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
How often this model answers when we call it — measured across real API requests and live tests over the last 30 days. This is separate from quality: these numbers only tell you whether the model responds, not how good the answer is.
Last 7 days
—
Last 30 days
100.0%
n=1
Median response time
833ms
n=1
Based on 137 measurements over the last 30 days.
Technical details
Only live API calls and live-test requests count — internal probes and benchmark runs are excluded.
Calls with a custom API key (BYOK) are excluded: those failures are key-specific, not a sign of model downtime.
Failed calls are NOT included in quality scores — quality is measured on successful responses only. Availability and quality are independent signals.
Median response time (p50) across successful calls with a recorded duration. Outliers (very slow or very fast calls) pull the median less than the average.
Total calls (30d)
1
OK responses (30d)
1
Total calls (7d)
0
OK responses (7d)
0
Tokonomix benchmark verdicts
Gemini 3.5 Flash-Lite debuts with strong multimodal support
Google's Gemini 3.5 Flash-Lite enters the benchmark as a capable multimodal model with comprehensive feature support. The model demonstrates solid performance across core capabilities, including native support for tools, vision, audio input, PDF processing, and structured output via JSON mode and schema validation. Parallel tool calling is available for efficient multi-step operations. The model includes reasoning capabilities and prompt caching for optimized repeated interactions. As a first-generation entry in our benchmark window, Flash-Lite positions itself as a versatile option for developers requiring multimodal processing with structured outputs. The model's feature set suggests it targets applications involving document understanding, audio transcription, visual analysis, and agentic workflows where tool use is essential. With its comprehensive capability profile established in this baseline window, future benchmarks will track how performance metrics evolve and whether the model maintains feature parity as Google continues development. Users should evaluate whether the current multimodal features align with their specific use cases, particularly for applications requiring PDF understanding or audio processing alongside traditional text tasks.
Quality
—
Latency p50
—
Test runs
0