Lore bible generator
Create consistent lore references (timelines, factions, glossaries).
Provisional leader
gpt-4.1-20250414
Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.
20.1%
Best benchmark score
30.6%
Confidence
All ranked models — top 3
Ranked Models
30
Evidence Quality
80%
Evidence Points
21
Top Signal
MMLongBench-Doc Leaderboard: acc_score_pct
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| 🥇 | gpt-4.1-20250414 Strong on MMLongBench-Doc Leaderboard acc_score_pct and UGI Leaderboard Writing ✍️ | 20.1% |
| 🥈 | gpt-5-2025-08-07 Strong on UGI Leaderboard Writing ✍️ and ExtractBench Paper Baselines credit_pass_rate_pct | 19.9% |
| 🥉 | Grok-4-0709 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 19.7% |
| #4 | gemini-3-pro-preview Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Writing ✍️ | 18.6% |
| #5 | gemini-2.5-pro Strong on UGI Leaderboard Writing ✍️ and MWS Vision Bench validation_overall_score | 18.5% |
| #6 | qwen-2.5-72b-instruct Strong on EQ-Bench Leaderboard judgemark_score and DuckDB NSQL Leaderboard all_execution_accuracy | 17.5% |
| #7 | gpt-4o Strong on EQ-Bench Leaderboard judgemark_score and JSONSchemaBench Leaderboard medium_schema_compliance_pct | 16.6% |
| #8 | o3-20250416 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 16.5% |
| #9 | claude-sonnet-4 Strong on UGI Leaderboard Writing ✍️ and Galileo Agent Leaderboard v2 Avg AC | 16.3% |
| #10 | gemini-3.1-pro-preview Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 16.0% |
| #11 | gemini-3-flash-preview Strong on UGI Leaderboard Writing ✍️ and MWS Vision Bench validation_overall_score | 15.4% |
| #12 | gpt-5.2-2025-12-11 Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Writing ✍️ | 15.2% |
| #13 | grok-4-1-fast-reasoning Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Writing ✍️ | 15.0% |
| #15 | gpt-5.4-2026-03-05 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 13.6% |
| #16 | claude-sonnet-4.6 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 13.4% |
| #17 | claude-opus-4-5-20251101 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 13.2% |
| #19 | kimi-k2.5-thinking Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 12.6% |
| #22 | o4-mini Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 12.2% |
| #23 | Kimi-K2-Instruct Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Entertainment | 12.1% |
| #24 | gpt-5.1-2025-11-13 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 12.0% |
| #25 | gemini-2.5-flash Strong on MWS Vision Bench validation_overall_score and Galileo Agent Leaderboard v2 Avg TSQ | 11.8% |
| #26 | gpt-5-mini-2025-08-07 Strong on MWS Vision Bench validation_overall_score and Vals MedQA overall_accuracy_pct | 11.7% |
| #33 | GLM-4.6 Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Entertainment | 11.2% |
| #34 | grok-4-fast-reasoning Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 11.2% |
| #36 | grok-4-1-fast-non-reasoning Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Writing ✍️ | 11.0% |
| #39 | Kimi K2 Thinking Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 10.6% |
| #43 | grok-3 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 10.0% |
| #46 | gpt-4o-20241120 Strong on MMLongBench-Doc Leaderboard acc_score_pct and DuckDB NSQL Leaderboard all_execution_accuracy | 9.7% |
| #47 | claude-opus-4 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 9.5% |
| #48 | claude-opus-4-1-20250805 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 9.5% |
Compare Models
▶Ranking diagnostics & missing models
Source lift
Ranked
48
Sources
8
Quality
Low
UGI Leaderboard
Vals Legal Bench
Vals MedQA
Vals Tax Eval v2
Missing frontier models
No obvious gaps right now.
▶Taxonomy & task details
Core tasks
Required modes
Domains
Related in Creative
Interactive fiction / DM
Run interactive fiction with state tracking and user agency.
NPC dialogue
Low-latency in-character dialogue suitable for games.
SFW roleplay and simulation
Roleplay/simulations for learning or entertainment with state tracking.
Poetry and lyrics
Generate poems and lyrics with style control and variation.