Gemini 3.8 Flash and GPT-5.6 Terra achieved 100% of available points on the standing benchmark over the last seven days. Both models reached this score with $0 spent.
Prices
Google's pricing for the Gemini family varies across tiers. Gemini 3.1 Pro (preview) is the most expensive measured model at $2.00/M for input and $12.00/M for output. Gemini 2.5 Flash Lite is the lowest cost option at $0.100/M for input and $0.400/M for output.
| Model | Input Cost/M | Output Cost/M |
|---|---|---|
| Gemini 3.1 Pro (preview) | $2.00 | $12.00 |
| Gemini 2.5 Pro | $1.25 | $10.00 |
| Gemini 3.5 Flash | $1.50 | $9.00 |
| Gemini 2.5 Flash | $0.300 | $2.50 |
| Gemini 3.1 Flash Lite | $0.250 | $1.50 |
| Gemini 2.5 Flash Lite | $0.100 | $0.400 |
Speed
Responsiveness was non-existent across all measured models in the last 24 hours. GPT-5.4 Mini, GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna all recorded 0% of checks succeeded. Similarly, Gemini 3.1 Pro (preview), Gemini 3.1 Flash Lite, and Gemini 3.8 Flash recorded 0% of checks succeeded. No median response times were available due to the lack of successful requests.
Benchmark
Seven-day benchmark results show a divide in performance. Gemini 3.8 Flash and GPT-5.6 Terra lead with 100% of available points. Gemini 3.1 Flash Lite followed with 84.4%, and GPT-5.6 Luna recorded 66.7%. All four models listed reached these percentages with $0 spent.
These measurements prove the current cost of tokens and the historical benchmark performance of the models. They do not prove the cause of the 0% uptime recorded for the measured models over the last 24 hours.
