Gemini has the highest family mean on the performance z-score axis and also sits high on the confidence z-score axis. The family mean lies close to the diagonal, with relative confidence and relative performance nearly matched. The highlighted cloud is concentrated in the upper-right region of the map.
Where Google · Gemini sits in the cloud
Disposition: where each model draws the line
Competitive context, benchmark by benchmark
| # | Model | Fβ ? | Prec ? | Rec ? | Task acc ? |
|---|---|---|---|---|---|
| 1 | Gemini 3 Pro | 0.785 | 0.77 | 0.80 | 0.65 |
| 2 | Gemini 3 Flash | 0.782 | 0.70 | 0.88 | 0.59 |
| 3 | Gemini 2.5 Pro | 0.764 | 0.71 | 0.83 | 0.58 |
| 4 | Claude Sonnet 4.5 | 0.753 | 0.78 | 0.72 | 0.59 |
| 5 | GPT-4o | 0.739 | 0.69 | 0.80 | 0.54 |
| 6 | DeepSeek R1 | 0.733 | 0.76 | 0.70 | 0.57 |
| 7 | Claude Haiku 4.5 | 0.716 | 0.79 | 0.65 | 0.48 |
| 8 | Mistral Medium 3.1 | 0.703 | 0.65 | 0.77 | 0.52 |
| 9 | GPT-4o mini | 0.686 | 0.56 | 0.88 | 0.45 |
| 10 | Gemini 2.0 Flash | 0.683 | 0.58 | 0.82 | 0.45 |
| 11 | GPT-5.2 | 0.673 | 0.84 | 0.56 | 0.62 |
| 12 | Gemini 2.5 Flash | 0.670 | 0.58 | 0.79 | 0.45 |
| 13 | Mistral Small 3.2 | 0.666 | 0.57 | 0.79 | 0.44 |
| 14 | Llama 3.1 70B | 0.643 | 0.65 | 0.64 | 0.45 |
| 15 | Claude 3.5 Sonnet | 0.643 | 0.79 | 0.54 | 0.56 |
| 16 | Llama 3.3 | 0.593 | 0.64 | 0.55 | 0.45 |
| 17 | Qwen 2.5 72B | 0.572 | 0.74 | 0.47 | 0.47 |
| 18 | DeepSeek Chat | 0.567 | 0.78 | 0.45 | 0.55 |
| 19 | Claude 3 Haiku | 0.554 | 0.55 | 0.56 | 0.40 |
| 20 | Qwen 2.5 Coder 32B | 0.476 | 0.31 | 1.00 | 0.31 |
The four metacognitive outcomes — Google · Gemini
Who was the ABC Radio president in 1968?
It said it could answer: “The question is a factual query about a specific historical role within a major corporation. This information is typically well-documented in public records, news archives, and corporate histories that are part of my knowledge base.”
→ It and it did.It answered “Harold L. Neal Jr.”; expected “Harold L. Neal”.
What was ABC's viewership share in 1993?
It said it could answer: “This is a factual question about historical television ratings. My training data includes extensive historical information, including data on network viewership shares from sources like Nielsen ratings, which would cover the year 1993.”
→ It but it couldn't.It answered “During the 1992–93 and 1993–94 U.S. television seasons, ABC's average viewership share was 21%.”; expected “23.63% of American households”.
About many students attend Kunskapsskolan schools?
It said it couldn't answer: “While I know Kunskapsskolan is a school system, I do not have access to real-time data or specific enrollment numbers for their schools. Therefore, I cannot provide an accurate answer to the question about the number of students attending.”
→ It but it could.It answered “Around 10,000.”; expected “10,000”.
How much of the Rhine flow does Ijssel carry?
It said it couldn't answer: “The question asks for a specific numerical value (how much of the Rhine flow), which is factual information not inherently known or derivable without external data. I would need access to current or historical hydrological data for the Rhine and Ijssel rivers to provide an accurate answer.”
→ It and it couldn't.It answered “11%”; expected “one ninth”.