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.
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
2,985ms
n=1
Based on 121 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
Claude Fable 5.1 debuts with strong performance across key benchmarks
Claude Fable 5.1 establishes itself as a capable model with this initial benchmark window. The model demonstrates strong mathematical reasoning with an 88.0% score on MATH-500 and solid coding ability at 84.4% on HumanEval. General knowledge performance reaches 87.9% on MMLU, while graduate-level reasoning achieves 65.5% on GPQA Diamond. The model handles multimodal tasks effectively, scoring 66.7% on MMLU-Pro Vision and 81.4% on MathVista, indicating competent visual understanding. Instruction following proves reliable at 80.1% on IFEval. This baseline establishes Claude Fable 5.1 as a well-rounded model suitable for diverse applications including mathematical problem solving, code generation, and multimodal analysis. The comprehensive capability set including tools, vision, JSON modes, PDF input, reasoning features, and prompt caching provides flexibility for different use cases. Users can expect consistent performance across technical and knowledge-based tasks, with particular strength in mathematical domains. As this is the first benchmark window, future verdicts will track performance trends and stability over time.
Quality
—
Latency p50
—
Test runs
0