Claude Fable 5.2 (Low, Default Fallback) vs DeepSeek V4 Pro 0813 (Non-reasoning)
Which is better for the money: Claude Fable 5.2 (Low, Default Fallback) by Anthropic or DeepSeek V4 Pro 0813 (Non-reasoning) by DeepSeek? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-11-10.
Depends on your budget
Claude Fable 5.2 (Low, Default Fallback) scores 41.3 points higher (53.9 vs 12.6) but costs 3.7× as much to run the benchmark ($2862 vs $771; flagship vs premium cost classes). They are not alternatives at one budget: pick Claude Fable 5.2 (Low, Default Fallback) when you need intelligence above 12.6, and DeepSeek V4 Pro 0813 (Non-reasoning) when 12.6 is enough.
| Metric | Claude Fable 5.2 (Low, Default Fallback) | DeepSeek V4 Pro 0813 (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 53.9 | 12.6 | −76.6% DeepSeek V4 Pro 0813 … is 76.6% less intelligent |
| Total AA cost (lower is better) | $2,861.78 | $771.03 | −73.1% DeepSeek V4 Pro 0813 … is 73.1% cheaper |
| End-to-end time (lower is better) | 22.57s | 8.28s | −63.3% DeepSeek V4 Pro 0813 … is 63.3% faster |
| Price per 1M tokens (in / out) | $8.00 / $40.0 | $1.32 / $3.96 | |
| Input modalities | Text, Image | Text |
DeepSeek V4 Pro 0813 (Non-reasoning) vs Claude Fable 5.2 (Low, Default Fallback): 76.6% less intelligence, 73.1% less cost to run the AA benchmark, and 63.3% faster end-to-end.
Against the frontier
- Claude Fable 5.2 (Low, Default Fallback) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 54.60 for $1124.
- DeepSeek V4 Pro 0813 (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 52.50 for $718.
Compare something else
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-fable-5-2-low/deepseek-v4-pro-non-reasoning · Markdown: /api/v1/compare/claude-fable-5-2-low/deepseek-v4-pro-non-reasoning?format=md · llms.txt · agent skill