Figures: LiveBench Mathematics 90.1 (was 91.3), overall 77.4 / +3.2, matching the 2026-06-25 leaderboard

Regenerated the category-profile and vs-base charts from the published LiveBench numbers; the README delta text follows.

README.md

@@ -26,7 +26,7 @@ tags:
 
 ## 1. Model Introduction
 
-Smaug-Flash is an agentic-coding finetune of [DeepSeek-V4-Flash-0731](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731), finetuned by Abacus.AI. It improves end-to-end agentic performance by a wide margin (+14.3 on LiveBench agentic-coding, +10.1 on Terminal Bench 2.1 under the DeepSeek harness, +13.7 on AutomationBench, +19 on NL2Repo-Bench) while improving general capability (+3.4 overall LiveBench). The weights load exactly like the official release: same layout, same quantization formats, same context length (1M), same reasoning interface.
+Smaug-Flash is an agentic-coding finetune of [DeepSeek-V4-Flash-0731](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731), finetuned by Abacus.AI. It improves end-to-end agentic performance by a wide margin (+14.3 on LiveBench agentic-coding, +10.1 on Terminal Bench 2.1 under the DeepSeek harness, +13.7 on AutomationBench, +19 on NL2Repo-Bench) while improving general capability (+3.2 overall LiveBench). The weights load exactly like the official release: same layout, same quantization formats, same context length (1M), same reasoning interface.
 
 This card describes the training approach and the evaluation results. Dataset contents are not disclosed; training data consists of curated agentic loop traces from various sources - public repositories, traces synthesized from real world agentic product use cases, augmented with synthetic data variations.