MedXpertQA Text (MedXpertQA (Text))
We show this table for reference; we do not rank on it.
A medical multiple-choice benchmark spanning many specialties with 10 answer options per question.
Benchmark score on MedXpertQA (Text) — November 13, 2026
We compile the MedXpertQA (Text) rows from provider self-reports and secondary reports. Gemini 3.1 Pro leads the table at 71.5%, followed by GPT-5.4 (59.6%) and Muse Spark (52.6%). We do not use these results to rank models overall.
Gemini 3.1 Pro
GPT-5.4
OpenAI
Reported by Meta AI (comparison table)Muse Spark
Meta
Reported by Meta6 modelsKnowledgeCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (6 models)
None of the 6 results on this page has a documented run by the benchmark or an independent evaluator: 2 reported by the labs that built the models and 4 reported in another publisher’s document.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 ProGoogleReported by Meta AI (comparison table) | 71.5% | Reported by Meta AI (comparison table) | Not reported | Closed |
| 2 | GPT-5.4OpenAIReported by Meta AI (comparison table) | 59.6% | Reported by Meta AI (comparison table) | Not reported | Closed |
| 3 | Muse SparkMetaReported by Meta | 52.6% | Reported by Meta | Not reported | Closed |
| 4 | Claude Opus 4.6AnthropicReported by Meta AI (comparison table) | 52.1% | Reported by Meta AI (comparison table) | Not reported | Closed |
| 5 | Ling 3.0 Flash SanteInclusionAIReported by InclusionAI | 51.0% | Reported by InclusionAI | Not reported | Open |
| 6 | Grok 4.20xAIReported by Meta AI (comparison table) | 50.2% | Reported by Meta AI (comparison table) | Not reported | Closed |
- Lab-reported
- Benchmark-run
- Independent
Among the reported MedXpertQA (Text) rows, Gemini 3.1 Pro is first at 71.5%. The third row is 18.9 points behind. The broader top-10 range is 21.3 points, so the table still separates the published systems.
6 models have been evaluated on MedXpertQA (Text). The benchmark falls in the Knowledge category. MedXpertQA (Text) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About MedXpertQA (Text)
Year
2026
Tasks
2,450 medical multiple-choice questions
Format
Medical MCQ
Difficulty
Professional medical knowledge
Meta describes the text variant as 2,450 specialty-spanning medical questions with answer choices A-J. BenchLM treats it as a display-only health benchmark because it is not part of the weighted core schema.
Freshness and provenance
Version
MedXpertQA (Text) 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does MedXpertQA (Text) measure?
A medical multiple-choice benchmark spanning many specialties with 10 answer options per question.
Which model scores highest on MedXpertQA (Text)?
Gemini 3.1 Pro by Google currently leads with a score of 71.5% on MedXpertQA (Text).
How many models are evaluated on MedXpertQA (Text)?
6 AI models have published results on MedXpertQA (Text) in the BenchLM catalog.
Compare top models on MedXpertQA (Text)
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.