DeepSeek V4 Flash Benchmarks Leak: Beats Pro with 1/5 Parameters
togethercompute · x · 2026-08-06
Benchmark scores for DeepSeek's upcoming V4 Flash model have surfaced. The model reportedly achieved a high score of 82.7 on the Terminal-Bench 2.1 benchmark.
Notably, V4 Flash managed to outperform the V4 Pro Preview (which scored 72.1), despite using roughly one-fifth of the total parameters.
Related event: DeepSeek V4 Flash Benchmarks Leak, Outperforming Pro(3 posts)→
More from Models
- User rants GPT-6.1 Sol is painfully slow and buggy, says Claude is 7x faster — karmay007 · 2026-10-16
- $20-plan users have no idea how far AI agents have come in 10 months — realmeetjames · 2026-10-16
- Tencent Hunyuan open-sources Hy Memory 2.0: model, SDK and MemHub for agent memory — TencentHunyuan · 2026-10-16
- Four Gemini 4 Argon agents beat Minecraft's Ender Dragon in 27 hours — _rockt · 2026-10-16
- Leaked OpenAI roadmap hints GPT-6.1 Astra and GPT-6.5 Bell landing by end of 2026 — VraserX · 2026-10-16
- Open-weight models now beat Claude Sonnet 5 as gap closes fast — LegacyRemaster · 2026-10-16