-2025-08-07
18.1%
#9google/gemini-3.1-pro-preview
17.3%
#10openai/gpt-5.4-2026-03-05
16.9%
#11kimi/kimi-k2.5-thinking
16.5%
#12claude-opus-4-5-20251101
16.4%
#13gemini-2.5-flash
15.5%
#15xai-org/grok-4-fast-reasoning
15.0%
#16gpt-5.1-2025-11-13
15.0%
#17xai-org/grok-4-1-fast-reasoning
14.7%
#18gemini-3-flash-preview
14.6%
#19google/gemini-3.1-flash-lite-preview
14.1%
#20anthropic/claude-opus-4-6-thinking
13.1%
#21gpt-5.2-2025-12-11
13.1%
#22x-ai/grok-3
12.3%
#23anthropic/claude-opus-4-5-20251101-thinking
12.2%
#24anthropic/claude-sonnet-4-5-20250929-thinking
11.4%
#26zai/glm-5-thinking
11.1%
#27gpt-4o-2024-05-13
11.0%
#28Llama-2-7b-chat-hf
10.8%
#29openai/gpt-4o-mini-2024-07-18
10.7%
#30xai-org/grok-4-1-fast-non-reasoning
10.6%
#31Kimi K2 Thinking
10.6%
#33gpt-4.1-mini-20250414
10.4%

Compare Models

Model A leads by +0.4%

Shareable Link →

Model A

gemini-2.5-pro

external/google/gemini-2-5-pro

25.6%

Rank #1

Confidence 37.2%24 evidence pts

FACTS Benchmark Suite: facts_grounding_score_pct

Value 100.0% · Conf 100.0% · Weight 2.6%

facts_benchmark_suite.facts_grounding_score_pct (Mar 12, 2026)

Vectara HHEM Leaderboard: overall_hallucination_error_pct

Value 76.0% · Conf 100.0% · Weight 2.1%

vectara_hhem_leaderboard.overall_hallucination_error_pct (Mar 12, 2026)

Galileo Agent Leaderboard v2: Avg AC

Value 58.7% · Conf 100.0% · Weight 1.8%

galileo_agent_v2.avg_ac (Mar 12, 2026)

Galileo Agent Leaderboard v2: Avg TSQ

Value 79.5% · Conf 100.0% · Weight 1.7%

galileo_agent_v2.avg_tsq (Mar 12, 2026)

Model B

gemini-3-pro-preview

external/google/gemini-3-pro-preview

25.2%

Rank #2

Confidence 32.9%24 evidence pts

FACTS Benchmark Suite: facts_grounding_score_pct

Value 88.3% · Conf 100.0% · Weight 2.3%

facts_benchmark_suite.facts_grounding_score_pct (Mar 12, 2026)

FACTS Benchmark Suite: facts_search_score_pct

Value 100.0% · Conf 100.0% · Weight 2.0%

facts_benchmark_suite.facts_search_score_pct (Mar 12, 2026)

FACTS Benchmark Suite: average_score_pct

Value 100.0% · Conf 100.0% · Weight 1.9%

facts_benchmark_suite.average_score_pct (Mar 12, 2026)

Vals Finance Agent: overall_accuracy_pct

Value 87.0% · Conf 100.0% · Weight 1.8%

vals_finance_agent.overall_accuracy_pct (Mar 12, 2026)

Ranking Diagnostics & Missing Models

Source Lift

Ranked

53

Sources

8

Quality

Insufficient

Vals CorpFin v2

vals_corp_fin_v2

40 rows

1.3% avg lift

Vals Legal Bench

vals_legal_bench

35 rows

0.3% avg lift

Vals MedQA

vals_medqa

34 rows

0.3% avg lift

Vals Tax Eval v2

vals_tax_eval_v2

34 rows

0.3% avg lift

Missing Strong Models

gpt-4o

external/openai/gpt-4o

Rank #22

15.2%

Thin evidence after weighting

gpt-4o-20241120

external/openai/gpt-4o-20241120

Rank #49

10.7%

Thin evidence after weighting

deepseek/deepseek-r1

external/deepseek/deepseek-r1

Rank #54

10.5%

Thin evidence after weighting

google/gemini-2.0-flash-001

external/google/gemini-2-0-flash-001

Rank #56

10.3%

Thin evidence after weighting
Taxonomy Details

Core Tasks

task.prompt_injection_resistance

Required Modes

mode.tool_calling

Domains

domain.general_business

Related Use Cases