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

Law 2026-09-10: Claude Fable 5.1 (91)

2026-09-10T06:41:54.000Z

Law: Claude Fable 5.1 91/100.

In Law, Claude Fable 5.1 (top score) contradicts a stored key fact on average 0,0 times per answer and adds avg 1,7 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 0,6 per answer. Relative to answer length: 0,60 per 1000 output tokens, lowest DeepSeek V4 Pro at 0,11.

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

Law 2026-09-07: Claude Opus 5 (90)

2026-09-07T18:18:39.000Z

Law: Claude Opus 5 90/100.

In Law, Claude Opus 5 (top score) contradicts a stored key fact on average 0,3 times per answer and adds avg 1,4 claims the judge panel flags as false or unsupported; 94 % of answers carry at least one flag. The lowest value is Grok 4.5 at avg 0,4 per answer. Relative to answer length: 0,47 per 1000 output tokens, lowest DeepSeek V4 Pro at 0,13.

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

Law 2026-08-01: Claude Opus 4.7 (84)

2026-08-01T05:54:40.000Z

Law: Claude Opus 4.7 84/100.

In Law, Claude Opus 4.7 (top score) contradicts a stored key fact on average 0,2 times per answer and adds avg 0,7 claims the judge panel flags as false or unsupported; 80 % of answers carry at least one flag. The lowest value is Claude Opus 4.8 at avg 0,7 per answer. Relative to answer length: 1,03 per 1000 output tokens, lowest GPT-5.6 Sol at 0,29.

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

Law 2026-07-19: Claude Opus 4.7 (80)

2026-07-19T12:01:08.000Z

Law: Claude Opus 4.7 80/100.

In Law, Claude Opus 4.7 (top score) contradicts a stored key fact on average 0,3 times per answer and adds avg 0,7 claims the judge panel flags as false or unsupported; 91 % of answers carry at least one flag. The lowest value is Grok 4.5 at avg 0,5 per answer. Relative to answer length: 1,06 per 1000 output tokens, lowest GPT-5.6 Sol at 0,29.

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

Law 2026-06-21: Claude Opus 4.7 (82)

2026-06-21T14:39:14.000Z

Law: Claude Opus 4.7 82/100.

In Law, Claude Opus 4.7 (top score) contradicts a stored key fact on average 0,2 times per answer and adds avg 0,6 claims the judge panel flags as false or unsupported; 71 % of answers carry at least one flag. The lowest value is Grok 4.3 at avg 0,6 per answer. Relative to answer length: 0,98 per 1000 output tokens, lowest GPT-5.5 Pro at 0,07.

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

Law 2026-05-29: Claude Opus 4.7 (82)

2026-05-29T04:35:00.000Z

Law: Claude Opus 4.7 82/100.

In Law, Claude Opus 4.7 (top score) contradicts a stored key fact on average 0,2 times per answer and adds avg 0,8 claims the judge panel flags as false or unsupported; 86 % of answers carry at least one flag. The lowest value is Gemini 2.5 Pro at avg 0,2 per answer. Relative to answer length: 1,22 per 1000 output tokens, lowest GPT-5 at 0,58.

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