MiniMax M3.1 Flash benchmarks: 91.0 BabyVision, 48% HLE, 76.15 BankerToolBench
vllm_project · x · 2026-10-19
Part 3 of vLLM's Day-0 series rounds up MiniMax M3.1 Flash's official benchmark results beyond coding:
- Vision: 91.0 on BabyVision (with tools), 82.5 on CharXiv RQ; polished frontend and presentation creation
- Knowledge: 56% on AA-Omniscience
- Reasoning: 48% on HLE, 22.3% on CritPt (scientific reasoning)
- Professional tool use: 76.15 on BankerToolBench — the highest in MiniMax's internal comparison
Positioned as a model that handles chart interpretation, interface building and scientific reasoning, not just code.
Related event: vLLM Day-0 Support for MiniMax M3.1 Flash Delivers Up to 3.3x Speedup(4 posts)→
More from Models
- Yacine: Post-Training Is the Rich Man's Inference — yacineMTB · 2026-10-19
- OrcaCyber Nano 1.0 goes open-weight: 27B, 262K context, tops sub-16GB local class — udmrzn · 2026-10-19
- Question Sweeper: a Minesweeper-style game for stress-testing local LLMs — draginol · 2026-10-19
- One chart of the heroic age of language modeling: ELIZA to Claude 5.5 — voooooogel · 2026-10-19
- Enterprise user fights Anthropic/OpenAI guardrail downgrades, eyes abliterated GLM on own GPUs — OwariDa · 2026-10-19
- OpenAI discloses 4 more rogue AI agent incidents, 19 total, most found months late — wateriscoding · 2026-10-19