RPEval
Models respond in character to 9,018 scenarios. The test checks emotions, decisions, moral choices, and whether characters reveal knowledge outside their setting.
The authors’ leaderboard scores 12 models. It averages three percentages, combining decisions and moral choices into one category.
- Made by
- Yassine El Boudouri and colleagues
- Released
- May 2025
- Kind
- Overall chat quality
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Gemini 2.5 Pro Jun 2025 #97 on the capability index
- Last model added
- June 2025
- Scores refreshed
- November 20th, 2026
Gemini 1.5 Pro leads with 62.2% among models released by June 2025 Gemini 1.5 Pro leads with 62.2% among models released by June 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in June 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
Gemini 1.5 Pro Sep 2024 62.2%
- 2 GPT-4.1 57.6%
- 3 Mistral-medium-2505 56.7%
- 4 GPT-4.1 mini 53.1%
- 5
Gemini 2.5 Pro Jun 2025 48.5%
- 6 GPT-4o mini 48.1%
- 7 GPT-4o Aug 2024 44.4%
- 8
Gemma 3 12B 39.6%
- 9
Llama 3.2 3B 39.6%
- 10
Llama 3.2 1B 39.3%
- 11
Phi-4 36.3%
- 12
Qwen3-1.7B 30.5%
Source: Official RPEval leaderboard
- 1
Gemini 1.5 Pro Sep 2024 62.2%
- 2 GPT-4.1 57.6%
- 3 GPT-4.1 mini 53.1%
- 4
Gemini 2.5 Pro Jun 2025 48.5%
- 5 GPT-4o mini 48.1%
- 6 GPT-4o Aug 2024 44.4%
- 7
Gemma 3 12B 39.6%
- 8
Llama 3.2 3B 39.6%
- 9
Llama 3.2 1B 39.3%
- 10
Phi-4 36.3%
- 11
Qwen3-1.7B 30.5%
Source: Official RPEval leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 62.2% | Sep 2024 | Official leaderboard | |
| 2 | GPT-4.1 | 57.6% | Apr 2025 | Official leaderboard | |
| 3 | Mistral-medium-2505 | 56.7% | Official leaderboard | ||
| 4 | GPT-4.1 mini | 53.1% | Apr 2025 | Official leaderboard | |
| 5 | | 48.5% | Jun 2025 | Official leaderboard | |
| 6 | GPT-4o mini | 48.1% | Jul 2024 | Official leaderboard | |
| 7 | GPT-4o Aug 2024 | 44.4% | Aug 2024 | Official leaderboard | |
| 8 | | 39.6% | Mar 2025 | Official leaderboard | |
| 9 | | 39.6% | Sep 2024 | Official leaderboard | |
| 10 | | 39.3% | Sep 2024 | Official leaderboard | |
| 11 | | 36.3% | Dec 2024 | Official leaderboard | |
| 12 | | 30.5% | Apr 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 62.2% | Sep 2024 | Official leaderboard | |
| 2 | GPT-4.1 | 57.6% | Apr 2025 | Official leaderboard | |
| 3 | GPT-4.1 mini | 53.1% | Apr 2025 | Official leaderboard | |
| 4 | | 48.5% | Jun 2025 | Official leaderboard | |
| 5 | GPT-4o mini | 48.1% | Jul 2024 | Official leaderboard | |
| 6 | GPT-4o Aug 2024 | 44.4% | Aug 2024 | Official leaderboard | |
| 7 | | 39.6% | Mar 2025 | Official leaderboard | |
| 8 | | 39.6% | Sep 2024 | Official leaderboard | |
| 9 | | 39.3% | Sep 2024 | Official leaderboard | |
| 10 | | 36.3% | Dec 2024 | Official leaderboard | |
| 11 | | 30.5% | Apr 2025 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Emotional Understanding, Decision-Making/Moral Alignment and In-Character Consistency. Each ranks models on one part of the test. GPT-4.1 mini leads 2 of them, and Gemini 1.5 Pro leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Emotional Understanding
11 models we track have a score here.
- 1 GPT-4.1 mini ↑2 66.3%
- 2 GPT-4o mini ↑3 58.9%
- 3 GPT-4o Aug 2024 ↑3 56%
- 4
Gemini 1.5 Pro Sep 2024 ↓3 53.1%
- 5 GPT-4.1 ↓3 51.3%
- 6
Llama 3.2 1B ↑3 40.3%
- 7
Phi-4 ↑3 38.3%
- 8
Llama 3.2 3B 37.7%
- 9
Gemini 2.5 Pro Jun 2025 ↓5 36.2%
- 10
Qwen3-1.7B ↑1 26.9%
Decision-Making/Moral Alignment
11 models we track have a score here.
- 1 GPT-4.1 mini ↑2 79.8%
- 2 GPT-4o mini ↑3 77.5%
- 3
Gemini 1.5 Pro Sep 2024 ↓2 73.9%
- 4 GPT-4.1 ↓2 71.7%
- 5 GPT-4o Aug 2024 ↑1 71.4%
- 6
Gemini 2.5 Pro Jun 2025 ↓2 70.4%
- 7
Gemma 3 12B 67.2%
- 8
Phi-4 ↑2 56.1%
- 9
Qwen3-1.7B ↑2 38.9%
- 10
Llama 3.2 3B ↓2 33%
In-Character Consistency
11 models we track have a score here.
- 1
Gemini 1.5 Pro Sep 2024 59.8%
- 2 GPT-4.1 49.8%
- 3
Llama 3.2 1B ↑6 48.1%
- 4
Llama 3.2 3B ↑4 48.1%
- 5
Gemini 2.5 Pro Jun 2025 ↓1 39%
- 6
Gemma 3 12B ↑1 26.6%
- 7
Qwen3-1.7B ↑4 25.7%
- 8
Phi-4 ↑2 14.5%
- 9 GPT-4.1 mini ↓6 13.3%
- 10 GPT-4o mini ↓5 7.82%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official RPEval leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official RPEval 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 Instructions and chat
- IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy.
Gemma 4 31B IT 98.9%
- IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose). Flint 89.2%
- MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
- Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
- AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics.
MAI-Thinking-1 85%
- MM-IFEval In use Multimodal models follow image-grounded instructions with exact output constraints. Checks mix rule-based verification and a judge model. GPT-4o 64.6%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 17 months ago, in June 2025, for Gemini 2.5 Pro. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (12 entries).
- Pass Models scored 11 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 17 months ago, in June 2025, for Gemini 2.5 Pro.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Pro (#97).
- Pass Headroom The best is 62.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 11 rows for models we track and 1 other entry 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.