Underdog alert: Xiaomi MiMo keeps competing with top models on cost-adjusted benchmarks
VictorSanh · x · 2026-11-05
Developer mattwinters reports running experiments testing models' base vs potential intelligence with an optimized harness, and finds Xiaomi's MiMo quietly competing across benchmarks as a "dark horse value king." The attached chart plots score vs average cost per scenario (log scale) for models like GPT-6 Luna, MiMo-V2.6-Flash, Claude Haiku 5.5, GLM 5.3 Flash, DeepSeek V4.1 Flash and Kimi K3, showing the cost-quality gap before/after Beaker optimization.
More from Models
- Unsloth Dynamic v3.1 GGUFs boost Qwen3.8-Flash-Next accuracy 10-15% over GSQ-RCO — danielhanchen · 2026-11-05
- Arena data: Gemini 4 Carbon scales cheapest on hard tasks, rivals cost 3-4x more — arena · 2026-11-05
- QwenPuter dissected: the CPU emulator lives inside Qwen weights but is fully compartmentalized — srchvrs · 2026-11-05
- Artificial Analysis details benchmark methodology: every 6 hours, sustained load, agentic sessions — ArtificialAnlys · 2026-11-05
- GLM-5.3's Fastest-Streaming Endpoints Take 18-26s to First Token, Slipping in New Benchmark — ArtificialAnlys · 2026-11-05
- Artificial Analysis Overhauls API Benchmarks: Time per Task Replaces Streaming Speed — ArtificialAnlys · 2026-11-05