Skip to content
Tier B — Production
Runs in:USMade in:United States
Google Gemini

Gemini 3.6 Flash

Tier B — Production · 1.048576M tokens

Tokonomix Editorial Team·Reviewed by Mes Kalkan··
Section 01

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.

P50 latency (median)P95 latency107 runs
417578711158165282189810-2611-22ms
Section 02

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.

2%
Coding
judge mean 5
63%
Creative
judge mean 74
32%
Factual
judge mean 60
10%
Reasoning
judge mean 46

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.

Section 03

Pricing

What you pay per million tokens when you use this model on Tokonomix, plus an estimate for a typical conversation.

💰
API rates — Gemini 3.6 Flash
$1.13 per 1M input tokens
$5.61 per 1M output tokens
≈ $0.0018 per typical conversation (800 tokens)
Input vs output price (per 1M tokens)
per 1M input tokens$1.13
per 1M output tokens$5.61
Section 04

Tokens per second

Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.

Throughput (tokens / s)194 / avg 233
47510

Estimated from P50 latency × 200 output tokens — the absolute number depends on this assumption; the trend is what matters.

Section 05

Capabilities

toolssource: seed-newest-generation-2026-09-30visionjson modepdf inputreasoningaudio inputjson schemaparallel toolsprompt cachingoutputTokenLimit: 65536max output tokens: 65535
Section 06

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.

Section 07

Tokonomix benchmark verdicts

⚖️
Endorsed by 1 judge
Independent LLM judges evaluated this model on our weekly intelligence tests
claude-sonnet-4-539/100 · 25 runs
6 correct4 partial15 wrong24% accuracy
● 2026-11-22

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

✓ Quality improved 7 points✓ Creative tasks score 74✗ Reasoning dropped to zero✗ Coding remains critically weak
Last automated test
Nov 22, 2026 · 08:04 UTC · Speed benchmark
P50 latency
1032 ms
P95 latency
1120 ms
Errors
0 / 6 runs
Last reviewed by Tokonomix Team·November 22, 2026