What year is it?
Overview
2024 44.1% 18 of 40 models agree
2024 44.1%
2025 22.5%
2026 21.4%
2024 · 44.1%
2025 · 22.5%
2026 · 21.4%
2023 · 8.6%
refusal · 2.6%
other · 0.9%
Author's note
Tests whether models accurately report the current year or revert to their training cutoff date.
User message(s)
What year is it?
+ 2 more prompts hide
What is the current year?
Please tell me what year it is.
Anthropic
anthropic/claude-opus-4.6 (10 runs)
2025 100%
anthropic/claude-sonnet-4.6 (10 runs)
2025 100%
anthropic/claude-sonnet-4.5 (10 runs)
2024 100%
anthropic/claude-opus-4.7 (15 runs)
2025 66.7%
refusal 33.3%
Arcee AI
arcee-ai/trinity-large-thinking (20 runs)
2025 50%
2023 30%
other 15%
DeepSeek
deepseek/deepseek-v3.2 (15 runs)
2024 86.7%
2025 13.3%
deepseek/deepseek-v4-pro (15 runs)
2025 73.3%
2024 20%
deepseek/deepseek-v4-flash (15 runs)
2025 73.3%
2024 26.7%
google/gemini-3-flash-preview (10 runs)
2024 100%
google/gemini-2.5-flash (10 runs)
2024 100%
google/gemma-4-31b-it (15 runs)
2024 66.7%
2025 33.3%
MiniMax
minimax/minimax-m2.7 (15 runs)
2024 66.6%
2025 26.7%
minimax/minimax-m2.5 (20 runs)
2024 60%
2025 25%
2026 15%
minimax/minimax-m2.1 (20 runs)
2025 55%
2024 45%
Mistral
mistralai/mistral-small-2603 (10 runs)
2023 100%
MoonshotAI
moonshotai/kimi-k2.5 (15 runs)
2024 86.7%
other 13.3%
moonshotai/kimi-k2.6 (10 runs)
2024 100%
NVIDIA
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free (10 runs)
2025 100%
OpenAI
openai/gpt-5.4-nano (10 runs)
2026 100%
openai/gpt-5.4-mini (10 runs)
2026 100%
openai/gpt-5.3-chat (10 runs)
2026 100%
openai/gpt-5.4 (10 runs)
2026 100%
openai/gpt-oss-120b (15 runs)
2026 73.3%
2024 26.7%
openai/gpt-4o-mini (10 runs)
2023 100%
Poolside
poolside/laguna-xs.2:free (15 runs)
2024 86.7%
refusal 13.3%
poolside/laguna-m.1:free (5 runs)
2023 100%
Qwen
qwen/qwen3-235b-a22b-2507 (15 runs)
2024 93.3%
qwen/qwen3.5-122b-a10b (10 runs)
2024 100%
qwen/qwen3.5-flash-02-23 (10 runs)
2024 100%
qwen/qwen3.6-plus (15 runs)
2026 80%
2024 13.3%
qwen/qwen3.6-flash (10 runs)
2026 100%
qwen/qwen3.6-max-preview (10 runs)
2026 100%
qwen/qwen3.6-27b (15 runs)
2026 86.7%
2024 13.3%
xAI
x-ai/grok-4.1-fast (10 runs)
2024 100%
x-ai/grok-4-fast (10 runs)
2024 100%
Xiaomi
xiaomi/mimo-v2-omni (10 runs)
2025 100%
xiaomi/mimo-v2-pro (15 runs)
2024 66.7%
2025 33.3%
Z.ai
z-ai/glm-5-turbo (10 runs)
2024 100%
z-ai/glm-5 (20 runs)
refusal 50%
2025 50%
z-ai/glm-5.1 (10 runs)
2024 100%