Galileo LLM Hallucination Index
Version 2023
Models answer questions with and without retrieved context and generate long responses. Galileo judges factual accuracy and adherence to the supplied context.
- Made by
- Galileo
- Released
- November 2023
- Kind
- Hallucination rates
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Propensity
- Behavior
- Hallucination
- Language
- English
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- Anyone
- Strongest model tested
- GPT-4 Jun 2023 #186 on the capability index
- Last model added
- November 2023
- Scores refreshed
- November 20th, 2026
GPT-4 leads with 0.79 among models released by November 2023 GPT-4 leads with 0.79 among models released by November 2023
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in November 2023, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-4 Jun 2023 0.79
- 2 GPT-3.5 Turbo Nov 2023 0.77
- 3 GPT-3.5 Turbo Jun 2023 0.75
- 4
Llama 2-70B 0.72
- 5 GPT-3.5 Turbo Instruct 0.71
- 6
Llama 2-13B 0.69
- 7
Zephyr 7B Beta 0.68
- 8
Mistral-7B-Instruct-v0.1 0.64
- 9 falcon-40b-instruct 0.63
- 10
Llama 2-7B 0.63
- 11 mpt-7b-instruct 0.50
Source: Official Galileo LLM Hallucination Index leaderboard
- 1 GPT-4 Jun 2023 0.79
- 2 GPT-3.5 Turbo Nov 2023 0.77
- 3 GPT-3.5 Turbo Jun 2023 0.75
- 4
Llama 2-70B 0.72
- 5 GPT-3.5 Turbo Instruct 0.71
- 6
Llama 2-13B 0.69
- 7
Zephyr 7B Beta 0.68
- 8
Mistral-7B-Instruct-v0.1 0.64
- 9
Llama 2-7B 0.63
Source: Official Galileo LLM Hallucination Index leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Jun 2023 | 0.79 | Jun 2023 | Official leaderboard | |
| 2 | GPT-3.5 Turbo Nov 2023 | 0.77 | Nov 2023 | Official leaderboard | |
| 3 | GPT-3.5 Turbo Jun 2023 | 0.75 | Jun 2023 | Official leaderboard | |
| 4 | | 0.72 | Jul 2023 | Official leaderboard | |
| 5 | GPT-3.5 Turbo Instruct | 0.71 | Sep 2023 | Official leaderboard | |
| 6 | | 0.69 | Jul 2023 | Official leaderboard | |
| 7 | | 0.68 | Oct 2023 | Official leaderboard | |
| 8 | | 0.64 | Sep 2023 | Official leaderboard | |
| 9 | falcon-40b-instruct | 0.63 | Official leaderboard | ||
| 10 | | 0.63 | Jul 2023 | Official leaderboard | |
| 11 | mpt-7b-instruct | 0.50 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Jun 2023 | 0.79 | Jun 2023 | Official leaderboard | |
| 2 | GPT-3.5 Turbo Nov 2023 | 0.77 | Nov 2023 | Official leaderboard | |
| 3 | GPT-3.5 Turbo Jun 2023 | 0.75 | Jun 2023 | Official leaderboard | |
| 4 | | 0.72 | Jul 2023 | Official leaderboard | |
| 5 | GPT-3.5 Turbo Instruct | 0.71 | Sep 2023 | Official leaderboard | |
| 6 | | 0.69 | Jul 2023 | Official leaderboard | |
| 7 | | 0.68 | Oct 2023 | Official leaderboard | |
| 8 | | 0.64 | Sep 2023 | Official leaderboard | |
| 9 | | 0.63 | Jul 2023 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Q&A with RAG, Q&A without RAG and Long-Form Text Generation. Each ranks models on one part of the test. GPT-4 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
Q&A with RAG
9 models we track have a score here.
- 1 GPT-4 Jun 2023 0.76
- 2 GPT-3.5 Turbo Jun 2023 ↑1 0.75
- 3 GPT-3.5 Turbo Nov 2023 ↓1 0.74
- 4
Zephyr 7B Beta ↑3 0.71
- 5
Llama 2-13B ↑1 0.68
- 6
Llama 2-70B ↓2 0.68
- 7 GPT-3.5 Turbo Instruct ↓2 0.68
- 8
Mistral-7B-Instruct-v0.1 0.67
- 9
Llama 2-7B 0.65
Q&A without RAG
9 models we track have a score here.
- 1 GPT-4 Jun 2023 0.77
- 2 GPT-3.5 Turbo Nov 2023 0.74
- 3 GPT-3.5 Turbo Jun 2023 0.70
- 4 GPT-3.5 Turbo Instruct ↑1 0.70
- 5
Llama 2-70B ↓1 0.65
- 6
Zephyr 7B Beta ↑1 0.60
- 7
Llama 2-13B ↓1 0.59
- 8
Mistral-7B-Instruct-v0.1 0.59
- 9
Llama 2-7B 0.52
Long-Form Text Generation
9 models we track have a score here.
- 1 GPT-4 Jun 2023 0.83
- 2
Llama 2-70B ↑2 0.82
- 3 GPT-3.5 Turbo Nov 2023 ↓1 0.82
- 4 GPT-3.5 Turbo Jun 2023 ↓1 0.81
- 5
Llama 2-13B ↑1 0.79
- 6 GPT-3.5 Turbo Instruct ↓1 0.74
- 7
Zephyr 7B Beta 0.74
- 8
Llama 2-7B ↑1 0.72
- 9
Mistral-7B-Instruct-v0.1 ↓1 0.65
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Galileo LLM Hallucination Index leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Galileo LLM Hallucination Index leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
Versions
More in Factuality
- SimpleVQA In use Models answer 2,025 short factual questions about images across 9 tasks and 9 topics. An LLM judge grades answers against fixed references.
Qwen3.7-Plus 81.7%
- HallusionBench In use Models answer 1,129 yes or no questions about 346 images, built in pairs to expose language hallucination and visual illusion. Scored by accuracy.
Keye-VL-2.0-30B-A3B 73.5%
- SimpleQA Verified In use 1,000 human-verified, de-duplicated short-answer factual questions measuring parametric knowledge.
Gemini 3.1 Pro 77.5%
- AA-Omniscience v1.1 In use Models answer 3,000 knowledge questions in six domains without tools and may abstain. The index adds correct answers and subtracts wrong ones.
Inkling 2 Small 16.1
- GaRAGe In use Models write long-form RAG answers to 2,366 questions with human-annotated grounding passages. Scoring checks whether answers use the relevant passages.
Amazon Nova Pro 60.7%
- Kimi Hallu Bench In use Models answer hard prompts drawn from practical work tasks. Fact-checking agents score the share of claims that are hallucinated. GPT-6 Astra 4.20%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (11 entries).
- Pass Models scored 9 models we track, plus 2 other entries on its leaderboard.
- Note Newest score The newest came 3 years ago, in November 2023, for GPT-3.5 Turbo. That’s expected for a test replaced by Galileo LLM Hallucination Index RAG Special.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-4 (#186).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 9 rows for models we track and 2 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.