Long-form story co-author
Generate and refine long-form fiction with continuity.
Provisional leader
Grok-4-0709
Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.
27.6%
Best benchmark score
37.5%
Confidence
All ranked models — top 3
Ranked Models
30
Evidence Quality
82%
Evidence Points
23
Top Signal
UGI Leaderboard: Writing ✍️
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| 🥇 | Grok-4-0709 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 27.6% |
| 🥈 | gemini-3-pro-preview Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Writing ✍️ | 26.1% |
| 🥉 | gemini-2.5-pro Strong on UGI Leaderboard Writing ✍️ and MWS Vision Bench validation_overall_score | 25.9% |
| #4 | gpt-4.1-20250414 Strong on UGI Leaderboard Writing ✍️ and MMLongBench-Doc Leaderboard acc_score_pct | 25.4% |
| #5 | gpt-5-2025-08-07 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 23.7% |
| #6 | o3-20250416 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 23.1% |
| #7 | claude-sonnet-4 Strong on UGI Leaderboard Writing ✍️ and Galileo Agent Leaderboard v2 Avg AC | 22.8% |
| #8 | gemini-3.1-pro-preview Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 22.5% |
| #9 | gemini-3-flash-preview Strong on UGI Leaderboard Writing ✍️ and MWS Vision Bench validation_overall_score | 21.6% |
| #10 | gpt-5.2-2025-12-11 Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Writing ✍️ | 21.3% |
| #11 | grok-4-1-fast-reasoning Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Writing ✍️ | 21.1% |
| #13 | gpt-5.4-2026-03-05 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 19.2% |
| #14 | claude-sonnet-4.6 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 18.8% |
| #15 | claude-opus-4-5-20251101 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 18.5% |
| #16 | qwen-2.5-72b-instruct Strong on EQ-Bench Leaderboard judgemark_score and Galileo Agent Leaderboard v2 Avg AC | 18.2% |
| #18 | kimi-k2.5-thinking Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 17.7% |
| #19 | o4-mini Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 17.1% |
| #20 | Kimi-K2-Instruct Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Entertainment | 17.0% |
| #21 | gpt-5.1-2025-11-13 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 16.8% |
| #22 | gemini-2.5-flash Strong on MWS Vision Bench validation_overall_score and Galileo Agent Leaderboard v2 Avg TSQ | 16.6% |
| #23 | gpt-5-mini-2025-08-07 Strong on MWS Vision Bench validation_overall_score and Vals MedQA overall_accuracy_pct | 16.5% |
| #25 | gpt-4o Strong on EQ-Bench Leaderboard judgemark_score and MEGA-Bench overall_score | 16.4% |
| #26 | GLM-4.6 Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Entertainment | 15.7% |
| #27 | grok-4-fast-reasoning Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 15.7% |
| #28 | grok-4-1-fast-non-reasoning Strong on BFCL Multi-turn Official Multi Turn Acc and UGI Leaderboard Writing ✍️ | 15.5% |
| #30 | Kimi K2 Thinking Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 14.9% |
| #32 | grok-3 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 14.0% |
| #35 | claude-opus-4 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 13.4% |
| #36 | claude-opus-4-1-20250805 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 13.3% |
| #39 | claude-opus-4-6 Strong on UGI Leaderboard Writing ✍️ and UGI Leaderboard Entertainment | 12.8% |
Compare Models
▶Ranking diagnostics & missing models
Source lift
Ranked
68
Sources
8
Quality
Low
Vals Legal Bench
UGI Leaderboard
Vals Tax Eval v2
Vals LiveCodeBench
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.