Benchmark Almanac

OpenAI user-flagged hallucination eval

GPT-5.5 Instant 46.1% leads since May 2026 Only in system cards

Production conversations users flagged for factual errors. Measures the rate of incorrect claims.

Made by OpenAI Hallucination rates Tasks kept private Last in a system card Oct 2026 Last model added Oct 2026
Scored
Graded by a model A language model scores each response, usually against a rubric.
Answers
Open-ended Free-form text, documents, designs or media judged as a whole.
4
Models scored in lab cards
17
System cards report it, from 1 lab

GPT-5.5 Instant leads with 46.1%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

  1. 46.1 GPT-5.5 Instant
  2. 24.6 GPT-6 Luna
  3. 13.5 GPT-6 Sol
  4. 9.20 GPT-5.5
  1. 1 GPT-5.5 Instant 46.1%
  2. 2 GPT-6 Luna 24.6%
  3. 3 GPT-6 Sol 13.5%
  4. 4 GPT-5.5 9.20%
#ModelScoreSettingDateSource
1 GPT-5.5 Instant 46.1% May 2026 Model card
2 GPT-6 Luna 24.6% Oct 2026 Model card
3 GPT-6 Sol 13.5% Oct 2026 Model card
4 GPT-5.5 9.20% Apr 2026 Model card

2 models have held number one since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Lab claims 2 leaders
GPT-5.5 Instant 46.1%

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-5.5 Instant GPT-5.5 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-5.5 Instant GPT-5.5

Labs report it only in system cards

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.

17 system cards report it, from 1 lab

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
29 Oct 2026 GPT-6 Luna system card addendum 24.6 User Flagged Failures, responses with factual errors (claims with errors 7.2%), printed chart label (Figure 3) Hallucination
7 Oct 2026 GPT-6 Sol system card addendum 13.5 User Flagged Failures, responses with factual errors (claims with errors 3.5%), printed chart label (Figure 3) Hallucination
7 Oct 2026 GPT-6 Luna system card addendum 18.7 User Flagged Failures, responses with factual errors (claims with errors 5.1%), printed chart label (Figure 3) Hallucination
29 Sep 2026 GPT-6.1 Sol system card addendum Performance in Cases Flagged by Users, error rate vs latency, chart without printed numbers (Figure 5, 6.1) Hallucination
22 Sep 2026 GPT-6 Sol system card Performance in Cases Flagged by Users, error rate vs latency, chart without printed numbers (Figure 60, A.5.1) Hallucination
22 Sep 2026 GPT-6 Luna system card Performance in Cases Flagged by Users, error rate vs latency, chart without printed numbers (Figure 60, A.5.1) Hallucination
3 Sep 2026 GPT-6 Astra system card Performance in Cases Flagged by Users, error rate vs latency, chart without printed numbers (Figure 6, 7.1) Hallucination
6 Aug 2026 GPT-5.6 Sol system card addendum 0.31 User Flagged Failures, relative hallucination rate vs GPT-5.3 Instant, % responses with factual error, 0.31x, printed chart label (Figure 2, 6) Hallucination
6 Aug 2026 GPT-5.6 Luna system card addendum 0.49 User Flagged Failures, relative hallucination rate vs GPT-5.3 Instant, % responses with factual error, 0.49x, printed chart label (Figure 2, 6) Hallucination
9 Jul 2026 GPT-5.6 Terra system card Performance in Cases Flagged by Users, error rate vs simulated latency, chart without printed numbers (Figure 4, 6.1) Hallucination
9 Jul 2026 GPT-5.6 Sol system card Performance in Cases Flagged by Users, error rate vs simulated latency, chart without printed numbers (Figure 4, 6.1) Hallucination
9 Jul 2026 GPT-5.6 Luna system card Performance in Cases Flagged by Users, error rate vs simulated latency, chart without printed numbers (Figure 4, 6.1) Hallucination
25 Jun 2026 GPT-5.6 Terra system card Performance in Cases Flagged by Users, error rate vs simulated latency, chart without printed numbers (Figure 4, 6.1) Hallucination
25 Jun 2026 GPT-5.6 Sol system card Performance in Cases Flagged by Users, error rate vs simulated latency, chart without printed numbers (Figure 4, 6.1) Hallucination
25 Jun 2026 GPT-5.6 Luna system card Performance in Cases Flagged by Users, error rate vs simulated latency, chart without printed numbers (Figure 4, 6.1) Hallucination
4 May 2026 GPT-5.5 Instant system card 46.1 User flagged failures, responses with factual error (claims with factual error 15.8%), printed chart label (Figure 2) Hallucination
23 Apr 2026 GPT-5.5 system card 9.2 Performance in Cases Flagged by Users, response-level hallucination rate, printed chart label (claim-level 2.0%) (Figure 3, 6.1) Hallucination

More in Factuality

All 70 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%
  • 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. Nemotron 3.5 Bolt E4B 40.7%
  • 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. Kimi K3.1 Pro 8.30%
  • RAGTruth In use A word-level annotated corpus of hallucinations in retrieval-augmented generation answers. It is used to train and evaluate hallucination detection and RAG faithfulness. Nemotron 3.5 Bolt E4B 77.9%