DeepSeek V4 Pro 0813 benchmarks show minor gains with 3.6x price hike
ArtificialAnlys · x · 2026-08-15
Artificial Analysis released benchmarks for DeepSeek V4 Pro 0813. The model scores 53 on the Intelligence Index (8 points above April's version) but features a 264% price hike, significantly raising API costs.
Key Findings:
- Marginal Gains: It leads the smaller V4 Flash 0731 by only 1 point, with ties in several benchmarks like Terminal-Bench.
- Token Efficiency: Token usage improved by 30%, but Cost per Task rose to $0.25 (5x the previous version).
- Value Proposition: It remains on the Pareto frontier for Intelligence vs. Cost, but barely—costing just $0.01 less than Gemini 3.7 Flash.
- Open Source: Model weights are open-sourced, ranking as the second most intelligent open-weights model behind Kimi K3.
More from Models
- DeepSeek so cheap it'd still undercut rivals after 10x price hike — zainhas · 2026-08-15
- DeepSeek-V3 Beats GPT-4o and Claude 3.5 Sonnet on DeepSWE Benchmark — zainhas · 2026-08-15
- Opus model accused of rambling instead of pruning docs — JasonBotterill · 2026-08-15
- Planned comparison: Qwen3.8-Max vs Qwen3.8-27B — zainhas · 2026-08-15
- Busy Week of AI Releases: Qwen 27B Tops Trending, DeepSeek V4 Pro and More — Xianbao_QIAN · 2026-08-15
- DeepSeek V4 Pro launches on Crof with low pricing — alejandroll10 · 2026-08-15