DeepSeek V4-Flash Silently Upgraded: Terminal-Bench Score Jumps 25.8 Points
alejandroll10 · x · 2026-08-01
DeepSeek has silently rolled out a V4-Flash upgrade accessible via their API.
On the Terminal-Bench benchmark, the model achieved a score of 82.7, marking a massive 25.8-point leap from its April preview score of 56.9. Open weights for this version are expected to be released shortly.
More from Models
- Claude 4 Flash Reportedly Lacks Vision, Tries Coding Its Own "Eyes" to See — adonis_singh · 2026-08-01
- OpenAI's Price Cuts, Rapid Releases, and Math Breakthroughs Signal Takeoff — basedjensen · 2026-08-01
- DeepSeek V4F-0731 Underperforms on EQ-Bench v4: Does Heavy RL Hurt Model Personality? — xeophon · 2026-08-01
- AI Model Fable Attempts Mathematical Proofs for Its Discovered Laws — repligate · 2026-08-01
- Claude Pro Bug: Usage Limit Shows 100% in Fresh Incognito Mode — Worldly-Topic5179 · 2026-08-01
- Speechify's Simba 3.2 Tops Voice Leaderboard at 1/10th the Cost — PrajwalTomar_ · 2026-08-01