{"slug": "mimo-pro", "name": "MiMo Pro", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 23, "commenters": 38, "warners": 3, "score": 20.573, "rising": 7.75, "first": "2026-04-01", "latest": "2026-10-19", "why": "I switched to coding plans containing GLM 5.1, Kimi K2.6 and Xiaomi MiMo V2.5 Pro and I never been happier.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 27, "neutral": 9, "compare": 5, "warn": 4}, "spark": [0, 0, 0, 0, 0, 2, 4, 8, 1, 2, 5, 5], "listed": true, "loved": [], "caveat": "", "short_quote": "I switched to coding plans containing GLM 5.1, Kimi K2.6 and Xiaomi MiMo V2.5 Pro and I never been happier.", "kind": "", "icon": false, "domain": "mi.com", "github_repo": null, "official_url": "", "pricing": "", "aliases": ["MiMo v2.5 Pro", "MiMo 2.5", "MiMo V2.5 Pro", "MiMo-V2.5-Pro", "MiMo 2.5 Pro", "MiMo v2.5", "MiMo 2.6 Pro", "MiMo v2.6 Pro", "MiMo V2.6 Pro", "MiMo-V2.6-Pro", "Xiaomi MiMo V2.5 Pro", "MiMo-V2.5", "MiMo V2 Pro", "MiMo V2.5", "MiMo-v2.5-Pro", "Mimo V2.5 Pro", "MiMo-V2.6 Pro", "MiMo-v2.6-Pro", "Xiaomi MiMo-v2.5-Pro", "Mimo-V.26-Pro", "MiMo-2.5", "MiMo-2.5-pro", "MiMo-2.5-Pro", "Mimo 2.6 Pro"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 802507488, "item_id": 50156718, "url": "https://news.ycombinator.com/item?id=50156718", "by": "60secs", "date": "2026-10-19", "stance": "recommend", "quote": "Is there a single use case where you would not be better served using MiMo 2.6 Pro?", "excerpt": "Is there a single use case where you would not be better served using MiMo 2.6 Pro? https://artificialanalysis.ai/models/comparisons/mimo-v2-6-pro-vs-minimax-m3", "context": "", "use_case": "", "switched_from": "", "story": "MiniMax M3.1 Flash"}, {"id": 802501106, "item_id": 50156319, "url": "https://news.ycombinator.com/item?id=50156319", "by": "segmondy", "date": "2026-10-19", "stance": "recommend", "quote": "MiMo2.6-Pro is a beast", "excerpt": "Too early to call, I ran it through the weekend and compared with Qwen3.8-Flash-Next, DSv41F-1017 at FP8 and Q3.8FN at Q8. Both were great, but surprisingly, Q3.8FN had the better result. I was modelling and generating simulation code for a complex system. I used both because I had a bunch of images that needed to be used for input to steer the output. I think these models have strengths and it's best to experiment a", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek V4.1 Flash 1017 (Max)"}, {"id": 802233121, "item_id": 50139570, "url": "https://news.ycombinator.com/item?id=50139570", "by": "dom96", "date": "2026-10-18", "stance": "recommend", "quote": "MiMo V2.6 Pro is the best performing open-weight model", "excerpt": "I recently built KillSwitch[1], a brand new esoteric programming language which includes features designed to confuse/mislead/break LLMs, including: * certain constructs designed to trigger safety guardrails in models * counting of letters in identifiers as a language feature, hopefully triggering model's inability to accurately do so * the language spec containing hidden meaning and lies (designed to be invisible fo", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Benchmarking LLM ability to code in an adversarial language"}, {"id": 800283376, "item_id": 50017711, "url": "https://news.ycombinator.com/item?id=50017711", "by": "ralusek", "date": "2026-10-09", "stance": "recommend", "quote": "Isn't Mimo 2.6 pro smarter and cheaper?", "excerpt": "https://artificialanalysis.ai/#intelligence-comparison-tabs Isn't Mimo 2.6 pro smarter and cheaper? Haiku 5.5 is smarter and cheaper. Luna is basically as smart and much cheaper.", "context": "", "use_case": "", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800236400, "item_id": 50014775, "url": "https://news.ycombinator.com/item?id=50014775", "by": "codeprimate", "date": "2026-10-09", "stance": "recommend", "quote": "Mimo 2.6 Pro is even better.", "excerpt": "Mimo 2.6 Pro is even better. I switched from DeepSeek 4.1 flash about 2 weeks ago for my Hermes sysadmin/coding agents and I am seeing better intelligence and lower overall spend. https://artificialanalysis.ai/models/mimo-v2-6-pro", "context": "", "use_case": "sysadmin and coding agents", "switched_from": "DeepSeek 4.1 Flash", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 801004817, "item_id": 50062801, "url": "https://news.ycombinator.com/item?id=50062801", "by": "dom96", "date": "2026-10-12", "stance": "warn", "quote": "it's not better than MiMo V2.6 Pro which is pretty disappointing.", "excerpt": "I wish I could benchmark Muse Wonder Full, because Muse Wonder isn't much better than Muse Spark 1.3[1]. I created a brand new programming language designed to confuse LLMs[2] and created a model benchmark out of it. A lot of the tasks were failed because they exceeded the $5 budget though, so maybe it would have gone on to complete them, it just required a lot of funds to do so. Still, that's the benchmark, and it's", "context": "", "use_case": "", "switched_from": "", "story": "Muse Wonder"}, {"id": 796774912, "item_id": 49798432, "url": "https://news.ycombinator.com/item?id=49798432", "by": "NortySpock", "date": "2026-09-22", "stance": "warn", "quote": "Is a barely-trained model going to score 48 on DeepSWE v1.1 ?", "excerpt": "I sorta got the impression that the $3.47 million only covered post-training , given that few of the graphs start at zero. Is a barely-trained model going to score 48 on DeepSWE v1.1 ? https://mimo.xiaomi.com/rl/", "context": "", "use_case": "", "switched_from": "", "story": "MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis"}, {"id": 796763664, "item_id": 49797729, "url": "https://news.ycombinator.com/item?id=49797729", "by": "egeres", "date": "2026-09-22", "stance": "warn", "quote": "It feels suspicious that MiMo-V2.6", "excerpt": "It feels suspicious that MiMo-V2.6 Pro gets 46 in de index while DeepSeek-V4.1 (https://artificialanalysis.ai/models/deepseek-v4-1-flash) gets 39. According to the appendix at the bottom of https://mimo.xiaomi.com/mimo-v2-6 the deepseek model sometimes surpasses mimo and it's not so far behind in capabilities. A week ago opus 5 appeared 1 points ahead of fable 5 despite fable being a much smarter model (this has been", "context": "", "use_case": "", "switched_from": "", "story": "MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis"}, {"id": 785791600, "item_id": 49111975, "url": "https://news.ycombinator.com/item?id=49111975", "by": "CapyToolkit", "date": "2026-07-30", "stance": "warn", "quote": "All behave dumb, don't follow instructions properly even when they write skills for themselves.", "excerpt": "Honestly, I have a similar impressions after testing every model except Sonnet, Opus or Claude. I always test them inside Claude vscode extension in the terminal, using the same skills or workflows from multiple skills. I tested Mimo V2.5 Pro, Qwen 3.8 Max Preview, GLM 5.2, Macaron V1 Venti and many other, smaller model whenever hype on X appears. All behave dumb, don't follow instructions properly even when they wri", "context": "tests many models", "use_case": "simple tasks", "switched_from": "", "story": "Kimi-code not performing well"}]}], "who": [{"by": "bel8", "context": "works on ~1M line codebases", "url": "https://news.ycombinator.com/item?id=48719739", "date": "2026-06-29"}, {"by": "mdasen", "context": "heavy cached-input API user", "url": "https://news.ycombinator.com/item?id=48507479", "date": "2026-06-12"}, {"by": "DeathArrow", "context": "personal use", "url": "https://news.ycombinator.com/item?id=48073025", "date": "2026-05-09"}], "tags": [], "use_cases": ["coding", "coding with vision", "security exploit tasks", "sysadmin and coding agents", "cheap ai model", "home use"], "compared": [{"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 19, "switched_from": 1, "switched_to": 0}, {"slug": "deepseek-v4-pro", "name": "DeepSeek V4 Pro", "co": 19, "switched_from": 0, "switched_to": 0}, {"slug": "glm", "name": "GLM", "co": 19, "switched_from": 0, "switched_to": 0}, {"slug": "kimi", "name": "Kimi", "co": 18, "switched_from": 0, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 11, "switched_from": 1, "switched_to": 0}, {"slug": "qwen", "name": "Qwen", "co": 12, "switched_from": 0, "switched_to": 0}, {"slug": "deepseek", "name": "DeepSeek", "co": 8, "switched_from": 0, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 7, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48446639", "title": "MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=50000488", "title": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49977979", "title": "Mistral Large 4", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49796660", "title": "MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=48709670", "title": "Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=48814170", "title": "Inference Optimization for MiMo v2.5: Pushing Hybrid SWA Efficiency to the Limit", "mentions": 2}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"neutral": 2, "recommend": 2}, "2026-05": {"recommend": 4, "neutral": 1}, "2026-06": {"recommend": 8, "warn": 1, "compare": 2, "neutral": 2}, "2026-07": {"neutral": 2, "compare": 2, "recommend": 1, "warn": 1}, "2026-08": {"recommend": 2}, "2026-09": {"recommend": 5, "warn": 2}, "2026-10": {"neutral": 2, "recommend": 5, "compare": 1}}, "quotes": [{"id": 802507488, "item_id": 50156718, "url": "https://news.ycombinator.com/item?id=50156718", "by": "60secs", "date": "2026-10-19", "stance": "recommend", "quote": "Is there a single use case where you would not be better served using MiMo 2.6 Pro?", "excerpt": "Is there a single use case where you would not be better served using MiMo 2.6 Pro? https://artificialanalysis.ai/models/comparisons/mimo-v2-6-pro-vs-minimax-m3", "context": "", "use_case": "", "switched_from": "", "story": "MiniMax M3.1 Flash"}, {"id": 802501106, "item_id": 50156319, "url": "https://news.ycombinator.com/item?id=50156319", "by": "segmondy", "date": "2026-10-19", "stance": "recommend", "quote": "MiMo2.6-Pro is a beast", "excerpt": "Too early to call, I ran it through the weekend and compared with Qwen3.8-Flash-Next, DSv41F-1017 at FP8 and Q3.8FN at Q8. Both were great, but surprisingly, Q3.8FN had the better result. I was modelling and generating simulation code for a complex system. I used both because I had a bunch of images that needed to be used for input to steer the output. I think these models have strengths and it's best to experiment a", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek V4.1 Flash 1017 (Max)"}, {"id": 802233121, "item_id": 50139570, "url": "https://news.ycombinator.com/item?id=50139570", "by": "dom96", "date": "2026-10-18", "stance": "recommend", "quote": "MiMo V2.6 Pro is the best performing open-weight model", "excerpt": "I recently built KillSwitch[1], a brand new esoteric programming language which includes features designed to confuse/mislead/break LLMs, including: * certain constructs designed to trigger safety guardrails in models * counting of letters in identifiers as a language feature, hopefully triggering model's inability to accurately do so * the language spec containing hidden meaning and lies (designed to be invisible fo", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Benchmarking LLM ability to code in an adversarial language"}, {"id": 801004817, "item_id": 50062801, "url": "https://news.ycombinator.com/item?id=50062801", "by": "dom96", "date": "2026-10-12", "stance": "warn", "quote": "it's not better than MiMo V2.6 Pro which is pretty disappointing.", "excerpt": "I wish I could benchmark Muse Wonder Full, because Muse Wonder isn't much better than Muse Spark 1.3[1]. I created a brand new programming language designed to confuse LLMs[2] and created a model benchmark out of it. A lot of the tasks were failed because they exceeded the $5 budget though, so maybe it would have gone on to complete them, it just required a lot of funds to do so. Still, that's the benchmark, and it's", "context": "", "use_case": "", "switched_from": "", "story": "Muse Wonder"}, {"id": 800283376, "item_id": 50017711, "url": "https://news.ycombinator.com/item?id=50017711", "by": "ralusek", "date": "2026-10-09", "stance": "recommend", "quote": "Isn't Mimo 2.6 pro smarter and cheaper?", "excerpt": "https://artificialanalysis.ai/#intelligence-comparison-tabs Isn't Mimo 2.6 pro smarter and cheaper? Haiku 5.5 is smarter and cheaper. Luna is basically as smart and much cheaper.", "context": "", "use_case": "", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800236400, "item_id": 50014775, "url": "https://news.ycombinator.com/item?id=50014775", "by": "codeprimate", "date": "2026-10-09", "stance": "recommend", "quote": "Mimo 2.6 Pro is even better.", "excerpt": "Mimo 2.6 Pro is even better. I switched from DeepSeek 4.1 flash about 2 weeks ago for my Hermes sysadmin/coding agents and I am seeing better intelligence and lower overall spend. https://artificialanalysis.ai/models/mimo-v2-6-pro", "context": "", "use_case": "sysadmin and coding agents", "switched_from": "DeepSeek 4.1 Flash", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800183616, "item_id": 50011476, "url": "https://news.ycombinator.com/item?id=50011476", "by": "aguilaair", "date": "2026-10-08", "stance": "recommend", "quote": "but is above the pareto line, and cheaper", "excerpt": "What about MiMo v2.6 Pro? It\u2019s throughput is slower by default (UltraSpeed is faster than DS4.1F) but is above the pareto line, and cheaper. see https://artificialanalysis.ai/models/releases/comparisons?compare=claude-opus-5-5,deepseek-v4-1-flash,mimo-v2-6-pro", "context": "", "use_case": "Cheap AI model", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 799708145, "item_id": 49981759, "url": "https://news.ycombinator.com/item?id=49981759", "by": "smartbit", "date": "2026-10-06", "stance": "compare", "quote": "Mimo-V.26-Pro", "excerpt": "Too late to edit, now including AA-omni Score [0] and 'by Domain' Software Engineering [1]. Also added comparison to the eyeballs-median of the 'top 10' models and then you see that indeed Mistral Large 4 Preview scores miserable in the AA-Omni indices. Inte Cost AA- Omni llig per Omni Softw Open Weight model ence Speed Task score Eng Mimo-V.26-Pro 46 47 $0.13 8 33 GLM-5.3 (max) 45 73 $2.01 14 37 DeepSeek 4.1 Flash M", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Large 4"}, {"id": 799665713, "item_id": 49979107, "url": "https://news.ycombinator.com/item?id=49979107", "by": "segmondy", "date": "2026-10-06", "stance": "neutral", "quote": "I use MiMov2.6Pro, DeepSeekv4.1Flash, GLM5.3, Hy4, Qwen3.8 and KimiK3 at home.", "excerpt": "I use Opus 5.5 at work. I use MiMov2.6Pro, DeepSeekv4.1Flash, GLM5.3, Hy4, Qwen3.8 and KimiK3 at home. Opus5.5 is not a game changer.", "context": "", "use_case": "home use", "switched_from": "", "story": "Mistral Large 4"}, {"id": 799655217, "item_id": 49978451, "url": "https://news.ycombinator.com/item?id=49978451", "by": "dom96", "date": "2026-10-06", "stance": "recommend", "quote": "MiMo v2.6 Pro which is currently the best open-weight model as far as I'm concerned", "excerpt": "Excited to test this on my benchmark[1], but I'm guessing it won't fare better than MiMo v2.6 Pro which is currently the best open-weight model as far as I'm concerned. Why isn't this on openrouter yet? Is there a better router that gets models much quicker? 1 - https://bench.killswitch-lang.org/", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Large 4"}, {"id": 798858160, "item_id": 49928635, "url": "https://news.ycombinator.com/item?id=49928635", "by": "dac23116", "date": "2026-10-02", "stance": "neutral", "quote": "These all very cheap. =_=", "excerpt": "https://llmrank.cn/ MiMo-V2.6-Pro US$100/month Qwen3.8 Max (0902) GLM-5.3 (max) Kimi K3 (max) These all very cheap. =_=", "context": "", "use_case": "", "switched_from": "", "story": "ChatGPT Pro 500"}, {"id": 796911058, "item_id": 49806941, "url": "https://news.ycombinator.com/item?id=49806941", "by": "dom96", "date": "2026-09-22", "stance": "recommend", "quote": "MiMo V2.6 Pro performs better and is cheaper than GPT 6 Sol on my benchmark", "excerpt": "It's surprising but MiMo V2.6 Pro performs better and is cheaper than GPT 6 Sol on my benchmark[1]. Open weight models are really snapping at the heels of the major western models. 1 - https://bench.killswitch-lang.org", "context": "", "use_case": "", "switched_from": "", "story": "GPT-6 Sol and Luna"}, {"id": 796774912, "item_id": 49798432, "url": "https://news.ycombinator.com/item?id=49798432", "by": "NortySpock", "date": "2026-09-22", "stance": "warn", "quote": "Is a barely-trained model going to score 48 on DeepSWE v1.1 ?", "excerpt": "I sorta got the impression that the $3.47 million only covered post-training , given that few of the graphs start at zero. Is a barely-trained model going to score 48 on DeepSWE v1.1 ? https://mimo.xiaomi.com/rl/", "context": "", "use_case": "", "switched_from": "", "story": "MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis"}, {"id": 796763776, "item_id": 49797736, "url": "https://news.ycombinator.com/item?id=49797736", "by": "dom96", "date": "2026-09-22", "stance": "recommend", "quote": "It is an impressive model.", "excerpt": "It is an impressive model. Agreed on most that is written on this page, with the exception of it being fast. I ran it on my own LLM benchmark suite[1] and it is faster than DeepSeek but still much slower than leading models. But it's pricing is where it really shines. KillSwitch-Bench 1.0 Claude Opus 5 66.9 GPT-6 Astra 57.9 Claude Fable 5.1 46.7 MiMo-V2.6-Pro 38.8 Muse Spark 1.3 36.5 1 - https://bench.killswitch-lang", "context": "", "use_case": "", "switched_from": "", "story": "MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis"}, {"id": 796763664, "item_id": 49797729, "url": "https://news.ycombinator.com/item?id=49797729", "by": "egeres", "date": "2026-09-22", "stance": "warn", "quote": "It feels suspicious that MiMo-V2.6", "excerpt": "It feels suspicious that MiMo-V2.6 Pro gets 46 in de index while DeepSeek-V4.1 (https://artificialanalysis.ai/models/deepseek-v4-1-flash) gets 39. According to the appendix at the bottom of https://mimo.xiaomi.com/mimo-v2-6 the deepseek model sometimes surpasses mimo and it's not so far behind in capabilities. A week ago opus 5 appeared 1 points ahead of fable 5 despite fable being a much smarter model (this has been", "context": "", "use_case": "", "switched_from": "", "story": "MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis"}, {"id": 796712560, "item_id": 49794535, "url": "https://news.ycombinator.com/item?id=49794535", "by": "dom96", "date": "2026-09-21", "stance": "recommend", "quote": "", "excerpt": "Very capable model. I just ran it on my own LLM benchmark suite[1] and it matches Muse Spark 1.3 in pass rate but is significantly cheaper. KillSwitch-Bench 1.0 Claude Opus 5 66.9 GPT-6 Astra 57.9 Claude Fable 5.1 46.7 MiMo-V2.6-Pro 38.8 Muse Spark 1.3 36.5 1 - https://bench.killswitch-lang.org/", "context": "", "use_case": "", "switched_from": "", "story": "MiMo v2.6"}, {"id": 796700404, "item_id": 49793775, "url": "https://news.ycombinator.com/item?id=49793775", "by": "bel8", "date": "2026-09-21", "stance": "recommend", "quote": "which are happy to follow your orders without accusing you of being a terrorist", "excerpt": "> Claude crapped out on \u201ccyber safety\u201d grounds. A $10/mo subscription to OpenCode Go would have done the job for you. They have models like Kimi K3, Grok 4.6 , GLM-5.3, Mimo 2.6 Pro (launched today, already available) which are happy to follow your orders without accusing you of being a terrorist. https://models.dev/providers/opencode/", "context": "", "use_case": "", "switched_from": "", "story": "M5 Ultra Mac Studio Review"}, {"id": 795746480, "item_id": 49734155, "url": "https://news.ycombinator.com/item?id=49734155", "by": "ricardobeat", "date": "2026-09-16", "stance": "recommend", "quote": "For reference, Mimo-v2.5-Pro scored 19% on DeepSWE 1.1. This is looking great.", "excerpt": "For reference, Mimo-v2.5-Pro scored 19% on DeepSWE 1.1. This is looking great. Fable scores 70%, Kimi K3 69%, Astra 74% (all on max effort). https://deepswe.datacurve.ai/blog/deepswe-v1-1", "context": "", "use_case": "", "switched_from": "", "story": "Xiaomi Mimo 2.6 live post-training dashboard"}, {"id": 794771488, "item_id": 49673218, "url": "https://news.ycombinator.com/item?id=49673218", "by": "bellowsgulch", "date": "2026-09-12", "stance": "recommend", "quote": "mimo-v2.5-free, mimo-v2.5, deepseek-flash in that order", "excerpt": "mimo-v2.5-free, mimo-v2.5, deepseek-flash in that order, honestly don\u2019t even bother using qwen3.6-35b-a3b now unless i need uncensored tasks finished, mostly reverse engineering most engineering tasks don\u2019t require frontier llms when they get stuck, then i consider moving up to more capable models purchasing a claude plan seems widely unnecessary to me the tasks they do better than the average engineer cut both ways:", "context": "", "use_case": "engineering tasks", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 792664929, "item_id": 49541558, "url": "https://news.ycombinator.com/item?id=49541558", "by": "wyrdcurt", "date": "2026-09-02", "stance": "recommend", "quote": "at least the FPS counter is real!", "excerpt": "Pretty typical \"cool HTML toy\" LLM output, tbh. The only thing impressive about this is how fast it generated it (13 seconds is wild!), but that's more of testament to Google's infrastructural advantage than to the quality of the model. For comparison's sake, I tried something similar with a couple other cheap models I've used lately, with the prompt \"Impress me. Make something cool in HTML. Ensure that it is mobile ", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 3.8 Flash and 3.8 Flash Cyber"}, {"id": 790318691, "item_id": 49394918, "url": "https://news.ycombinator.com/item?id=49394918", "by": "surgical_fire", "date": "2026-08-21", "stance": "recommend", "quote": "mostly GLM-5.3, DS-V4-Flash, and MiMo-2.5-pro", "excerpt": "Which is why I actually used all those models. At work I am stuck with Claude because it is what the employer provides. In my home setup I use a combination of different models; mostly GLM-5.3, DS-V4-Flash, and MiMo-2.5-pro. I vastly prefer my home setup.", "context": "", "use_case": "home setup", "switched_from": "", "story": "Bringing the cybersecurity capabilities of Claude Mythos 5 to more defenders"}, {"id": 787165168, "item_id": 49197823, "url": "https://news.ycombinator.com/item?id=49197823", "by": "shortformblog", "date": "2026-08-06", "stance": "recommend", "quote": "I have found Xiaomi\u2019s MiMo-V2.5-Pro to be a pretty cost-effective alternative.", "excerpt": "FWIW, I have found Xiaomi\u2019s MiMo-V2.5-Pro to be a pretty cost-effective alternative. https://mimo.mi.com/models/en-US/mimo-v2.5-pro While it won\u2019t cover everything DeepSeek does, it handles sophisticated tasks quite well. I found it after spotting it on a chart of different models and it was listed as being near Deepseek v4 Flash\u2019s price/performance levels. I have noticed by the way that DeepSeek\u2019s API has been prett", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek planning to significantly raise prices"}, {"id": 785923393, "item_id": 49120212, "url": "https://news.ycombinator.com/item?id=49120212", "by": "miyuru", "date": "2026-07-31", "stance": "compare", "quote": "it looks like Dv4F us more popular than mimov2.5", "excerpt": "Judging by the openrouter leaderboard ranking for today, it looks like Dv4F us more popular than mimov2.5. https://openrouter.ai/rankings?view=day#leaderboard-table These days cost per task is more important, and SOTA models have become expensive.", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek-V4-Flash Update"}, {"id": 785791600, "item_id": 49111975, "url": "https://news.ycombinator.com/item?id=49111975", "by": "CapyToolkit", "date": "2026-07-30", "stance": "warn", "quote": "All behave dumb, don't follow instructions properly even when they write skills for themselves.", "excerpt": "Honestly, I have a similar impressions after testing every model except Sonnet, Opus or Claude. I always test them inside Claude vscode extension in the terminal, using the same skills or workflows from multiple skills. I tested Mimo V2.5 Pro, Qwen 3.8 Max Preview, GLM 5.2, Macaron V1 Venti and many other, smaller model whenever hype on X appears. All behave dumb, don't follow instructions properly even when they wri", "context": "tests many models", "use_case": "simple tasks", "switched_from": "", "story": "Kimi-code not performing well"}, {"id": 785312918, "item_id": 49082057, "url": "https://news.ycombinator.com/item?id=49082057", "by": "Frannky", "date": "2026-07-28", "stance": "recommend", "quote": "MiMo 2.5 Pro for reasoning", "excerpt": "I think they're doing something wrong. I have access to better models, but I just use 4.6 and 4.8. Fable and Opus 5 burn tokens too fast for me. I also switched to a cheaper plan to work less and to experiment with OpenCode and open models when I hit the 5h limits. I'm doing this partly because I feel they've already started the enshittification of the old models, and I want to be able to just stop paying for the sub", "context": "", "use_case": "reasoning", "switched_from": "", "story": "\"Opus 5 is a really bad model\""}, {"id": 785288337, "item_id": 49080521, "url": "https://news.ycombinator.com/item?id=49080521", "by": "ignoramous", "date": "2026-07-28", "stance": "recommend", "quote": "I've found this to be true for 1M context-size open weights that I use (GLM 5.2, MiMo v2.5 Pro, & DeepSeek v4 Pro)", "excerpt": "> have terra write code and it will find lots of bugs in its own code. But let it iterate code reviews/fixes/test cases a few times, and you\u2019ll have something nice I've found this to be true for 1M context-size open weights that I use (GLM 5.2, MiMo v2.5 Pro, & DeepSeek v4 Pro). I think the prompt \"code review\", \"edge case\" etc triggers different parts of the LLM, bringing more files into its large context window. Th", "context": "", "use_case": "iterative code review and fixes", "switched_from": "", "story": "A $500 RL fine-tune of a 9B open model beat frontier models on catalog review"}, {"id": 783407777, "item_id": 48962986, "url": "https://news.ycombinator.com/item?id=48962986", "by": "ignoramous", "date": "2026-07-18", "stance": "recommend", "quote": "Prefer the latter over DeepSeek v4 Pro because it costs the same while being equally good & less chattier for coding workloads.", "excerpt": "> It's cheap enough to where I don't think about cost, made even cheaper by DeepSeek having the most effective and cheap caching in the industry I use DeepSeek v4 Flash & MiMo v2.5 Pro. Prefer the latter over DeepSeek v4 Pro because it costs the same while being equally good & less chattier for coding workloads. Although, I've begun experimenting with Hy3 (as an in-between Flash & Pro) & GLM 5.2 (for long-horizon tas", "context": "", "use_case": "coding workloads", "switched_from": "", "story": "The Kimi K3 Moment"}, {"id": 783005153, "item_id": 48937822, "url": "https://news.ycombinator.com/item?id=48937822", "by": "ignoramous", "date": "2026-07-16", "stance": "recommend", "quote": "are genuinely good enough as daily drivers, given the costs", "excerpt": "Possible, but pay-as-you-go Hy3 / DeepSeek v4 Pro / MiMo v2.5 Pro (from respective vendors) are genuinely good enough as daily drivers, given the costs (especially, low prices for input cache, which usually makes up 70%+ of total input for agentic workflows). I put in $10 in DeepSeek & Xiaomi MiMo, and I've barely used $1 each, in a week of coding work. Coding Plans by MiniMax ($20/mo for 1.7b tokens) and Z.ai (~$30/", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Kimi K3 is now live"}, {"id": 782086784, "item_id": 48880424, "url": "https://news.ycombinator.com/item?id=48880424", "by": "nmfisher", "date": "2026-07-12", "stance": "neutral", "quote": "", "excerpt": "I'm not a regular v2.5 user, so I don't really know. But given the TileRT team write-up says the entire network gets quantized to FP8 (and experts get quantized to FP4)[0], I'm assuming there's at least a modest drop in quality. [0] https://www.tilert.ai/blog/breaking-1000-tps.html", "context": "", "use_case": "Coding assistant model", "switched_from": "", "story": "Inference Optimization for MiMo v2.5: Pushing Hybrid SWA Efficiency to the Limit"}, {"id": 781864177, "item_id": 48866511, "url": "https://news.ycombinator.com/item?id=48866511", "by": "ignoramous", "date": "2026-07-10", "stance": "compare", "quote": "it is striking how similar performance & pricing of the models, DeepSeek v4 Pro & MiMo v2.5 Pro, is", "excerpt": "> the kind of engineering that goes into Xiaomi (and Deepseeks) inference optimizations At Xiaomi, MiMo is now led by Luo Fuli. She is a former Alibaba & DeepSeek employee: https://newsen.pku.edu.cn/news_events/news/people/15385.html (https://archive.vn/I8Pmu) / https://e.vnexpress.net/news/tech/personalities/who-is-luo-fuli-the-30-year-old-ai-genius-girl-behind-deepseek-s-success-4953445.html (https://archive.vn/sb3", "context": "", "use_case": "", "switched_from": "", "story": "Inference Optimization for MiMo v2.5: Pushing Hybrid SWA Efficiency to the Limit"}, {"id": 779940115, "item_id": 48746257, "url": "https://news.ycombinator.com/item?id=48746257", "by": "coder543", "date": "2026-07-01", "stance": "neutral", "quote": "I was doing it just fine on llama-server with 200k+ of context.", "excerpt": "It\u2019s not FUD. It is my actual, lived experience. FUD is false, which this is not. I use both vLLM and llama-server. vLLM is very painful, even with the Spark community docker image. It is slow to start, it does not support 3-bit dynamic quants well, and it takes a lot of tweaking to get it to run well for each model I want to try out, which is made worse by the slow starts. I\u2019m glad you\u2019ve had a better experience? I ", "context": "", "use_case": "local model", "switched_from": "", "story": "Qwen 3.6 27B is the sweet spot for local development"}, {"id": 779827252, "item_id": 48739203, "url": "https://news.ycombinator.com/item?id=48739203", "by": "Imustaskforhelp", "date": "2026-06-30", "stance": "recommend", "quote": "Deepseek v4 pro /mimo v2.5 pro models are comparably good", "excerpt": "I think that there are some subscriptions to go by. Z.ai subscription might still be interesting. I once haggled with kimi to get it for 1$ per month. I can only help in providing pointers: If you wish to go Non-API but rather subscription route: Z.Ai subscription/ Kimi subscription / MiniMax subscriptions are good. You could also take a look at ollama subscription and opencode subscriptions. If you wish to go API ro", "context": "", "use_case": "API coding model", "switched_from": "", "story": "Claude Code Is Steganographically Marking Requests"}, {"id": 779515825, "item_id": 48719739, "url": "https://news.ycombinator.com/item?id=48719739", "by": "bel8", "date": "2026-06-29", "stance": "recommend", "quote": "I use DeepSeek V4 Flash (high) and MiMo 2.5 (non Pro, because vision)", "excerpt": "Why would you say that? I use DeepSeek V4 Flash (high) and MiMo 2.5 (non Pro, because vision) to work on medium sized projects (~1mil lines of code, C#, Go, TypeScript) with great success. And that is coming from someone who used Opus 4.7 and GPT 5.5 as workhorses before. And I'm pretty sure GLM 5.2 is better than the lighter models I use. My worflow is simple: plan -> clarify -> implement. 1) plan prompt template: I", "context": "works on ~1M line codebases", "use_case": "coding with vision", "switched_from": "Opus 4.7", "story": "Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks"}, {"id": 779443872, "item_id": 48715242, "url": "https://news.ycombinator.com/item?id=48715242", "by": "SwellJoe", "date": "2026-06-28", "stance": "neutral", "quote": "MiMo 2.5 Pro was released in April, at least a month before any of the cases were published", "excerpt": "That's covered in the article. All bugs (which you can see here: https://github.com/swelljoe/nelson/tree/main/cases ) are extremely recent (like a week old when I pulled them at the end of May). MiMo 2.5 Pro was released in April, at least a month before any of the cases were published, and I don't remember the exact training data cutoff for that one (if I found it), but I'm certain it's at least a couple/few months ", "context": "", "use_case": "", "switched_from": "", "story": "Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks"}, {"id": 779398946, "item_id": 48712434, "url": "https://news.ycombinator.com/item?id=48712434", "by": "SwellJoe", "date": "2026-06-28", "stance": "warn", "quote": "it's performed worse on almost every test I've done since", "excerpt": "I added GLM 5.2 to my security bug hunting benchmark when it came out, and found it to be a good performer, but not the best open model. The benchmark tests whether models can find bugs Mythos found. The best open models in the initial benchmark were DeepSeek V4 Pro or MiMo 2.5 Pro. But it turned out MiMo got lucky, it's performed worse on almost every test I've done since, while DeepSeek has consistently been among ", "context": "", "use_case": "Security bug finding", "switched_from": "", "story": "Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks"}, {"id": 778794865, "item_id": 48674679, "url": "https://news.ycombinator.com/item?id=48674679", "by": "bel8", "date": "2026-06-25", "stance": "recommend", "quote": "You'll get 10x more value by using MiMo 2.5 or DeepSeek Flash which is what I use for most code.", "excerpt": "GLM 5.2 is priced at 1/3 of Opus. Depending on who you ask for a napkin math. Not worth it in my opinion. You'll get 10x more value by using MiMo 2.5 or DeepSeek Flash which is what I use for most code.", "context": "", "use_case": "coding", "switched_from": "", "story": "Elevated error rate across multiple models"}, {"id": 778697187, "item_id": 48668574, "url": "https://news.ycombinator.com/item?id=48668574", "by": "JSR_FDED", "date": "2026-06-24", "stance": "compare", "quote": "Deepseek, Kimi, MiMo started giving me multiple options but advocating strongly that I should either accept this deficiency", "excerpt": "Anecdote, not \u201cresearch\u201d: Yesterday I compared Deepseek, Kimi 2.6, MiMo 2.5 and GLM 5.2 for the same task (replace a custom token-based auth scheme with a cookies-based scheme across a front- and back-end codebase). I used Opencode with the zen subscription to try different models. All did this perfectly, basically indistinguishable from each other. However, when I pointed out that the new cookies-based auth didn\u2019t a", "context": "", "use_case": "coding", "switched_from": "", "story": "GLM-5.2 is the step change for open agents"}, {"id": 778474163, "item_id": 48654635, "url": "https://news.ycombinator.com/item?id=48654635", "by": "ignoramous", "date": "2026-06-23", "stance": "recommend", "quote": "MiMo v2.5 & Pro", "excerpt": "> How do you go about comparing models? I do this often: I'd have a prompt in mind before I manually find the fix for subtle bugs, or plan out how I'd implement a feature. Then, I prompt the models I want to test (with the prompt I originally had in mind) and see if any of them get it right. To my surprise, the Claudes always perform better, and so, it seems like my prompting behaviour is either attuned to them, or C", "context": "", "use_case": "", "switched_from": "", "story": "China is having another AI moment"}, {"id": 777992034, "item_id": 48624502, "url": "https://news.ycombinator.com/item?id=48624502", "by": "trollbridge", "date": "2026-06-21", "stance": "recommend", "quote": "Please do yourself a favour and check out GLM-5.2, Qwen-3.7-Max, MiMo-2.5-Pro, and DeepSeek-V4-Pro.", "excerpt": "Please do yourself a favour and check out GLM-5.2, Qwen-3.7-Max, MiMo-2.5-Pro, and DeepSeek-V4-Pro. And then for stuff that you already said you were able to use Mistral for... Qwen-3.6 (option to run locally), MiMo-2.5, DeepSeek-V4-Flash, or... many, many other models to choose from too.", "context": "", "use_case": "alternative to Claude Opus", "switched_from": "", "story": "Anthropic to Require ID Verification for Certain Capabilities Starting July 8"}, {"id": 777377796, "item_id": 48586112, "url": "https://news.ycombinator.com/item?id=48586112", "by": "Imustaskforhelp", "date": "2026-06-18", "stance": "recommend", "quote": "you have glm 5.2, kimi k2.7,mimo v2.5 pro and deepseek v4", "excerpt": "Qwen models are generally the best if you want local models in the 100b max size. I am not sure but I recommend looking at the size of deepseek flash as well to see if it can work for you, perhaps GLM 5 Air model is also around this size. and if you want something at the larger models scale, then you have glm 5.2, kimi k2.7,mimo v2.5 pro and deepseek v4", "context": "", "use_case": "larger models", "switched_from": "", "story": "Ask HN: Whats the best and small open source model?"}]}