head-to-head
| Metric | Claude Fable 5 | DeepSeek V4 Pro |
|---|---|---|
| SWE-bench Verified | 95.0% | 80.6% |
| SWE-bench Pro | 80.3% | 55.4% |
| Terminal-Bench | — | 67.9% (TB2.0) |
| Input $ / 1M | $10 | $0.435 |
| Context | 1M | 1M |
| Open weights | No | Yes |
| Maker | Anthropic | DeepSeek |
when to pick each
Pick Claude Fable 5 if
Mythos-class flagship for long-horizon agentic runs: the model to reach for when a task spans hours and hundreds of tool calls and has to actually finish.
Pick DeepSeek V4 Pro if
The cheapest frontier-class coder — top open-weights score at ~11× less than Opus. Best pick when cost or self-hosting rules.
Full reviewsClaude Fable 5, decoded
Ranked on our AI Coding Leaderboard, updated 2026-07-03. Scores are confirmed against primary sources; prices are per 1M input tokens and can change.
Primary sources
- AnthropicGENZ TECH — Claude Fable 5 returns — SWE-bench Verified 95.0% (vals.ai independent eval) is the highest confirmed score of any model. SWE-bench Pro 80.3% uses Anthropic's own scaffolding and is contested. Restored Jul 1, 2026 after a 20-day export-control suspension. Pricing $10/$50 per 1M.
- DeepSeekDeepSeek V4 — specs & benchmarks — Independent tracker (llm-stats, June 2026); tied with Gemini 3.1 Pro on Verified, ahead on Pro.
- BenchmarkSWE-bench — the real-GitHub-issue benchmark