Benchmark Almanac

E/RP Leaderboard by PsychoSmiley

Kimi K2.5 289.0 leads since January 2026
Not in model cards

Models answer 25 yes or no questions and write three roleplay responses. Claude Sonnet 4.5 grades the two parts for up to 325 points.

The maker publishes scores for six named models. Three open responses account for 300 of the 325 possible points.

Made by
PsychoSmiley
Released
November 2025
Kind
Creative writing
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Gemini 3 Pro #56 on the capability index
Last model added
June 2026
Scores refreshed
November 20th, 2026
6
Models scored on its own leaderboard

Kimi K2.5 leads with 289.0 among models released by June 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in June 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Kimi K2.5 289.0
  2. 2 Gemini 3 Pro 283.0
  3. 3 Grok 4.1 Fast 279.0
  4. 4 Claude Opus 4.5 216.0
  5. 5 GPT-5.1-Codex 201.0
  6. 6 Nemotron 3 Ultra 184.0

Source: Official E/RP Leaderboard by PsychoSmiley leaderboard

#ModelScoreSettingReleasedRun onSource
1 Kimi K2.5 289.0 Jan 2026 Feb 2026 Official leaderboard
2 Gemini 3 Pro 283.0 Nov 2025 Nov 2025 Official leaderboard
3 Grok 4.1 Fast 279.0 Nov 2025 Nov 2025 Official leaderboard
4 Claude Opus 4.5 216.0 Nov 2025 Nov 2025 Official leaderboard
5 GPT-5.1-Codex 201.0 Nov 2025 Nov 2025 Official leaderboard
6 Nemotron 3 Ultra 184.0 Jun 2026 Jun 2026 Official leaderboard

Rankings by part

We read 2 parts from the benchmark’s own leaderboard: Yes/No and Open-ended. Each ranks models on one part of the test. Grok 4.1 Fast leads Yes/No and Kimi K2.5 leads Open-ended. Arrows show how far a model moved from its overall rank among the models we track.

Yes/No

6 models we track have a score here.

  1. 1 Grok 4.1 Fast ↑2 20.0
  2. 2 Kimi K2.5 ↓1 17.0
  3. 3 GPT-5.1-Codex ↑2 15.0
  4. 4 Gemini 3 Pro ↓2 15.0
  5. 5 Claude Opus 4.5 ↓1 14.0
  6. 6 Nemotron 3 Ultra 13.0

3 models have held number one on the official leaderboard since its release in November 2025

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI Google DeepMind Moonshot AI
Own leaderboard Not tested since Jun 2026
Kimi K2.5 289.0

Source: Official E/RP Leaderboard by PsychoSmiley leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
175.0 200.0 225.0 250.0 275.0 300.0 2026 175.0 200.0 225.0 250.0 275.0 300.0 2026

Source: Official E/RP Leaderboard by PsychoSmiley leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Writing and taste

All 65 in Writing and taste
  • Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
  • WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
  • Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing. MiniMax-Text-01 81.3%
  • DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate. DeepSeek-V4-Pro 62.6%
  • Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
  • Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right. Muse Spark 0.21

Data audit

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 6 models we track.
  • Pass Newest score The newest is from June 2026, for Nemotron 3 Ultra.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3 Pro (#56).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on psychosmiley.github.io: 6 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check