Benchmark Almanac

ProSA

Not in model cards

Models answer equivalent instructions with different wording. PromptSensiScore measures how much model performance varies with the prompt.

Released
October 2024
Kind
Following precise instructions
Level
University
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Propensity
Behavior
Unreliability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Last model added
February 2024
Scores refreshed
November 20th, 2026
5
Entries in its paper, 2 models we track

Qwen1.5-14B-Chat leads with 0.14 Qwen1.5-14B-Chat leads with 0.14

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the plain mean of its two PSS benchmark parts. 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.

  1. 1 InternLM2-20B-Chat 0.14
  2. 2 Qwen1.5-14B-Chat 0.14
  3. 3 Llama3-70B-Instruct 0.14
  4. 4 Llama3-8B-Instruct 0.14
  5. 5 Qwen1.5-72B 0.14

Source: The ProSA paper

Source: The ProSA paper

#EntryScoreSettingDateSource
1 InternLM2-20B-Chat 0.14 Official leaderboard
2 Qwen1.5-14B-Chat 0.14 Feb 2024 Official leaderboard
3 Llama3-70B-Instruct 0.14 Official leaderboard
4 Llama3-8B-Instruct 0.14 Official leaderboard
5 Qwen1.5-72B 0.14 Feb 2024 Official leaderboard
#ModelScoreSettingDateSource
1 Qwen1.5-14B-Chat 0.14 Feb 2024 Official leaderboard
2 Qwen1.5-72B 0.14 Feb 2024 Official leaderboard

Scores over time

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

In the benchmark’s paper
0.13 0.14 0.14 0.14 0.14 0.14 2024 0.13 0.14 0.14 0.14 0.14 0.14 2024

Source: Official ProSA 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in February 2024, for Qwen1.5-14B-Chat. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (5 entries).
  • Pass Models scored 2 models we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in February 2024, for Qwen1.5-14B-Chat.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 2 rows for models we track and 3 other entries 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