Gemini 3.1 Pro
Weighted composite
4.40
Recommendation
Practitioner-grade
OpenRouter ID
google/gemini-3.1-pro
Cohort
latest 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
| Part | Opus 4.7 (inline) | DeepSeek V4 Pro (judge) |
|---|---|---|
| Part A | 4.40 | 2.85 |
| Part B | 4.60sampled | 2.10 |
| Part C | 4.00 | 3.40 |
Notes from the evaluation
Gemini 3.1 Pro, Opus 4.7, GPT-5.5 (1 iteration each, both parts)
Source files in the repo
Cross-judge composites: analysis/results_overview.md
Raw responses: search raw_responses/Part_*_gemini_3_1_pro_* in the repo
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.
Welcome back.
You've already requested the full report.