What year is it?
Overview
2024 32.8% 43 of 131 models agree
2024 33%
2026 27%
2025 20%
2023 14%
2024 · 32.8%
2026 · 26.6%
2025 · 19.6%
2023 · 14.3%
hedge · 2.3%
refusal · 3.3%
Other answers · 1% + 4 answers hide
- 2022 0.5%
- 2021 0.3%
- other 0.2%
- 2029 0.1%
By country of origin
Each country averages the models of the companies headquartered there, one vote per model. Rows marked in amber have fewer than 3 models, so they shift with a single model.United States
73 models
2024 26%
2026 31%
2025 19%
2023 14%
China
49 models
2024 49%
2026 17%
2025 24%
France
5 models
2023 100%
South Korea
3 models
2026 97%
Japan
1 model
2026 100%
By company
Each company averages its own models, one vote per model.OpenAI
22 models
2024 10%
2026 54%
2025 13%
2023 18%
Anthropic
13 models
2024 20%
2025 42%
hedge 18%
refusal 12%
Qwen
13 models
2024 49%
2026 50%
Google
11 models
2024 52%
2026 33%
Meta
10 models
2024 32%
2026 45%
2025 10%
2023 12%
Z.ai
8 models
2024 54%
2025 37%
DeepSeek
7 models
2024 28%
2026 16%
2025 35%
2023 21%
xAI
7 models
2024 59%
2025 25%
refusal 10%
Mistral
5 models
2023 100%
Bytedance
4 models
2024 63%
2023 25%
MiniMax
4 models
2024 50%
2026 13%
2025 33%
MoonshotAI
4 models
2024 58%
2025 29%
Tencent
4 models
2024 65%
2025 10%
2023 25%
Xiaomi
4 models
2024 34%
2025 59%
Amazon
3 models
2024 13%
2023 70%
refusal 17%
Upstage
3 models
2026 97%
+ 6 with fewer than 3 models hide
Inception
2 models
2026 100%
NVIDIA
2 models
2025 78%
refusal 20%
ThinkingMachines
2 models
2024 40%
2026 25%
2025 28%
IBM
1 model
2025 33%
2023 67%
Sakana
1 model
2026 100%
StepFun
1 model
2024 40%
2025 60%
By model release quarter
Each quarter averages only the models released in that quarter. 6 models excluded (no release date on record). 2024
2026
2025
2023
hedge
refusal
Other answers
+ Show data hide
| Quarter | Models | 2024 | 2026 | 2025 | 2023 | hedge | refusal | Other answers |
|---|---|---|---|---|---|---|---|---|
| 2023 Q2 | 2 | 0% | 0% | 0% | 50% | 0% | 0% | 50% |
| 2024 Q1 | 2 | 0% | 0% | 0% | 100% | 0% | 0% | 0% |
| 2024 Q3 | 5 | 16% | 0% | 0% | 82% | 0% | 0% | 2% |
| 2024 Q4 | 3 | 17% | 17% | 0% | 67% | 0% | 0% | 0% |
| 2025 Q1 | 4 | 13% | 0% | 3% | 85% | 0% | 0% | 0% |
| 2025 Q2 | 9 | 56% | 22% | 0% | 22% | 0% | 0% | 0% |
| 2025 Q3 | 4 | 76% | 18% | 0% | 5% | 0% | 0% | 0% |
| 2025 Q4 | 8 | 68% | 0% | 9% | 14% | 1% | 7% | 0% |
| 2026 Q1 | 19 | 37% | 32% | 21% | 5% | 0% | 4% | 1% |
| 2026 Q2 | 30 | 37% | 27% | 27% | 3% | 1% | 5% | 0% |
| 2026 Q3 | 39 | 15% | 42% | 29% | 3% | 7% | 4% | 0% |
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.
131 models
Amazon
amazon/nova-2-lite-v1 (10 runs) · consistency 44.4
2024 40%
2023 10%
refusal 50%
amazon/nova-lite-v1 (10 runs) · consistency 100
2023 100%
amazon/nova-micro-v1 (10 runs) · consistency 100
2023 100%
Anthropic
anthropic/claude-sonnet-5.5 (10 runs) · consistency 61.1
2025 70%
hedge 30%
anthropic/claude-opus-5.5 (10 runs) · consistency 61.1
2025 20%
hedge 80%
anthropic/claude-fable-5.1 (10 runs) · consistency 61.1
2025 20%
hedge 80%
anthropic/claude-opus-5 (20 runs) · consistency 27.8
2025 15%
hedge 40%
refusal 45%
anthropic/claude-sonnet-5 (20 runs) · consistency 44.4
2024 55%
2025 45%
anthropic/claude-fable-5 (20 runs) · consistency 100
2025 95%
anthropic/claude-opus-4.8 (15 runs) · consistency 58.3
2025 13%
refusal 80%
anthropic/claude-opus-4.7 (15 runs) · consistency 50
2025 67%
refusal 33%
anthropic/claude-sonnet-4.6 (10 runs) · consistency 100
2025 100%
anthropic/claude-opus-4.6 (10 runs) · consistency 100
2025 100%
anthropic/claude-haiku-4.5 (20 runs) · consistency 100
2024 95%
anthropic/claude-sonnet-4.5 (10 runs) · consistency 100
2024 100%
anthropic/claude-3-haiku (10 runs) · consistency 100
2023 100%
Bytedance
bytedance-seed/seed-2-1-turbo (10 runs) · consistency 50
2024 70%
2025 30%
bytedance-seed/seed-2.0-lite (10 runs) · consistency 100
2024 100%
bytedance-seed/seed-1.6 (10 runs) · consistency 77.8
2024 80%
hedge 10%
refusal 10%
bytedance-seed/seed-1.6-flash (10 runs) · consistency 100
2023 100%
DeepSeek
deepseek/deepseek-v4-pro-0813 (10 runs) · consistency 61.1
2026 80%
2025 20%
deepseek/deepseek-v4-flash-0731 (9 runs) · consistency 36.1
2024 11%
2026 33%
2025 56%
deepseek/deepseek-v4-flash (15 runs) · consistency 61.1
2024 27%
2025 73%
deepseek/deepseek-v4-pro (15 runs) · consistency 77.8
2024 20%
2025 73%
deepseek/deepseek-v3.2 (15 runs) · consistency 77.8
2024 87%
2025 13%
deepseek/deepseek-chat-v3-0324 (10 runs) · consistency 50
2024 40%
2023 60%
deepseek/deepseek-r1 (10 runs) · consistency 58.3
2024 10%
2025 10%
2023 80%
google/gemini-3.8-flash (10 runs) · consistency 100
2024 10%
2026 90%
google/gemini-3.7-flash (10 runs) · consistency 77.8
2024 10%
2026 90%
google/gemini-3.6-flash (10 runs) · consistency 77.8
2024 10%
2026 90%
google/gemini-3.5-flash (15 runs) · consistency 77.8
2026 93%
google/gemini-3.1-flash-lite (10 runs) · consistency 100
2024 100%
google/gemma-4-26b-a4b-it (20 runs) · consistency 100
2024 85%
2025 15%
google/gemma-4-31b-it (15 runs) · consistency 50
2024 67%
2025 33%
google/gemini-3-flash-preview (10 runs) · consistency 100
2024 100%
google/gemini-2.5-flash-lite (20 runs) · consistency 77.8
2024 85%
2023 15%
google/gemini-2.5-flash (10 runs) · consistency 100
2024 100%
google/gemma-2-27b-it (10 runs) · consistency 77.8
2024 10%
2023 90%
IBM
ibm-granite/granite-4.1-8b (15 runs) · consistency 50
2025 33%
2023 67%
Inception
inception/mercury-2.5 (10 runs) · consistency 100
2026 100%
inception/mercury-2 (10 runs) · consistency 100
2026 100%
Meta
meta/muse-spark-1.3 (10 runs) · consistency 100
2026 100%
meta/muse-glimmer-30b (10 runs) · consistency 100
2025 100%
meta/muse-spark-1.2 (10 runs) · consistency 100
2026 100%
meta/muse-spark-1.1 (10 runs) · consistency 100
2026 100%
meta-llama/llama-4-maverick (10 runs) · consistency 100
2024 100%
meta-llama/llama-4-scout (10 runs) · consistency 100
2024 100%
meta-llama/llama-3.3-70b-instruct (10 runs) · consistency 44.4
2024 50%
2026 50%
meta-llama/llama-3.1-70b-instruct (10 runs) · consistency 77.8
2024 20%
2023 80%
meta-llama/llama-3.1-8b-instruct (10 runs) · consistency 36.1
2024 50%
2023 40%
2029 10%
muse-spark-1.1 (20 runs) · consistency 100
2026 100%
MiniMax
minimax/minimax-m3 (30 runs) · consistency 16.7
2024 27%
2026 37%
2025 23%
hedge 10%
minimax/minimax-m2.7 (15 runs) · consistency 44.4
2024 67%
2025 27%
minimax/minimax-m2.5 (20 runs) · consistency 50
2024 60%
2026 15%
2025 25%
minimax/minimax-m2.1 (20 runs) · consistency 44.4
2024 45%
2025 55%
Mistral
mistralai/mistral-small-2603 (10 runs) · consistency 100
2023 100%
mistralai/mistral-small-3.2-24b-instruct (20 runs) · consistency 100
2023 100%
mistralai/mistral-small-24b-instruct-2501 (10 runs) · consistency 100
2023 100%
mistralai/mistral-nemo (20 runs) · consistency 100
2023 100%
mistralai/mistral-large (10 runs) · consistency 100
2023 100%
MoonshotAI
moonshotai/kimi-k3 (20 runs) · consistency 44.4
2025 60%
hedge 20%
refusal 20%
moonshotai/kimi-k2.7-code (20 runs) · consistency 44.4
2024 45%
2025 55%
moonshotai/kimi-k2.6 (10 runs) · consistency 100
2024 100%
moonshotai/kimi-k2.5 (15 runs) · consistency 77.8
2024 87%
other 13%
NVIDIA
nvidia/nemotron-3.5-lightning (10 runs) · consistency 100
2025 100%
nvidia/nemotron-3-ultra-550b-a55b (20 runs) · consistency 36.1
2025 55%
refusal 40%
OpenAI
openai/gpt-6.1-sol (10 runs) · consistency 77.8
2026 90%
refusal 10%
openai/gpt-6-luna (10 runs) · consistency 100
2025 100%
openai/gpt-6-sol (10 runs) · consistency 100
2026 100%
openai/gpt-6-astra (10 runs) · consistency 100
2026 100%
openai/gpt-5.6-luna (20 runs) · consistency 77.8
2026 25%
2025 70%
openai/gpt-5.6-sol (20 runs) · consistency 100
2026 90%
2025 10%
openai/gpt-5.6-terra (20 runs) · consistency 77.8
2025 95%
openai/gpt-5.5 (10 runs) · consistency 100
2026 100%
openai/gpt-5.4-mini (10 runs) · consistency 100
2026 100%
openai/gpt-5.4-nano (10 runs) · consistency 100
2026 100%
openai/gpt-5.4 (10 runs) · consistency 100
2026 100%
openai/gpt-5.3-chat (10 runs) · consistency 100
2026 100%
openai/gpt-oss-120b (15 runs) · consistency 61.1
2024 27%
2026 73%
openai/o3 (10 runs) · consistency 100
2026 100%
openai/o4-mini (10 runs) · consistency 100
2026 100%
openai/gpt-4.1 (10 runs) · consistency 100
2024 100%
openai/gpt-4.1-mini (20 runs) · consistency 100
2024 100%
openai/gpt-4.1-nano (10 runs) · consistency 100
2023 100%
openai/o3-mini (10 runs) · consistency 100
2023 100%
openai/gpt-4o-mini (10 runs) · consistency 100
2023 100%
openai/gpt-3.5-turbo (10 runs) · consistency 27.8
2023 40%
2022 20%
2021 40%
openai/gpt-4 (10 runs) · consistency 44.4
2023 60%
2022 40%
Qwen
qwen/qwen3.8-max-0902 (10 runs) · consistency 77.8
2024 10%
2026 90%
qwen/qwen3.8-flash (8 runs)
2024 88%
2026 13%
qwen/qwen3.8-27b (10 runs) · consistency 100
2024 100%
qwen/qwen3.7-flash (10 runs) · consistency 61.1
2024 20%
2026 80%
qwen/qwen3.7-plus (10 runs) · consistency 100
2026 100%
qwen/qwen3.7-max (10 runs) · consistency 100
2024 100%
qwen/qwen3.6-27b (15 runs) · consistency 100
2024 13%
2026 87%
qwen/qwen3.6-flash (10 runs) · consistency 100
2026 100%
qwen/qwen3.6-max-preview (10 runs) · consistency 100
2026 100%
qwen/qwen3.6-plus (15 runs) · consistency 77.8
2024 13%
2026 80%
qwen/qwen3.5-122b-a10b (10 runs) · consistency 100
2024 100%
qwen/qwen3.5-flash-02-23 (10 runs) · consistency 100
2024 100%
qwen/qwen3-235b-a22b-2507 (15 runs) · consistency 77.8
2024 93%
Sakana
sakana/fugu-ultra (10 runs) · consistency 100
2026 100%
StepFun
stepfun/step-3.7-flash (20 runs) · consistency 50
2024 40%
2025 60%
Tencent
tencent/hy4-preview (10 runs) · consistency 50
2024 70%
2025 30%
tencent/hy-mt2-30b-a3b (10 runs) · consistency 100
2023 100%
tencent/hy3 (10 runs) · consistency 100
2024 90%
2025 10%
tencent/hy3:free (20 runs) · consistency 100
2024 100%
ThinkingMachines
thinkingmachines/inkling-small (10 runs) · consistency 61.1
2024 80%
2025 20%
thinkingmachines/inkling (20 runs) · consistency 30.6
2026 50%
2025 35%
Upstage
upstage/solar-mini4 (10 runs) · consistency 100
2026 100%
upstage/solar-pro4 (10 runs) · consistency 100
2026 100%
upstage/solar-pro-3 (10 runs) · consistency 77.8
2026 90%
2025 10%
xAI
x-ai/grok-4.7 (10 runs) · consistency 36.1
2026 30%
hedge 10%
refusal 60%
x-ai/grok-4.6 (10 runs) · consistency 100
2024 90%
2025 10%
x-ai/grok-4.5 (20 runs) · consistency 61.1
2024 15%
2025 80%
x-ai/grok-4.3 (10 runs) · consistency 100
2024 100%
x-ai/grok-4.20 (20 runs) · consistency 58.3
2025 85%
x-ai/grok-4-fast (10 runs) · consistency 100
2024 100%
x-ai/grok-4.1-fast (10 runs) · consistency 100
2024 100%
Xiaomi
xiaomi/mimo-v2.5 (20 runs) · consistency 50
2024 25%
2025 65%
xiaomi/mimo-v2.5-pro (20 runs) · consistency 33.3
2024 45%
2025 40%
2023 10%
xiaomi/mimo-v2-omni (10 runs) · consistency 100
2025 100%
xiaomi/mimo-v2-pro (15 runs) · consistency 61.1
2024 67%
2025 33%
Z.ai
z-ai/glm-5.3-flash (10 runs) · consistency 100
2025 100%
z-ai/glm-5.3 (10 runs) · consistency 77.8
2025 90%
hedge 10%
z-ai/glm-5.2 (20 runs) · consistency 44.4
2024 45%
2025 55%
z-ai/glm-5.1 (10 runs) · consistency 100
2024 100%
z-ai/glm-5-turbo (10 runs) · consistency 100
2024 100%
z-ai/glm-5 (20 runs) · consistency 50
2025 50%
refusal 50%
z-ai/glm-4.7-flash (20 runs) · consistency 100
2024 90%
z-ai/glm-4.7 (20 runs) · consistency 77.8
2024 95%
No models match.