Pass IndexThe State of AISign in

Vectara Hallucination Leaderboard

Vectara Hallucination Leaderboard is run by read by the crawler. It has ranked 105 models, of which the catalogue holds 81, scoring from 3.1 to 24.2 on Hallucination Rate.

measured by read by the crawler · the board itself

PlaceModelMetricScore
2ndof 105GPT-5.4 nanoHallucination Rate3.1
3rdof 105Gemini 2.5 Flash-LiteHallucination Rate3.3
4thof 105Phi-4Hallucination Rate3.7
5thof 105Llama-3.3-70B-Instruct-TurboHallucination Rate4.1
7thof 105Gemma 3 12BHallucination Rate4.4
9thof 105Qwen3 8BHallucination Rate4.8
10thof 105Nova ProHallucination Rate5.1
11thof 105Nova 2 LiteHallucination Rate5.1
13thof 105Granite 4.0 H SmallHallucination Rate5.2
16thof 105DeepSeek V3.2 ExpHallucination Rate5.3
17thof 105Qwen3 14BHallucination Rate5.4
18thof 105Nova MicroHallucination Rate5.5
19thof 105DeepSeek-V3.1Hallucination Rate5.5
20thof 105GPT-5.4 miniHallucination Rate5.5
21stof 105GPT-4.1 fine-tunedHallucination Rate5.6
22ndof 105Qwen3 4BHallucination Rate5.7
23rdof 105Grok 3Hallucination Rate5.8
24thof 105Qwen3 32BHallucination Rate5.9
25thof 105Nova LiteHallucination Rate6.1
26thof 105DeepSeek-V3Hallucination Rate6.1
27thof 105DeepSeek v3.2Hallucination Rate6.3
28thof 105Gemma 3 4BHallucination Rate6.4
29thof 105Command R+ (08-2024)Hallucination Rate6.9
31stof 105GPT-5.4Hallucination Rate7
32ndof 105Gemini 2.5 ProHallucination Rate7
34thof 105Gemma 3 27BHallucination Rate7.4
35thof 105Gemma 4 31BHallucination Rate7.4
38thof 105Gemini 2.5 FlashHallucination Rate7.8
39thof 105Llama 4 Maverick 17BHallucination Rate8.2
40thof 105Gemini 3.1 Flash-LiteHallucination Rate8.2
41stof 105GPT-5.4 ProHallucination Rate8.3
42ndof 105GPT-5.2Hallucination Rate8.4
43rdof 105DeepSeek V4 ProHallucination Rate8.6
44thof 105MiniMax M2.5Hallucination Rate9.1
45thof 105Command A 03-2025Hallucination Rate9.3
46thof 105GPT-5.5Hallucination Rate9.3
48thof 105Qwen3 235B A22BHallucination Rate9.3
49thof 105Qwen3 Next 80B A3B ThinkingHallucination Rate9.3
50thof 105GLM-4.7 FlashHallucination Rate9.3
52ndof 105GLM-4.6Hallucination Rate9.5
53rdof 105Nemotron 3 Nano 30B A3BHallucination Rate9.6
54thof 105GPT-4o (2024-08-06)Hallucination Rate9.6
56thof 105Claude Haiku 4.5Hallucination Rate9.8
57thof 105GLM-5Hallucination Rate10.1
58thof 105Claude Sonnet 4Hallucination Rate10.3
59thof 105Gemini 3.1 Pro PreviewHallucination Rate10.4
60thof 105Qwen3.5-FlashHallucination Rate10.5
61stof 105Qwen3.5-35B-A3BHallucination Rate10.5
62ndof 105GPT-5 nanoHallucination Rate10.5
63rdof 105Claude Sonnet 4.6Hallucination Rate10.6
65thof 105Qwen3.5 Plus 2026-02-15Hallucination Rate10.7
67thof 105Kimi K2.6Hallucination Rate10.8
68thof 105Claude Opus 4.5Hallucination Rate10.9
69thof 105Aya Expanse 32BHallucination Rate10.9
70thof 105GPT-5.1Hallucination Rate10.9
71stof 105Qwen3.5-122B-A10BHallucination Rate11.2
72ndof 105DeepSeek-R1Hallucination Rate11.3
73rdof 105GLM-4.7Hallucination Rate11.7
74thof 105Claude Opus 4.1Hallucination Rate11.8
75thof 105MiniMax M2.1Hallucination Rate11.8
76thof 105Claude Opus 4Hallucination Rate12
77thof 105Claude Sonnet 4.5Hallucination Rate12
78thof 105Claude Opus 4.7Hallucination Rate12
79thof 105Qwen3.5-27BHallucination Rate12.1
81stof 105Claude Opus 4.6Hallucination Rate12.2
82ndof 105Mercury 2Hallucination Rate12.3
83rdof 105MiniMax M2.7Hallucination Rate12.9
84thof 105GPT-5 miniHallucination Rate12.9
85thof 105Gemini 3 Flash PreviewHallucination Rate13.5
86thof 105gemini-3-pro-previewHallucination Rate13.6
87thof 105Kimi K2.5Hallucination Rate14.2
88thof 105GPT OSS 120BHallucination Rate14.2
91stof 105GPT-5Hallucination Rate14.7
93rdof 105Grok 4.1 Fast Non-ReasoningHallucination Rate17.8
95thof 105o4-miniHallucination Rate18.6
97thof 105Grok 4.1 Fast ReasoningHallucination Rate19.2
98thof 105Ministral 3 14B 2512Hallucination Rate19.4
99thof 105grok-4-fast-non-reasoningHallucination Rate19.7
101stof 105Ministral 3 8B 2512Hallucination Rate21.7
103rdof 105o3-proHallucination Rate23.3
105thof 105Ministral 3 3B 2512Hallucination Rate24.2

Read from the board on 2026-09-02