Benchmark Almanac

RPEval

Gemini 1.5 Pro Sep 2024 62.2% leads since May 2025
Not in model cards

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.

Released
May 2025
Kind
Overall chat quality
Level
Everyday
Scored
Checked automatically
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 2.5 Pro Jun 2025 #97 on the capability index
Last model added
June 2025
Scores refreshed
November 20th, 2026
12
Entries on its own leaderboard, 11 models we track

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:

  1. 1 Gemini 1.5 Pro Sep 2024 62.2%
  2. 2 GPT-4.1 57.6%
  3. 3 Mistral-medium-2505 56.7%
  4. 4 GPT-4.1 mini 53.1%
  5. 5 Gemini 2.5 Pro Jun 2025 48.5%
  6. 6 GPT-4o mini 48.1%
  7. 7 GPT-4o Aug 2024 44.4%
  8. 8 Gemma 3 12B 39.6%
  9. 9 Llama 3.2 3B 39.6%
  10. 10 Llama 3.2 1B 39.3%
  11. 11 Phi-4 36.3%
  12. 12 Qwen3-1.7B 30.5%

Source: Official RPEval leaderboard

#EntryScoreSettingDateSource
1 Gemini 1.5 Pro Sep 2024 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 Gemini 2.5 Pro Jun 2025 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 Gemma 3 12B 39.6% Mar 2025 Official leaderboard
9 Llama 3.2 3B 39.6% Sep 2024 Official leaderboard
10 Llama 3.2 1B 39.3% Sep 2024 Official leaderboard
11 Phi-4 36.3% Dec 2024 Official leaderboard
12 Qwen3-1.7B 30.5% Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 1.5 Pro Sep 2024 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 Gemini 2.5 Pro Jun 2025 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 Gemma 3 12B 39.6% Mar 2025 Official leaderboard
8 Llama 3.2 3B 39.6% Sep 2024 Official leaderboard
9 Llama 3.2 1B 39.3% Sep 2024 Official leaderboard
10 Phi-4 36.3% Dec 2024 Official leaderboard
11 Qwen3-1.7B 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. 1 GPT-4.1 mini ↑2 66.3%
  2. 2 GPT-4o mini ↑3 58.9%
  3. 3 GPT-4o Aug 2024 ↑3 56%
  4. 4 Gemini 1.5 Pro Sep 2024 ↓3 53.1%
  5. 5 GPT-4.1 ↓3 51.3%
  6. 6 Llama 3.2 1B ↑3 40.3%
  7. 7 Phi-4 ↑3 38.3%
  8. 8 Llama 3.2 3B 37.7%
  9. 9 Gemini 2.5 Pro Jun 2025 ↓5 36.2%
  10. 10 Qwen3-1.7B ↑1 26.9%

Number one over time

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

Google DeepMind
Own leaderboard Not tested since Jun 2025

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.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Gemini 1.5 Pro GPT-4o mini 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Gemini 1.5 Pro GPT-4o mini

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

All 144 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.

How we check