{"slug": "mistral-medium", "name": "Mistral Medium", "category": "ai-models", "category_name": "AI models", "description": "", "recommenders": 4, "commenters": 16, "warners": 4, "score": 0.555, "rising": -1.31, "first": "2025-11-04", "latest": "2026-10-06", "why": "if price, speed, and reliability are a concern for your use cases I cannot recommend Mistral enough.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 6, "compare": 4, "warn": 4}, "spark": [0, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "if price, speed, and reliability are a concern for your use cases I cannot recommend Mistral enough.", "kind": "", "icon": true, "domain": "openrouter.ai", "github_repo": null, "official_url": "https://mistral.ai", "pricing": "", "aliases": ["Mistral Medium 3.5", "Mistral Medium", "Mistral Medium 3.1"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 777234850, "item_id": 48577178, "url": "https://news.ycombinator.com/item?id=48577178", "by": "gertlabs", "date": "2026-06-17", "version": "3.5", "stance": "recommend", "quote": "Gemini 3.5 Flash and Mistral Medium 3.5 being significantly better at real-time decision making", "excerpt": "We do something like this at scale at https://gertlabs.com/spectate In particular, we run social intelligence evaluations, in addition to the more popular coding evals. These games are mostly cooperative, but we also incorporate social deduction and theory of mind like in our adversarial customer service environment (not being compromised by an identity thief, or conversely, being able to compromise a customer servic", "context": "", "use_case": "", "switched_from": "", "story": "A Robot Is Sprinting Towards You: Do You Want It Running on Claude or Grok?"}, {"id": 767243824, "item_id": 47952739, "url": "https://news.ycombinator.com/item?id=47952739", "by": "KronisLV", "date": "2026-04-29", "version": "3.5", "stance": "recommend", "quote": "For it's size, that's really good!", "excerpt": "For it's size, that's really good! Though I bet it being a dense model probably helps a lot, if it was MoE at that size, I bet the benchmark performance would go quite a bit down (which consequently would also mean that I'd at least be able to run it with decent tokens/second, with the bunch of Nvidia L4 cards available to me, which presently are only okay with MoE models). It's cool that they added comparisons to th", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Medium 3.5"}, {"id": 758492048, "item_id": 47405753, "url": "https://news.ycombinator.com/item?id=47405753", "by": "chucky_z", "date": "2026-03-16", "version": "3.1", "stance": "recommend", "quote": "I use mistral-medium-3.1 for a lot of random daily tasks", "excerpt": "I use mistral-medium-3.1 for a lot of random daily tasks, along with the vibe cli. I'd state from my personal opinion that mistral is my preferred 'model vendor' by far at this point. They're extremely consistent between releases while each of them just feels better. I also have a strong personal preference to the output. I actively use gemini-3.1-pro-preview, claude-4.6-opus-high, and gpt-5.3-codex as well. I prefer", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Releases Leanstral"}, {"id": 737961792, "item_id": 46122612, "url": "https://news.ycombinator.com/item?id=46122612", "by": "barrell", "date": "2025-12-02", "version": null, "stance": "recommend", "quote": "if price, speed, and reliability are a concern for your use cases I cannot recommend Mistral enough.", "excerpt": "I use large language models in http://phrasing.app to format data I can retrieve in a consistent skimmable manner. I switched to mistral-3-medium-0525 a few months back after struggling to get gpt-5 to stop producing gibberish. It's been insanely fast, cheap, reliable, and follows formatting instructions to the letter. I was (and still am) super super impressed. Even if it does not hold up in benchmarks, it still out", "context": "", "use_case": "formatting retrieved data in app", "switched_from": "GPT-5", "story": "Mistral 3 family of models released"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 773334528, "item_id": 48333408, "url": "https://news.ycombinator.com/item?id=48333408", "by": "kioleanu", "date": "2026-05-29", "version": "3.5", "stance": "warn", "quote": "priced $1.5/$7.5 per million input/output tokens (change from the previous $0.4/$2)", "excerpt": "I just got an email from them saying that they\u2019re retiring some (most?) of the dedicated models like devstral gradually through August and one should now use the general model. Cost grows exponentially Devstral 2 (devstral-2512 and devstral-latest) \u2192 We recommend transitioning to Mistral Medium 3.5 (mistral-medium-3-5 with reasoning_effort set to \"high\"), a stronger model, priced $1.5/$7.5 per million input/output to", "context": "", "use_case": "coding via API", "switched_from": "Devstral 2", "story": "Notes from the Mistral AI Now Summit in Paris"}, {"id": 767349282, "item_id": 47959330, "url": "https://news.ycombinator.com/item?id=47959330", "by": "barrell", "date": "2026-04-30", "version": "3.5", "stance": "warn", "quote": "the fact it's a \"Medium\" and 5x the price of the Large definitely concerns me", "excerpt": "Yeah I use Mistral Large for a lot of formatting work. For this one use case of mine, it outperforms frontier models by a significant margin. I've found tons of use cases for mistral small as well. I'd love to use Mistral for more tasks, but Mistral Large doesn't quite cut it for all tasks. So on the one hand, I'm excited there is another model, and presumably more performant based on the price? But the fact it's a \"", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Medium 3.5"}, {"id": 767217248, "item_id": 47951078, "url": "https://news.ycombinator.com/item?id=47951078", "by": "Mashimo", "date": "2026-04-29", "version": "3.5", "stance": "warn", "quote": "I also did some SVG tests, it's really bad.", "excerpt": "I also did some SVG tests, it's really bad. https://chat.mistral.ai/chat/897fbe7d-b1ae-4109-9b29-f3ccc4f8896d", "context": "", "use_case": "SVG generation", "switched_from": "", "story": "Mistral Medium 3.5"}, {"id": 767210704, "item_id": 47950669, "url": "https://news.ycombinator.com/item?id=47950669", "by": "simonw", "date": "2026-04-29", "version": "3.5", "stance": "warn", "quote": "it's pretty disappointing.", "excerpt": "Some poking around in the source code for https://github.com/mistralai/mistral-vibe got me to this: curl https://api.mistral.ai/v1/chat/completions \\ -H \"Content-Type: application/json\" \\ -H \"Authorization: Bearer $(llm keys get mistral)\" \\ -d '{ \"model\": \"mistral-medium-3.5\", \"messages\": [ {\"role\": \"user\", \"content\": \"Generate an SVG of a pelican riding a bicycle\"} ] }' Which did work: https://gist.github.com/simonw", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Medium 3.5"}]}], "who": [], "tags": [], "use_cases": ["coding", "coding via api", "svg generation", "formatting retrieved data in app"], "compared": [{"slug": "glm", "name": "GLM", "co": 3, "switched_from": 0, "switched_to": 2}, {"slug": "gpt-5", "name": "GPT-5", "co": 1, "switched_from": 1, "switched_to": 0}, {"slug": "devstral-2", "name": "Devstral 2", "co": 1, "switched_from": 1, "switched_to": 0}, {"slug": "mistral-large", "name": "Mistral Large", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "mistral-small", "name": "Mistral Small", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "kimi", "name": "Kimi", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "mistral-vibe", "name": "Mistral Vibe", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=47949642", "title": "Mistral Medium 3.5", "mentions": 6}, {"url": "https://news.ycombinator.com/item?id=49977979", "title": "Mistral Large 4", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49753878", "title": "An empirical study of harness design for coding agents", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48935342", "title": "Kimi K3 is now live", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48576824", "title": "A Robot Is Sprinting Towards You: Do You Want It Running on Claude or Grok?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48541014", "title": "Show HN: Can Europe train a frontier AI model on the compute it owns?", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 2}, "2025-12": {"recommend": 1}, "2026-01": {}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {"compare": 1, "warn": 3, "neutral": 1, "recommend": 1}, "2026-05": {"neutral": 1, "warn": 1}, "2026-06": {"compare": 1, "recommend": 1}, "2026-07": {"compare": 1}, "2026-08": {}, "2026-09": {"neutral": 1}, "2026-10": {"neutral": 1, "compare": 1}}, "versions": [], "version_unnamed": 3, "quotes": [{"id": 799742929, "item_id": 49983933, "url": "https://news.ycombinator.com/item?id=49983933", "by": "chriddyp", "date": "2026-10-06", "version": "3.5", "stance": "compare", "quote": "It's 10x cheaper than Mistral Medium 3.5 from April", "excerpt": "Just ran this through our data analytics benchmark (I work at Plotly). It's 10x cheaper than Mistral Medium 3.5 from April and goes from 58% to 74% correct. Definitely a generational shift. It's not on the Pareto curve yet, but it's good enough for data analytics, and at this rate I suspect it'll be excellent in another few months. Full write up: https://plotly.com/blog/mistral-large-4-plotly-data-analytics-bench/", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Large 4"}, {"id": 799694544, "item_id": 49980909, "url": "https://news.ycombinator.com/item?id=49980909", "by": "phillc73", "date": "2026-10-06", "version": "3.5", "stance": "neutral", "quote": "I struggled on with Mistral Medium 3.5 for longer than I should have", "excerpt": "I'm at a loss as to what to do now. I've been wanting to support Mistral for so long. I struggled on with Mistral Medium 3.5 for longer than I should have (although I also think it taught me some valuable process lessons). Recently I switched to the Mistral hosted GLM-5.3, this worked very well and powered through a tonne of work. Unfortunately, I also completely maxed out two subscriptions within the space of six da", "context": "", "use_case": "coding", "switched_from": "", "story": "Mistral Large 4"}, {"id": 796114338, "item_id": 49757146, "url": "https://news.ycombinator.com/item?id=49757146", "by": "rahulmax", "date": "2026-09-18", "version": null, "stance": "neutral", "quote": "the models are Nemotron-3 and Mistral-Medium, not the frontier models", "excerpt": "Quite inline with what I had found with my Claude code sessions over the last year. I wrote about this a few months ago. https://rahulmax.com/notes/how-i-keep-the-ai-bill-down/ In their case, context management pays off more the tighter your window. Their gap between managing and not managing is 35.7 points of success rate at 32k and 2.7 points at 128k. My version of that was a rule I stick to, as much as I can. I ch", "context": "", "use_case": "", "switched_from": "", "story": "An empirical study of harness design for coding agents"}, {"id": 783108450, "item_id": 48944278, "url": "https://news.ycombinator.com/item?id=48944278", "by": "rldjbpin", "date": "2026-07-17", "version": "3.5", "stance": "compare", "quote": "twice the European counterpart", "excerpt": "> I think that's the most expensive pelican I've rendered through a Chinese model so far. quite insane that it costs as much as 5.6 Terra [1], and twice the European counterpart (albeit dated for today's standards?) [2]. to be fair, the pelicans from Terra were quite weird all things considered. also, given the limited TPS from the first-party, it has to be pushing the limits of inference capabilities. [1] https://op", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K3 is now live"}, {"id": 777234850, "item_id": 48577178, "url": "https://news.ycombinator.com/item?id=48577178", "by": "gertlabs", "date": "2026-06-17", "version": "3.5", "stance": "recommend", "quote": "Gemini 3.5 Flash and Mistral Medium 3.5 being significantly better at real-time decision making", "excerpt": "We do something like this at scale at https://gertlabs.com/spectate In particular, we run social intelligence evaluations, in addition to the more popular coding evals. These games are mostly cooperative, but we also incorporate social deduction and theory of mind like in our adversarial customer service environment (not being compromised by an identity thief, or conversely, being able to compromise a customer servic", "context": "", "use_case": "", "switched_from": "", "story": "A Robot Is Sprinting Towards You: Do You Want It Running on Claude or Grok?"}, {"id": 776736224, "item_id": 48546014, "url": "https://news.ycombinator.com/item?id=48546014", "by": "SyneRyder", "date": "2026-06-15", "version": "3.5", "stance": "compare", "quote": "Mistral Medium 3.5 costs 5x the price of Mistral Large 3", "excerpt": "Well, the front page of their website claims \"Frontier AI In Your Hands\", so I guess they're not marketing it that way. I personally think there's a hint in that Mistral Medium 3.5 costs 5x the price of Mistral Large 3, and that Mistral Large is not listed anymore as a \"Featured Model\" and hasn't been updated since Dec 2025: https://docs.mistral.ai/models/overview But what I really base it on is an interview the Mist", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Can Europe train a frontier AI model on the compute it owns?"}, {"id": 773334528, "item_id": 48333408, "url": "https://news.ycombinator.com/item?id=48333408", "by": "kioleanu", "date": "2026-05-29", "version": "3.5", "stance": "warn", "quote": "priced $1.5/$7.5 per million input/output tokens (change from the previous $0.4/$2)", "excerpt": "I just got an email from them saying that they\u2019re retiring some (most?) of the dedicated models like devstral gradually through August and one should now use the general model. Cost grows exponentially Devstral 2 (devstral-2512 and devstral-latest) \u2192 We recommend transitioning to Mistral Medium 3.5 (mistral-medium-3-5 with reasoning_effort set to \"high\"), a stronger model, priced $1.5/$7.5 per million input/output to", "context": "", "use_case": "coding via API", "switched_from": "Devstral 2", "story": "Notes from the Mistral AI Now Summit in Paris"}, {"id": 771380466, "item_id": 48211279, "url": "https://news.ycombinator.com/item?id=48211279", "by": "KronisLV", "date": "2026-05-20", "version": "3.5", "stance": "neutral", "quote": "Mistral Medium 3.5 is interesting because it's 128B but dense", "excerpt": "There definitely have been some options in the past, cool to see them. Oddly enough, though, Qwen 3.6 35B A3B and Gemma got some really good reviews, despite being way smaller than any of these ones. Qwen 3.5, 122B A10B: https://huggingface.co/unsloth/Qwen3.5-122B-A10B-GGUF Qwen Coder Next, 80B A3B: https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF It's kinda weird that DeepSeek V4 Flash is supposed to be 284B A13", "context": "", "use_case": "", "switched_from": "", "story": "Qwen3.7-Max: The Agent Frontier"}, {"id": 767349282, "item_id": 47959330, "url": "https://news.ycombinator.com/item?id=47959330", "by": "barrell", "date": "2026-04-30", "version": "3.5", "stance": "warn", "quote": "the fact it's a \"Medium\" and 5x the price of the Large definitely concerns me", "excerpt": "Yeah I use Mistral Large for a lot of formatting work. For this one use case of mine, it outperforms frontier models by a significant margin. I've found tons of use cases for mistral small as well. I'd love to use Mistral for more tasks, but Mistral Large doesn't quite cut it for all tasks. So on the one hand, I'm excited there is another model, and presumably more performant based on the price? But the fact it's a \"", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Medium 3.5"}, {"id": 767243824, "item_id": 47952739, "url": "https://news.ycombinator.com/item?id=47952739", "by": "KronisLV", "date": "2026-04-29", "version": "3.5", "stance": "recommend", "quote": "For it's size, that's really good!", "excerpt": "For it's size, that's really good! Though I bet it being a dense model probably helps a lot, if it was MoE at that size, I bet the benchmark performance would go quite a bit down (which consequently would also mean that I'd at least be able to run it with decent tokens/second, with the bunch of Nvidia L4 cards available to me, which presently are only okay with MoE models). It's cool that they added comparisons to th", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Medium 3.5"}, {"id": 767217248, "item_id": 47951078, "url": "https://news.ycombinator.com/item?id=47951078", "by": "Mashimo", "date": "2026-04-29", "version": "3.5", "stance": "warn", "quote": "I also did some SVG tests, it's really bad.", "excerpt": "I also did some SVG tests, it's really bad. https://chat.mistral.ai/chat/897fbe7d-b1ae-4109-9b29-f3ccc4f8896d", "context": "", "use_case": "SVG generation", "switched_from": "", "story": "Mistral Medium 3.5"}, {"id": 767216144, "item_id": 47951009, "url": "https://news.ycombinator.com/item?id=47951009", "by": "gregsadetsky", "date": "2026-04-29", "version": "3.5", "stance": "neutral", "quote": "", "excerpt": "I didn't know about HERMES.md ... (??) - found information here for others who are curious https://github.com/anthropics/claude-code/issues/53262", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Medium 3.5"}, {"id": 767210704, "item_id": 47950669, "url": "https://news.ycombinator.com/item?id=47950669", "by": "simonw", "date": "2026-04-29", "version": "3.5", "stance": "warn", "quote": "it's pretty disappointing.", "excerpt": "Some poking around in the source code for https://github.com/mistralai/mistral-vibe got me to this: curl https://api.mistral.ai/v1/chat/completions \\ -H \"Content-Type: application/json\" \\ -H \"Authorization: Bearer $(llm keys get mistral)\" \\ -d '{ \"model\": \"mistral-medium-3.5\", \"messages\": [ {\"role\": \"user\", \"content\": \"Generate an SVG of a pelican riding a bicycle\"} ] }' Which did work: https://gist.github.com/simonw", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Medium 3.5"}, {"id": 767198512, "item_id": 47949907, "url": "https://news.ycombinator.com/item?id=47949907", "by": "spwa4", "date": "2026-04-29", "version": "3.5", "stance": "compare", "quote": "but is worse than Sonnet 3.6", "excerpt": "TLDR: Mistral Medium 3.5, text-only, 128B dense model, 256k context window, modified MIT license. Model is ~140G ... https://huggingface.co/mistralai/Mistral-Medium-3.5-128B They more or less claim this exceeds Claude Sonnet 3.5 on most things, but is worse than Sonnet 3.6, and exceeds all other open models. Oh and they have a cloud service that will code your apps \"in the cloud\". But, yeah, at this point, so does my", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Medium 3.5"}, {"id": 758492048, "item_id": 47405753, "url": "https://news.ycombinator.com/item?id=47405753", "by": "chucky_z", "date": "2026-03-16", "version": "3.1", "stance": "recommend", "quote": "I use mistral-medium-3.1 for a lot of random daily tasks", "excerpt": "I use mistral-medium-3.1 for a lot of random daily tasks, along with the vibe cli. I'd state from my personal opinion that mistral is my preferred 'model vendor' by far at this point. They're extremely consistent between releases while each of them just feels better. I also have a strong personal preference to the output. I actively use gemini-3.1-pro-preview, claude-4.6-opus-high, and gpt-5.3-codex as well. I prefer", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Releases Leanstral"}, {"id": 737961792, "item_id": 46122612, "url": "https://news.ycombinator.com/item?id=46122612", "by": "barrell", "date": "2025-12-02", "version": null, "stance": "recommend", "quote": "if price, speed, and reliability are a concern for your use cases I cannot recommend Mistral enough.", "excerpt": "I use large language models in http://phrasing.app to format data I can retrieve in a consistent skimmable manner. I switched to mistral-3-medium-0525 a few months back after struggling to get gpt-5 to stop producing gibberish. It's been insanely fast, cheap, reliable, and follows formatting instructions to the letter. I was (and still am) super super impressed. Even if it does not hold up in benchmarks, it still out", "context": "", "use_case": "formatting retrieved data in app", "switched_from": "GPT-5", "story": "Mistral 3 family of models released"}, {"id": 733814624, "item_id": 45863414, "url": "https://news.ycombinator.com/item?id=45863414", "by": "b16m", "date": "2025-11-08", "version": "3.1", "stance": "neutral", "quote": "rigged it so that Mistral Medium 3.1 would be at the top", "excerpt": "The french government created an LLM leaderboard akin to lmarena, but rigged it so that Mistral Medium 3.1 would be at the top? https://x.com/scaling01/status/1987226193959993742 https://huggingface.co/datasets/ministere-culture/comparia-conversations", "context": "", "use_case": "", "switched_from": "", "story": "French government AI model leaderboard"}, {"id": 732969504, "item_id": 45810594, "url": "https://news.ycombinator.com/item?id=45810594", "by": "simon-inta", "date": "2025-11-04", "version": null, "stance": "neutral", "quote": "Note on Mistral Medium's great performance : there is no style control on compar:IA", "excerpt": "The data is open : https://huggingface.co/ministere-culture Colab notebook to reproduce the calculations : https://colab.research.google.com/drive/1j5AfStT3h-IK8V6FSJY9CLAYr_1SvYw7#scrollTo=LgXO1k5Tp0pq Note on Mistral Medium's great performance : there is no style control on compar:IA, and the majority of questions are not focused on code, thus explaining the great performance of the model.", "context": "", "use_case": "", "switched_from": "", "story": "Ranking LLMs based on 180k French votes (French government's AI arena)"}]}