Benchmark Almanac

LLM Persuasion Benchmark

GPT-5.4 1.71 leads since March 2026
Not in model cards

Models try to change another model’s stated position over multiple conversation turns.

The author publishes the model comparison in the repository.

Made by
Lech Mazur
Kind
Multi-turn conversation
Level
Everyday
Scored
Settled by events
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Multi-agent
Items from
Live play or votes
Refresh
Live
Run by
Anyone
In views
Agents, Kept fresh
Strongest model tested
GPT-5.4 #28 on the capability index
Last model added
March 2026
Scores refreshed
November 20th, 2026
15
Entries on its own leaderboard, 11 models we track

GPT-5.4 leads with 1.71 among models released by March 2026 GPT-5.4 leads with 1.71 among models released by March 2026

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 March 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 GPT-5.4 high reasoning 1.71
  2. 2 Claude Opus 4.6 high reasoning 1.67
  3. 3 ByteDance Seed2.0 Pro 1.64
  4. 4 Claude Sonnet 4.6 high reasoning 1.58
  5. 5 Kimi K2.5 thinking 1.33
  6. 6 Gemini 3.1 Pro 1.23
  7. 7 GLM-5 1.22
  8. 8 Grok 4.20 Beta 0309 Reasoning 1.20
  9. 9 Qwen3.5 397B-A17B 0.98
  10. 10 MiniMax-M2.7 0.96
  11. 11 Gemini 3.1 Flash-Lite 0.81
  12. 12 Baidu Ernie 5.0 0.77
  13. 13 DeepSeek-V3.2 0.71
  14. 14 Xiaomi MiMo V2 Pro 0.52
  15. 15 Mistral Large 3 0.42

Source: Official LLM Persuasion Benchmark leaderboard

#EntryScoreSettingDateSource
1 GPT-5.4 1.71 high reasoning Mar 2026 Official leaderboard
2 Claude Opus 4.6 1.67 high reasoning Feb 2026 Official leaderboard
3 ByteDance Seed2.0 Pro 1.64 Official leaderboard
4 Claude Sonnet 4.6 1.58 high reasoning Feb 2026 Official leaderboard
5 Kimi K2.5 1.33 thinking Jan 2026 Official leaderboard
6 Gemini 3.1 Pro 1.23 Feb 2026 Official leaderboard
7 GLM-5 1.22 Feb 2026 Official leaderboard
8 Grok 4.20 Beta 0309 1.20 Reasoning Official leaderboard
9 Qwen3.5 397B-A17B 0.98 Feb 2026 Official leaderboard
10 MiniMax-M2.7 0.96 Mar 2026 Official leaderboard
11 Gemini 3.1 Flash-Lite 0.81 Mar 2026 Official leaderboard
12 Baidu Ernie 5.0 0.77 Official leaderboard
13 DeepSeek-V3.2 0.71 Dec 2025 Official leaderboard
14 Xiaomi MiMo V2 Pro 0.52 Official leaderboard
15 Mistral Large 3 0.42 Dec 2025 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5.4 1.71 high reasoning Mar 2026 Official leaderboard
2 Claude Opus 4.6 1.67 high reasoning Feb 2026 Official leaderboard
3 Claude Sonnet 4.6 1.58 high reasoning Feb 2026 Official leaderboard
4 Kimi K2.5 1.33 thinking Jan 2026 Official leaderboard
5 Gemini 3.1 Pro 1.23 Feb 2026 Official leaderboard
6 GLM-5 1.22 Feb 2026 Official leaderboard
7 Qwen3.5 397B-A17B 0.98 Feb 2026 Official leaderboard
8 MiniMax-M2.7 0.96 Mar 2026 Official leaderboard
9 Gemini 3.1 Flash-Lite 0.81 Mar 2026 Official leaderboard
10 DeepSeek-V3.2 0.71 Dec 2025 Official leaderboard
11 Mistral Large 3 0.42 Dec 2025 Official leaderboard

4 models have held number one on the official leaderboard since 2023

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

DeepSeek Moonshot AI Anthropic OpenAI
Own leaderboard Not tested since Mar 2026
GPT-5.4 1.71

Source: Official LLM Persuasion Benchmark 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
0.00 0.50 1.00 1.50 2.00 2026 0.00 0.50 1.00 1.50 2.00 2026

Source: Official LLM Persuasion Benchmark 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 8 months ago, in March 2026, for MiniMax-M2.7. 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 official leaderboard (15 entries).
  • Pass Models scored 11 models we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 8 months ago, in March 2026, for MiniMax-M2.7.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 11 rows for models we track and 4 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