AI-Roundtable Ranking — one entry per benchmark run — Medicine

Medicine 2026-09-10: Claude Opus 5 (92)

2026-09-10T06:41:54.000Z

Medicine: Claude Opus 5 92/100.

In Medicine, Claude Opus 5 (top score) contradicts a stored key fact on average 0,2 times per answer and adds avg 1,9 claims the judge panel flags as false or unsupported; 100 % of answers carry at least one flag. The lowest value is Gemini 3.1 Pro at avg 0,4 per answer. Relative to answer length: 0,65 per 1000 output tokens, lowest DeepSeek V4 Pro at 0,24.

Full run with confidence intervals, diff to the previous run and raw data

Medicine 2026-09-07: Claude Fable 5.1 (90)

2026-09-07T18:18:39.000Z

Medicine: Claude Fable 5.1 90/100.

In Medicine, Claude Fable 5.1 (top score) contradicts a stored key fact on average 0,3 times per answer and adds avg 0,9 claims the judge panel flags as false or unsupported; 100 % of answers carry at least one flag. The lowest value is Grok 4.5 at avg 0,2 per answer. Relative to answer length: 0,52 per 1000 output tokens, lowest GLM-5.3 at 0,20.

Full run with confidence intervals, diff to the previous run and raw data

Medicine 2026-08-01: Claude Opus 4.7 (87)

2026-08-01T05:54:40.000Z

Medicine: Claude Opus 4.7 87/100.

In Medicine, Claude Opus 4.7 (top score) contradicts a stored key fact on average 0,5 times per answer and adds avg 0,7 claims the judge panel flags as false or unsupported; 90 % of answers carry at least one flag. The lowest value is GLM-4.6 at avg 0,2 per answer. Relative to answer length: 1,07 per 1000 output tokens, lowest GLM-4.6 at 0,08.

Full run with confidence intervals, diff to the previous run and raw data

Medicine 2026-07-19: Claude Opus 4.7 (83)

2026-07-19T12:01:08.000Z

Medicine: Claude Opus 4.7 83/100.

In Medicine, Claude Opus 4.7 (top score) contradicts a stored key fact on average 0,4 times per answer and adds avg 0,8 claims the judge panel flags as false or unsupported; 95 % of answers carry at least one flag. The lowest value is Grok 4.5 at avg 0,3 per answer. Relative to answer length: 1,09 per 1000 output tokens, lowest GLM-4.6 at 0,12.

Full run with confidence intervals, diff to the previous run and raw data

Medicine 2026-06-21: GPT-5.5 Pro (88)

2026-06-21T14:39:14.000Z

Medicine: GPT-5.5 Pro 88/100.

In Medicine, GPT-5.5 Pro (top score) contradicts a stored key fact on average 0,5 times per answer and adds avg 0,4 claims the judge panel flags as false or unsupported; 85 % of answers carry at least one flag. The lowest value is Gemini 3.1 Pro at avg 0,4 per answer. Relative to answer length: 0,18 per 1000 output tokens.

Full run with confidence intervals, diff to the previous run and raw data

Medicine 2026-05-29: Claude Opus 4.7 (84)

2026-05-29T04:35:00.000Z

Medicine: Claude Opus 4.7 84/100.

In Medicine, Claude Opus 4.7 (top score) contradicts a stored key fact on average 0,5 times per answer and adds avg 0,8 claims the judge panel flags as false or unsupported; 100 % of answers carry at least one flag. The lowest value is Gemini 2.5 Pro at avg 0,4 per answer. Relative to answer length: 1,15 per 1000 output tokens, lowest Claude Opus 4.8 at 0,68.

Full run with confidence intervals, diff to the previous run and raw data