MHGraphBench - Two-hop Verification with Evidence: leaderboard

Two-hop verification questions with sanitized PrimeKG feature snippets added, in MHGraphBench (2026), a knowledge-graph-grounded mental-health benchmark built from a curated PrimeKG subgraph, with letter-only multiple-choice answers. Accuracy in percent; higher is better.

Metric: Accuracy (%) on the 1,200 two-hop verification items with sanitized PrimeKG feature snippets added, letter-only answers; the OpenAI API models answer at temperature 0 (at most 120 completion tokens) with strict answer-letter parsing, the open models are scored by forced-choice option-letter log-probabilities; higher is better. Source: arxiv.org. Saturation forecast: Around April 2028. 15 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-4.171.42#505
2GPT-4o68.83#751
3Qwen 2.5 32B Instruct61.25#1247
4GPT-5.2 Instant61.08#304
5GPT-5.1 Instant60#472
6GPT-5 Mini59.67#364
7Qwen 2.5 7B Instruct56.75#2723
8Llama3-OpenBioLLM-8B56.5#6364
9Mistral 7B Instruct (v0.3)56.17#6750
10BioMistral-7B53.17#8332
11Llama3-Med42-8B51.42#5084
12Meditron-7B51#8733
13Llama 3.1 8B Instruct50.25#4600
14DeepSeek-R1-Distill-Qwen-7B49.75#8055
15DeepSeek R1 Distill Qwen 32B49.58#1834

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=mhgraphbench-two-hop-verification-with-evidence · How It Works · Data refreshed daily, snapshot 2026-11-21.