LLaDA 2.2-flash posts 592.8 on τ²-Bench and 705.3 in fast mode
omarsar0 · x · 2026-07-26
More benchmark numbers for LLaDA 2.2-flash show its agentic and long-context performance.
- τ²-Bench: 592.80 vs 334.90 on Ling-2.6-flash.
- In fast mode, the score rises to 705.30.
- The attached table also compares throughput across SWE-bench, BFCL-v4, AIME 2026, LiveCodeBench, IFBench, KOR-Bench, GPQA-Diamond, and LongBench-v2, with the FP8-quantized variant usually faster still.
More from Models
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11