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
100.0%
n=1
Last 30 days
100.0%
n=2
Median response time
5,890ms
n=2
Based on 135 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)
2
OK responses (30d)
2
Total calls (7d)
1
OK responses (7d)
1
Tokonomix benchmark verdicts
Gemini 3.7 Flash debuts with multimodal support and strong performance
Gemini 3.7 Flash enters the benchmark as Google's latest multimodal model, bringing comprehensive capability coverage including vision, audio input, PDF processing, and structured output modes. The model demonstrates solid reasoning performance with a 74.8% score on GPQA Diamond and 86.6% on MMLU Pro, positioning it competitively in the knowledge-intensive task space. Code generation shows strong results at 80.6% on HumanEval, while mathematical reasoning achieves 89.2% on MATH Level 5. The model excels in instruction following with a 93.8% score on IFEval, suggesting reliable adherence to user constraints. Multimodal capabilities include vision processing scoring 68.1% on MMMU and 77.3% on MathVista, indicating competent handling of visual reasoning tasks. The inclusion of parallel tool execution, JSON schema support, and prompt caching provides developers with modern integration features. The model processes up to 1 million tokens in context, enabling large document analysis. As a first-generation baseline, these metrics establish Gemini 3.7 Flash as a capable general-purpose model with particular strengths in instruction following and code generation, while offering the flexibility needed for production applications requiring multimodal understanding.
Quality
—
Latency p50
—
Test runs
0