Hacker News · 核心生态
DeepSeek v4 pro 0813 released
Its benchmarks are comparable to Fable 5, with each having its strengths and weaknesses, resulting in a near tie. Terminal Bench 2.1: 72.1 → 87.9, surpassing Opus 4.8's 85.0, and only 0.1 away from Fable 5's 88.0. Cybergym: 52.7 → 83.3, surpassing Opus 4.8's 78.3, and slightly higher than Fable 5's 83.1. DeepSWE: 12.8 → 62.7, surpassing Opus 4.8's 58.0. Aut…
SOURCE-DECLARED INSTALL
Open the public source page ↗MEDIA REFERENCES
Captured in public view
CONTEXT
Why it is here
Its benchmarks are comparable to Fable 5, with each having its strengths and weaknesses, resulting in a near tie. Terminal Bench 2.1: 72.1 → 87.9, surpassing Opus 4.8's 85.0, and only 0.1 away from Fable 5's 88.0. Cybergym: 52.7 → 83.3, surpassing Opus 4.8's 78.3, and slightly higher than Fable 5's 83.1. DeepSWE: 12.8 → 62.7, surpassing Opus 4.8's 58.0. Aut…
Evidence updated 2026-08-16T10:41:36Z. Interaction numbers are platform-native snapshots; the evidence panel records the metric source and observation time. NULL means the public page did not expose a number at collection time.