Last refresh: 2026-05-17 · 17 models graded 3 OPEN RUBRIC ITEMS · DeepSeek judge coverage: 98%

← Leaderboard

Anthropic Sonnet 4.6

Weighted composite
4.35
Recommendation
Practitioner-grade
Cohort
legacy frontier

Scorecard

Per-criterion scores not available for this model. It appears in the cross-part overview but is not part of the canonical Models 1–10 hand-graded set; only the headline composite is shown.

Per-part composites

PartOpus 4.7 (inline)DeepSeek V4 Pro (judge)
Part A 4.35rep-sample → 4.55 full-pass⁴ 3.40
Part B 3.95sampled (`_or`, truncated)¹ / Opus inline regrade pending on `_or_r1_64k`³ 3.95
Part C 4.65(`_or`)² 4.60

Notes from the evaluation

Anthropic Sonnet 4.6 | `anthropic/claude-sonnet-4.6` | `raw_responses/Part_B_Sonnet_4_6_or_r1_openrouter.txt` | 123,142 | Q51–Q80 (response truncated at max_tokens=32000 mid-Q80) | | OpenAI GPT 5.4 (non-thinking) | `openai/gpt-5.4` | `raw_responses/Part_B_GPT_5_4_nonthinking_or_r1_openrouter.txt` | 91,174 | Q51–Q100 (full 50/50) |

Source files in the repo

Cross-judge composites: analysis/results_overview.md

Full report · PDF

Get the full report

All 111 questions, the complete rubric, per-model verdicts, and the methodology paper. Delivered as PDF within 60 seconds. CC-BY 4.0.

Sent from noreply@verdatir.com. We store your address to deliver the report and, if you opt in, future updates. See /privacy. CC-BY 4.0.
Welcome back. You've already requested the full report.

Download the report (PDF) ↓