LLM Sycophancy Benchmark
Models judge the same dispute from opposite narrators’ perspectives. Contradictory judgments count toward the sycophancy rate.
The author publishes the model comparison in the repository.
- Made by
- Lech Mazur
- Kind
- Deception and alignment
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Propensity
- Behavior
- Misaligned with intent
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- Claude Fable 5 #12 on the capability index
- Last model added
- July 2026
- Scores refreshed
- November 20th, 2026
2 models share the top score of 0% among models released by July 2026 2 models share the top score of 0% among models released by July 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 July 2026, 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 13 more
- 1 Grok 4.5 high reasoning 0%
- 2 GPT-5.6 Terra high reasoning 0%
- 3 Claude Fable 5 medium reasoning 0.50%
- 4
Tencent Hy3 high 0.50%
- 5
Gemini 3.6 Flash 0.50%
- 6 GPT-5.6 Luna high reasoning 1.00%
- 7
Gemini 3.5 Flash-Lite 1.00%
- 8
Qwen3.7-Max 2026-06-08 1.50%
- 9 Baidu Ernie 5.1 2.00%
- 10
Qwen3.7 Flash 2.50%
- 11 Xiaomi MiMo V2.5 Pro 2.60%
- 12 GPT-5.6 Sol high reasoning 3.00%
- 13
Inkling high reasoning 3.50%
- 14
MiniMax-M3 3.60%
- 15 Kimi K3 4.50%
- 16
Gemma 4 31B IT reasoning 4.60%
- 17
DeepSeek-V4-Pro 5.10%
- 18
Qwen3.7-Plus 5.10%
- 19
DeepSeek-V4-Flash high reasoning 5.60%
- 20 Claude Sonnet 5 high reasoning 9.10%
- 21 GLM-5.2 max reasoning 12.6%
- 22 ByteDance Seed2.1 Pro 14.6%
- 23 Arcee Trinity Large Thinking 18.9%
- 24
Mistral Medium 3.5 high 22.4%
Source: Official LLM Sycophancy Benchmark leaderboard
- 1 Grok 4.5 high reasoning 0%
- 2 GPT-5.6 Terra high reasoning 0%
- 3 Claude Fable 5 medium reasoning 0.50%
- 4
Tencent Hy3 high 0.50%
- 5
Gemini 3.6 Flash 0.50%
- 6 GPT-5.6 Luna high reasoning 1.00%
- 7
Gemini 3.5 Flash-Lite 1.00%
- 8
Qwen3.7-Max 2026-06-08 1.50%
- 9
Qwen3.7 Flash 2.50%
- 10 GPT-5.6 Sol high reasoning 3.00%
- 11
Inkling high reasoning 3.50%
- 12
MiniMax-M3 3.60%
- 13 Kimi K3 4.50%
- 14
Gemma 4 31B IT reasoning 4.60%
- 15
DeepSeek-V4-Pro 5.10%
- 16
Qwen3.7-Plus 5.10%
- 17
DeepSeek-V4-Flash high reasoning 5.60%
- 18 Claude Sonnet 5 high reasoning 9.10%
- 19 GLM-5.2 max reasoning 12.6%
- 20
Mistral Medium 3.5 high 22.4%
Source: Official LLM Sycophancy Benchmark leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4.5 | 0% | high reasoning | Jul 2026 | Official leaderboard |
| 2 | GPT-5.6 Terra | 0% | high reasoning | Jul 2026 | Official leaderboard |
| 3 | Claude Fable 5 | 0.50% | medium reasoning | Jun 2026 | Official leaderboard |
| 4 | | 0.50% | high | Jul 2026 | Official leaderboard |
| 5 | | 0.50% | Jul 2026 | Official leaderboard | |
| 6 | GPT-5.6 Luna | 1.00% | high reasoning | Jul 2026 | Official leaderboard |
| 7 | | 1.00% | Jul 2026 | Official leaderboard | |
| 8 | | 1.50% | 2026-06-08 | May 2026 | Official leaderboard |
| 9 | Baidu Ernie 5.1 | 2.00% | Official leaderboard | ||
| 10 | | 2.50% | Jul 2026 | Official leaderboard | |
| 11 | Xiaomi MiMo V2.5 Pro | 2.60% | Official leaderboard | ||
| 12 | GPT-5.6 Sol | 3.00% | high reasoning | Jul 2026 | Official leaderboard |
| 13 | | 3.50% | high reasoning | Jul 2026 | Official leaderboard |
| 14 | | 3.60% | Jun 2026 | Official leaderboard | |
| 15 | Kimi K3 | 4.50% | Jul 2026 | Official leaderboard | |
| 16 | | 4.60% | reasoning | Apr 2026 | Official leaderboard |
| 17 | | 5.10% | Apr 2026 | Official leaderboard | |
| 18 | | 5.10% | Jun 2026 | Official leaderboard | |
| 19 | | 5.60% | high reasoning | Apr 2026 | Official leaderboard |
| 20 | Claude Sonnet 5 | 9.10% | high reasoning | Jun 2026 | Official leaderboard |
| 21 | GLM-5.2 | 12.6% | max reasoning | Jun 2026 | Official leaderboard |
| 22 | ByteDance Seed2.1 Pro | 14.6% | Official leaderboard | ||
| 23 | Arcee Trinity Large Thinking | 18.9% | Official leaderboard | ||
| 24 | | 22.4% | high | Apr 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4.5 | 0% | high reasoning | Jul 2026 | Official leaderboard |
| 2 | GPT-5.6 Terra | 0% | high reasoning | Jul 2026 | Official leaderboard |
| 3 | Claude Fable 5 | 0.50% | medium reasoning | Jun 2026 | Official leaderboard |
| 4 | | 0.50% | high | Jul 2026 | Official leaderboard |
| 5 | | 0.50% | Jul 2026 | Official leaderboard | |
| 6 | GPT-5.6 Luna | 1.00% | high reasoning | Jul 2026 | Official leaderboard |
| 7 | | 1.00% | Jul 2026 | Official leaderboard | |
| 8 | | 1.50% | 2026-06-08 | May 2026 | Official leaderboard |
| 9 | | 2.50% | Jul 2026 | Official leaderboard | |
| 10 | GPT-5.6 Sol | 3.00% | high reasoning | Jul 2026 | Official leaderboard |
| 11 | | 3.50% | high reasoning | Jul 2026 | Official leaderboard |
| 12 | | 3.60% | Jun 2026 | Official leaderboard | |
| 13 | Kimi K3 | 4.50% | Jul 2026 | Official leaderboard | |
| 14 | | 4.60% | reasoning | Apr 2026 | Official leaderboard |
| 15 | | 5.10% | Apr 2026 | Official leaderboard | |
| 16 | | 5.10% | Jun 2026 | Official leaderboard | |
| 17 | | 5.60% | high reasoning | Apr 2026 | Official leaderboard |
| 18 | Claude Sonnet 5 | 9.10% | high reasoning | Jun 2026 | Official leaderboard |
| 19 | GLM-5.2 | 12.6% | max reasoning | Jun 2026 | Official leaderboard |
| 20 | | 22.4% | high | Apr 2026 | 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.
Source: Official LLM Sycophancy Benchmark 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 LLM Sycophancy 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 Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6%
- Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts.
Gemini 4 Carbon 0%
- Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior.
Inkling 2 Mini 8.30%
- Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions.
Inkling 2 Small 4.70%
- Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior.
Inkling 2 Mini 9.80%
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 (24 entries).
- Pass Models scored 20 models we track, plus 4 other entries on its leaderboard.
- Pass Newest score The newest is from July 2026, for Qwen3.7 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Fable 5 (#12).
- Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 20 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.