Speed analysis
Latency measured across all benchmark runs. P50 (median) and P95 (95th percentile) give a realistic picture of response speed under normal and peak load.
Quality scores
How this model compares to the rest of the field on each prompt category, from a pairwise fit over the same prompts. The raw judge score sits underneath each number.
Win rate per category: how often this model beats a field-average model on a prompt from that category. 50% is average, not a failing grade. It is not a percentage of correct answers.
Pricing
What you pay per million tokens when you use this model on Tokonomix, plus an estimate for a typical conversation.
Tokens per second
Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.
Estimated from P50 latency × 200 output tokens — the absolute number depends on this assumption; the trend is what matters.
Capabilities
Availability
Availability
No measurements yet
We haven't recorded enough API calls to show availability stats for this model. Data appears once the model starts receiving live traffic.
Tokonomix benchmark verdicts
Gemini 3.6 Flash shows modest quality gain but remains in bottom quartile
Gemini 3.6 Flash has posted a 7-point quality improvement in the current benchmark window, rising from 17.7 to 24.7 out of 100. Despite this uptick, the model continues to perform in the bottom quartile of evaluated systems. The improvement appears concentrated in creative tasks, which now score 74 out of 100, representing the model's strongest category. However, both coding and reasoning capabilities remain critically weak at or near zero. The previous window showed a reasoning score of 50, but this has now dropped to zero, indicating significant instability in logical performance. Latency has improved from 4057ms to 3503ms at the median, making responses moderately faster. The limited test run sample of three executions in the current window suggests these results should be interpreted with caution. Users seeking creative text generation may find some utility here, but those requiring coding assistance or complex reasoning should look elsewhere. The model's extreme performance variance across categories and between benchmark windows raises questions about consistency and production readiness.
Quality
24.7
Latency p50
3,503 ms
Test runs
3
Gemini 3.6 Flash
by Google Gemini
- Released
- July 21, 2026
- Context window
- 1.048576M tokens
- Input price
- $1.13 / 1M
- Output price
- $5.61 / 1M
- Tier
- Tier B — Production
- Modality
- Text + vision
- API type
- REST · streaming
- Benchmark runs
- 240
More from Google Gemini