Загрузка видео...

Не удалось загрузить видео

На главную

DeepSeek V4 Flash 0731 vs Opus 5. Only 7 days separated their releases. While Opus 5 accomplished in 1 shot what took DS 3, DeepSeek V4 Flash did it in ~900 lines vs ~3000 lines for Opus. Cost delta is stark. DeepSeek cost 1 cent. DS V4 Flash 0731...

TeksEdge's profile picture

David Hendrickson

8,888 subscribers

41,980 просмотров • 10 дней назад •via X (Twitter)

Наука и технологииОбразованиеНовости и политика
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

By popular demand, we are extending our 90% off discount on DeepSeek V4 Flash 0731 for the next 3 days. Try it today at
0:26

By popular demand, we are extending our 90% off discount on DeepSeek V4 Flash 0731 for the next 3 days. Try it today at

Nous Research

183,085 просмотров • 2 дней назад

Dostlar yeni LLM Coding Benchmark çıktılarımız hazır. 🎉 Bu kez yine zorlu alanları bir araya getiren Trail ile Çift sarkaç: Euler vs RK4 entegrasyonu task'ını test ettim.Bu task ile modellerin hibrit; algoritma, matematik, coding ve Frontend yeteneklerini ölçümledim. Tüm modelleri opencode kullanarak kodlama yaptırdım. Aynı zamanda hepsinde en üst thinking eforu kullandım. Bu kez skorlamada Fiyat/Performans ve Kalite/Performans skalasında yaptım. Değerlendirmeyi modellerin isimlerini görmeden GPT 5.6 Pro yaptı. Testte yer alan Modeller; - DeepSeek V4 Flash 0731 - Gemini 3.6 Flash - Grok 4.5 - Sonnet 5 - GPT5.6-Luna - GPT5.6-Sol - Opus 5 - Kimi K3 - Qwen 3.8 Kalite/Performans - Genel sıralama - Opus 5 — 96.32/100 - $1.4660 - GPT5.6-Sol — 93.85/100 - $0.3627 - GPT5.6-Luna — 92.15/100 - $0.2373 - Kimi K3 — 91.70/100 - $0.3312 - Qwen3.8 — 89.95/100 - $0.2807 - Sonnet 5 — 88.16/100 - $0.4429 - DeepSeek V4 Flash 0731 — 85.12/100 - $0.0994 - Gemini 3.6 Flash — 83.24/100 - $0.0637 - Grok 4.5 — 79.82/100 - $0.4768 Fiyat/performans - Genel sıralama - DeepSeek V4 Flash - 88.00 - GPT5.6-Luna - 87.04 - Qwen 3.8 - 85.75 - Kimi K3 - 84.91 - Gemini 3.6 Flash - 83.57 - GPT5.6-Sol - 82.91 - Grok 4.5 - 81.87 - Sonnet 5 - 80.66 - Opus 5 - 80.22 Genel Değerlendirme: - Prod fiyat/performans kazananı: Qwen3.8. - Maksimum kalite, maliyet önemsiz: Opus 5. - En düşük bütçede yeterli ve tam özellikli çıktı: DeepSeek V4 Flash - En dengeli orta nokta: GPT5.6-Luna ve Kimi K3 Teknik Alan Spesifik Başarı: - En iyi saf numerical integrator: Opus 5 = GPT5.6-Sol - En doğru built-in validator: GPT5.6-Luna - En iyi standart runtime performansı: DeepSeek V4 Flash ve Kimi K3 - En iyi görsel kalite: Opus 5 - En iyi UI/ürün: GPT5.6-Sol - En iyi mimari: Opus 5 - En iyi ekonomik F/P: DeepSeek V4 Flash - En iyi production F/P: GPT5.6-Sol - En pahalı marjinal kalite artışı: Opus 5 - En ciddi validator hatası: Grok 4.5 - En yüksek hot-path/GC riski: Gemini 3.6 Flash
0:58

Dostlar yeni LLM Coding Benchmark çıktılarımız hazır. 🎉 Bu kez yine zorlu alanları bir araya getiren Trail ile Çift sarkaç: Euler vs RK4 entegrasyonu task'ını test ettim.Bu task ile modellerin hibrit; algoritma, matematik, coding ve Frontend yeteneklerini ölçümledim. Tüm modelleri opencode kullanarak kodlama yaptırdım. Aynı zamanda hepsinde en üst thinking eforu kullandım. Bu kez skorlamada Fiyat/Performans ve Kalite/Performans skalasında yaptım. Değerlendirmeyi modellerin isimlerini görmeden GPT 5.6 Pro yaptı. Testte yer alan Modeller; - DeepSeek V4 Flash 0731 - Gemini 3.6 Flash - Grok 4.5 - Sonnet 5 - GPT5.6-Luna - GPT5.6-Sol - Opus 5 - Kimi K3 - Qwen 3.8 Kalite/Performans - Genel sıralama - Opus 5 — 96.32/100 - $1.4660 - GPT5.6-Sol — 93.85/100 - $0.3627 - GPT5.6-Luna — 92.15/100 - $0.2373 - Kimi K3 — 91.70/100 - $0.3312 - Qwen3.8 — 89.95/100 - $0.2807 - Sonnet 5 — 88.16/100 - $0.4429 - DeepSeek V4 Flash 0731 — 85.12/100 - $0.0994 - Gemini 3.6 Flash — 83.24/100 - $0.0637 - Grok 4.5 — 79.82/100 - $0.4768 Fiyat/performans - Genel sıralama - DeepSeek V4 Flash - 88.00 - GPT5.6-Luna - 87.04 - Qwen 3.8 - 85.75 - Kimi K3 - 84.91 - Gemini 3.6 Flash - 83.57 - GPT5.6-Sol - 82.91 - Grok 4.5 - 81.87 - Sonnet 5 - 80.66 - Opus 5 - 80.22 Genel Değerlendirme: - Prod fiyat/performans kazananı: Qwen3.8. - Maksimum kalite, maliyet önemsiz: Opus 5. - En düşük bütçede yeterli ve tam özellikli çıktı: DeepSeek V4 Flash - En dengeli orta nokta: GPT5.6-Luna ve Kimi K3 Teknik Alan Spesifik Başarı: - En iyi saf numerical integrator: Opus 5 = GPT5.6-Sol - En doğru built-in validator: GPT5.6-Luna - En iyi standart runtime performansı: DeepSeek V4 Flash ve Kimi K3 - En iyi görsel kalite: Opus 5 - En iyi UI/ürün: GPT5.6-Sol - En iyi mimari: Opus 5 - En iyi ekonomik F/P: DeepSeek V4 Flash - En iyi production F/P: GPT5.6-Sol - En pahalı marjinal kalite artışı: Opus 5 - En ciddi validator hatası: Grok 4.5 - En yüksek hot-path/GC riski: Gemini 3.6 Flash

Alican Kiraz

14,150 просмотров • 8 дней назад

DeepSeek V4 Flash 0731 in Hermes Agent and one prompt, took 32 minutes and cost 0.07$, this model is so cheap to the point where 2 dollars can last you a full day.
1:03

DeepSeek V4 Flash 0731 in Hermes Agent and one prompt, took 32 minutes and cost 0.07$, this model is so cheap to the point where 2 dollars can last you a full day.

Elshayib

668,858 просмотров • 11 дней назад

DeepSeek-V4-Flash vs Gemini-3.6-Flash both given the exact same prompt to build 3D pirate ship Cost: > deepseek-v4-flash: $0.14 / $0.28 > gemini-3.6-flash: $1.50 / $7.50 though deepseek is 20x cheaper, gemini was surprising faster with the output Prompt used: "build a 3D model of pirate ship in Three js with minimal dashboard buttons in light theme background, with wide view of the pirate ship"
0:33

DeepSeek-V4-Flash vs Gemini-3.6-Flash both given the exact same prompt to build 3D pirate ship Cost: > deepseek-v4-flash: $0.14 / $0.28 > gemini-3.6-flash: $1.50 / $7.50 though deepseek is 20x cheaper, gemini was surprising faster with the output Prompt used: "build a 3D model of pirate ship in Three js with minimal dashboard buttons in light theme background, with wide view of the pirate ship"

Tim Jayas

20,127 просмотров • 9 дней назад

DeepSeek V4 Flash costs just 1% as much as Fable 5 for the same task. Starting Thursday, it’s free and unlimited on Open Design for 7 days.
0:20

DeepSeek V4 Flash costs just 1% as much as Fable 5 for the same task. Starting Thursday, it’s free and unlimited on Open Design for 7 days.

Open Design

11,251 просмотров • 7 дней назад

I can't believe this works, but I got DeepSeek-V4-Flash (284B params) running on a Raspberry Pi 5 (8GB edition) at >1tok/s @ ~8W during full-tilt inference! It uses an untouched copy of antirez's GGUF. Took 160+ experiments over 5 days between GPT-5.5 xhigh and Opus 4.8 max.
0:32

I can't believe this works, but I got DeepSeek-V4-Flash (284B params) running on a Raspberry Pi 5 (8GB edition) at >1tok/s @ ~8W during full-tilt inference! It uses an untouched copy of antirez's GGUF. Took 160+ experiments over 5 days between GPT-5.5 xhigh and Opus 4.8 max.

Dan Woods

184,583 просмотров • 2 месяцев назад

DwarfStar DeepSeek v4 Flash 0731 pre-M5 kernel keeps improving 💪🏻 - prefill +11% - decode +10% - single request no DSpark/MTP. - 100% same logics between baseline and now. Today is QA like crazy. I hope to file PR by EOD antirez Here are results on the M3 Ultra and a video now vs baseline using ds4-eval.
0:42

DwarfStar DeepSeek v4 Flash 0731 pre-M5 kernel keeps improving 💪🏻 - prefill +11% - decode +10% - single request no DSpark/MTP. - 100% same logics between baseline and now. Today is QA like crazy. I hope to file PR by EOD antirez Here are results on the M3 Ultra and a video now vs baseline using ds4-eval.

Ivan Fioravanti ᯅ

17,121 просмотров • 4 дней назад

holy sh*t this is f**king insane I cancelled my $200/mo Claude for this I replaced opus 5 with deepseek v4-flash and someone figured out to how to use them as subagents on codex [it takes 3 mins to set up here is how] 1. install this repo called 'model-router' 2. toggle subagent models > 'all selected models' 3. that's it
0:33

holy sh*t this is f**king insane I cancelled my $200/mo Claude for this I replaced opus 5 with deepseek v4-flash and someone figured out to how to use them as subagents on codex [it takes 3 mins to set up here is how] 1. install this repo called 'model-router' 2. toggle subagent models > 'all selected models' 3. that's it

Avid

376,227 просмотров • 4 дней назад

FREE DeepSeek V4 Pro and V4 Flash API. Runtime by Bad Theory Labs just dropped it. Same platform, new free model, same 2-minute setup. > Runtime already gave you free Claude Opus 4.8 and GPT 5.5 access. Now they added DeepSeek V4 Pro and V4 Flash to the free tier. Absolutely FREE, YES. Same exact flow as before: → Go to runtime(.)badtheorylabs(.)com → Sign up with Google → Fill in your details during onboarding → Free balance lands automatically(But you don't need it to use DeepSeek - it's completely free right now) → Grab your API key from the dashboard → Plug into OpenCode, OpenClaw, or Hermes - done DeepSeek V4 Pro is one of the strongest coding and reasoning models available right now. Free tier also includes btl-2 - auto-routes between GLM, OpenAI, Anthropic, and Gemma. 10 million tokens per month at zero cost. 344 models total. One OpenAI-compatible endpoint. No code rebuild, no card, no limits hunting. >> Just start using the API, and when choosing a provider, select DeepSeek I tested it myself - fully working. Bookmark this before the free tier fills up.
0:23

FREE DeepSeek V4 Pro and V4 Flash API. Runtime by Bad Theory Labs just dropped it. Same platform, new free model, same 2-minute setup. > Runtime already gave you free Claude Opus 4.8 and GPT 5.5 access. Now they added DeepSeek V4 Pro and V4 Flash to the free tier. Absolutely FREE, YES. Same exact flow as before: → Go to runtime(.)badtheorylabs(.)com → Sign up with Google → Fill in your details during onboarding → Free balance lands automatically(But you don't need it to use DeepSeek - it's completely free right now) → Grab your API key from the dashboard → Plug into OpenCode, OpenClaw, or Hermes - done DeepSeek V4 Pro is one of the strongest coding and reasoning models available right now. Free tier also includes btl-2 - auto-routes between GLM, OpenAI, Anthropic, and Gemma. 10 million tokens per month at zero cost. 344 models total. One OpenAI-compatible endpoint. No code rebuild, no card, no limits hunting. >> Just start using the API, and when choosing a provider, select DeepSeek I tested it myself - fully working. Bookmark this before the free tier fills up.

Atenov int.

26,920 просмотров • 1 месяц назад

deepseek-v4-flash 实战测评来了，真的便宜居然只花了不到6毛钱。对比kimi-k3 和opus-5 都得$10 起步，且需要差不多1 h ，而deepseek-v4-flash 只花了20多分钟 缺点来了：我感觉前端测评效果只能给到拉。。。 不过确实便宜我明天多测测，看看有没有惊喜
0:32

deepseek-v4-flash 实战测评来了，真的便宜居然只花了不到6毛钱。对比kimi-k3 和opus-5 都得$10 起步，且需要差不多1 h ，而deepseek-v4-flash 只花了20多分钟 缺点来了：我感觉前端测评效果只能给到拉。。。 不过确实便宜我明天多测测，看看有没有惊喜

岚叔

45,688 просмотров • 11 дней назад

qwen 3.8 max vs deepseek v4 flash 0731 vs kimi k3 vs gpt 5.6 sol – on rubik's cube and chess four frontier models built a rubik's cube stand and solved it, then built a chess board and played claude opus 5 on it the setup: Nous Research's hermes agent cli on OpenRouter tasks: 1. cube – build a 3d rubik's cube with a cli and a Three.js viewer, then solve an identical scrambled position on your own stand 2. chess – build a 3d chess stand, then play white against claude opus 5 as black, live, one move at a time. no engine, no solver, no opening book on either side. stockfish depth 14 grades every chess ply afterwards; neither player sees the score models: DeepSeek v4 flash 0731, OpenAI gpt-5.6 sol, Kimi.ai kimi k3, Qwen qwen 3.8 max gpt-5.6 sol and deepseek v4 flash solved their cubes – sol in 24 moves and seventeen seconds, deepseek in 32. qwen and kimi never got there, giving up at 96 and 207 moves then all four built chess stands and played white against claude opus 5 on them, and all four resigned: deepseek on move 13, sol on 19, kimi on 21, qwen holding out longest at 29 - build time, both stands #1 gpt-5.6 sol – 16m 43s #2 deepseek v4 flash – 97m 39s #3 kimi k3 – 166m 09s #4 qwen 3.8 max – 215m 08s - build attempts before a working stand #1 gpt-5.6 sol – 3 #2 qwen 3.8 max – 4 #3 kimi k3 – 4 #4 deepseek v4 flash – 5 - total tokens #1 gpt-5.6 sol – 6,713,754 #2 qwen 3.8 max – 17,272,507 #3 kimi k3 – 22,427,504 #4 deepseek v4 flash – 27,417,442 - total price #1 deepseek v4 flash – $0.557 #2 gpt-5.6 sol – $6.319 #3 qwen 3.8 max – $10.270 #4 kimi k3 – $16.667 observations: • deepseek v4 flash is the cheapest model here by a margin nobody else is near, and it got there while being the least efficient of the four. it burned 27.4m tokens – more than anyone, 5m more than kimi – and still finished both benchmarks for $0.557. that is $0.02 per million tokens against kimi's $0.74. it also needed the most passes to produce working stands, five, and that did not matter: all five deepseek passes together cost a thirtieth of kimi's two • so what deepseek cannot do is get it right the first time. what it can do is get it right the fifth time, for half a dollar. that is a different thing to be buying – not a good first draft, but the option to keep asking • gpt-5.6 sol is the opposite profile and the strongest of the four on pure efficiency. 16m 43s to build both stands, 6.7m tokens, three passes – under 40% of the next lowest token count and a quarter of deepseek's, on an eighth of qwen's clock. it also solved the cube fastest of anyone, 24 moves in seventeen seconds. sol is what you reach for when you want the answer now and can absorb $0.94 per million • sol's weakness is in what it does not check. its chess viewer deleted the capturing piece instead of the captured one, so pieces disappeared off the board mid-game – a defect the fifty-cent deepseek stand did not have. fast and terse turns out to be the same dial as fast and unverified • qwen 3.8 max is not the cheap open-weights option it gets treated as. $10.270 across the two benchmarks, second most expensive of the four, 18x deepseek, and by a distance the slowest – 215 minutes of build time, nearly thirteen times sol's. what the money buys is judgment: it played eighteen moves without a single error worth a hundredth of a pawn, then made exactly one bad move in the whole game, and averaged 44.6 centipawns lost across the longest game any of the four managed. it also could not solve a rubik's cube in 96 tries • kimi k3 is the one line with no reading that flatters it. most expensive at $16.667, last on the cube at 207 moves, last at chess at 478 centipawns lost per move. it is also the model that verified hardest – on the cube it wrote its own integrity check instead of trusting its output. that makes the result worse rather than better: the checking was real, and the reasoning underneath it still was not follow thehype. for 24/7 ai news, analysis and breakdowns
1:03

qwen 3.8 max vs deepseek v4 flash 0731 vs kimi k3 vs gpt 5.6 sol – on rubik's cube and chess four frontier models built a rubik's cube stand and solved it, then built a chess board and played claude opus 5 on it the setup: Nous Research's hermes agent cli on OpenRouter tasks: 1. cube – build a 3d rubik's cube with a cli and a Three.js viewer, then solve an identical scrambled position on your own stand 2. chess – build a 3d chess stand, then play white against claude opus 5 as black, live, one move at a time. no engine, no solver, no opening book on either side. stockfish depth 14 grades every chess ply afterwards; neither player sees the score models: DeepSeek v4 flash 0731, OpenAI gpt-5.6 sol, Kimi.ai kimi k3, Qwen qwen 3.8 max gpt-5.6 sol and deepseek v4 flash solved their cubes – sol in 24 moves and seventeen seconds, deepseek in 32. qwen and kimi never got there, giving up at 96 and 207 moves then all four built chess stands and played white against claude opus 5 on them, and all four resigned: deepseek on move 13, sol on 19, kimi on 21, qwen holding out longest at 29 - build time, both stands #1 gpt-5.6 sol – 16m 43s #2 deepseek v4 flash – 97m 39s #3 kimi k3 – 166m 09s #4 qwen 3.8 max – 215m 08s - build attempts before a working stand #1 gpt-5.6 sol – 3 #2 qwen 3.8 max – 4 #3 kimi k3 – 4 #4 deepseek v4 flash – 5 - total tokens #1 gpt-5.6 sol – 6,713,754 #2 qwen 3.8 max – 17,272,507 #3 kimi k3 – 22,427,504 #4 deepseek v4 flash – 27,417,442 - total price #1 deepseek v4 flash – $0.557 #2 gpt-5.6 sol – $6.319 #3 qwen 3.8 max – $10.270 #4 kimi k3 – $16.667 observations: • deepseek v4 flash is the cheapest model here by a margin nobody else is near, and it got there while being the least efficient of the four. it burned 27.4m tokens – more than anyone, 5m more than kimi – and still finished both benchmarks for $0.557. that is $0.02 per million tokens against kimi's $0.74. it also needed the most passes to produce working stands, five, and that did not matter: all five deepseek passes together cost a thirtieth of kimi's two • so what deepseek cannot do is get it right the first time. what it can do is get it right the fifth time, for half a dollar. that is a different thing to be buying – not a good first draft, but the option to keep asking • gpt-5.6 sol is the opposite profile and the strongest of the four on pure efficiency. 16m 43s to build both stands, 6.7m tokens, three passes – under 40% of the next lowest token count and a quarter of deepseek's, on an eighth of qwen's clock. it also solved the cube fastest of anyone, 24 moves in seventeen seconds. sol is what you reach for when you want the answer now and can absorb $0.94 per million • sol's weakness is in what it does not check. its chess viewer deleted the capturing piece instead of the captured one, so pieces disappeared off the board mid-game – a defect the fifty-cent deepseek stand did not have. fast and terse turns out to be the same dial as fast and unverified • qwen 3.8 max is not the cheap open-weights option it gets treated as. $10.270 across the two benchmarks, second most expensive of the four, 18x deepseek, and by a distance the slowest – 215 minutes of build time, nearly thirteen times sol's. what the money buys is judgment: it played eighteen moves without a single error worth a hundredth of a pawn, then made exactly one bad move in the whole game, and averaged 44.6 centipawns lost across the longest game any of the four managed. it also could not solve a rubik's cube in 96 tries • kimi k3 is the one line with no reading that flatters it. most expensive at $16.667, last on the cube at 207 moves, last at chess at 478 centipawns lost per move. it is also the model that verified hardest – on the cube it wrote its own integrity check instead of trusting its output. that makes the result worse rather than better: the checking was real, and the reasoning underneath it still was not follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

80,750 просмотров • 6 дней назад

I refuse to believe that I built this website from a single prompt for $0.82 using DeepSeek V4 Flash 0731. > cost: $0.82 > 20.2M tokens > 310 requests for transparency, I built the prompt using GPT Sol... its currently the best model for writing a very detailed prompt still absolutely ridiculous...this is with 0 polish, btw.. I can’t imagine how good it would look if I actually polished it..
0:31

I refuse to believe that I built this website from a single prompt for $0.82 using DeepSeek V4 Flash 0731. > cost: $0.82 > 20.2M tokens > 310 requests for transparency, I built the prompt using GPT Sol... its currently the best model for writing a very detailed prompt still absolutely ridiculous...this is with 0 polish, btw.. I can’t imagine how good it would look if I actually polished it..

JUMPERZ

63,860 просмотров • 9 дней назад

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry
0:38

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry

OmedTheVibeCoder

25,980 просмотров • 10 дней назад

实测对比Deepseek V4的真实性能！ Deepseek V4 pro VS GPT5.5 VS Claude Opus 4.7 ! 👇👇👇 时间戳： 00:00 开场 00:36 价格对比 00:51 1.软件官网 02:22 2.数字杂志 04:09 3.电商首页 05:33 前端能力总结 06:00 4. AI编程后端 10:12 5.自媒体文案 11:38 6.广告营销 12:56 最终总结
13:53

实测对比Deepseek V4的真实性能！ Deepseek V4 pro VS GPT5.5 VS Claude Opus 4.7 ! 👇👇👇 时间戳： 00:00 开场 00:36 价格对比 00:51 1.软件官网 02:22 2.数字杂志 04:09 3.电商首页 05:33 前端能力总结 06:00 4. AI编程后端 10:12 5.自媒体文案 11:38 6.广告营销 12:56 最终总结

木子不写代码

14,881 просмотров • 3 месяцев назад

hy3 vs mimo-v2.5 vs deepseek v4 flash vs minimax m3 the four models on top of the openrouter leaderboard by tokens this week: #1 hy3 (Tencent Hy) – 7.5t #2 mimo-v2.5 (Xiaomi MiMo) – 6.56t #3 deepseek v4 flash (DeepSeek) – 5.24t #4 minimax m3 (MiniMax (official)) – 4.21t so we tested them. 3 prompts, single-file html, Three.js from a cdn, fully procedural, no external assets. all run via AI/ML API each prompt is a transparent cutaway machine that has to be mechanically correct, not decorative: • 4-stroke engine with full oil circulation – slider-crank kinematics, cam at 2:1, valve lift driven by lobes, oil loop from sump to gallery to big-end • watt walking-beam steam engine – four-bar vector-loop closure, eccentric-driven slide valve, steam events synced to real port position • francis reaction water turbine – 20 guide vanes on a regulating ring, 17 lofted runner blades, gpu particle advection, precessing vortex rope at part load the takeaway up front: none of the four cleared all three scenes on the first attempt. but the price spread between them is roughly 70x – hy3 fixed included costs less than two cents overall results (summed across all 3 scenes): cost #1 hy3 – $0.016 #2 deepseek v4 flash – $0.025 #3 mimo-v2.5 – $0.97 #4 minimax m3 – $1.17 tokens #1 hy3 – 19,326 #2 deepseek v4 flash – 63,126 #3 mimo-v2.5 – 322,523 #4 minimax m3 – 702,900 lines of code #1 hy3 – 1,047 #2 mimo-v2.5 – 2,759 #3 deepseek v4 flash – 3,273 #4 minimax m3 – 3,354 scenes needing a second attempt #1 hy3 – 1 (engine) #1 mimo-v2.5 – 1 (turbine) #1 minimax m3 – 1 (turbine) #4 deepseek v4 flash – 2 (steam engine, turbine) observations: 1. the token spread is the real story – minimax burns 36x hy3's tokens and lands in the same place, one retry, ~3.3k lines 2. hy3 is the outlier on density: 1,047 lines total, fewest tokens, cheapest run, and only one scene needed a second pass. deepseek is the opposite trade – near-hy3 pricing but the most retries 3. mimo and minimax seem to overthink instead of writing the code. minimax spent 359.1k tokens on the steam engine and produced 1,346 lines – the tokens are going somewhere other than the file 4. the francis turbine broke three of the four. the spec that separates them is the one with 20 linked guide vanes and gpu particle advection, not the one with the most parts overall impression: none of these models excelled at any of the tasks we gave them. but they were close, and they were extremely cheap. the gap that matters isn't quality anymore – it's that hy3 ran all three scenes for less than two cents while the frontier labs charge dollars for the same work right now you pick these because they're good for the zero price you pay. soon that's something openai and anthropic will have to think about follow thehype. for 24/7 ai news, analysis and breakdowns
0:55

hy3 vs mimo-v2.5 vs deepseek v4 flash vs minimax m3 the four models on top of the openrouter leaderboard by tokens this week: #1 hy3 (Tencent Hy) – 7.5t #2 mimo-v2.5 (Xiaomi MiMo) – 6.56t #3 deepseek v4 flash (DeepSeek) – 5.24t #4 minimax m3 (MiniMax (official)) – 4.21t so we tested them. 3 prompts, single-file html, Three.js from a cdn, fully procedural, no external assets. all run via AI/ML API each prompt is a transparent cutaway machine that has to be mechanically correct, not decorative: • 4-stroke engine with full oil circulation – slider-crank kinematics, cam at 2:1, valve lift driven by lobes, oil loop from sump to gallery to big-end • watt walking-beam steam engine – four-bar vector-loop closure, eccentric-driven slide valve, steam events synced to real port position • francis reaction water turbine – 20 guide vanes on a regulating ring, 17 lofted runner blades, gpu particle advection, precessing vortex rope at part load the takeaway up front: none of the four cleared all three scenes on the first attempt. but the price spread between them is roughly 70x – hy3 fixed included costs less than two cents overall results (summed across all 3 scenes): cost #1 hy3 – $0.016 #2 deepseek v4 flash – $0.025 #3 mimo-v2.5 – $0.97 #4 minimax m3 – $1.17 tokens #1 hy3 – 19,326 #2 deepseek v4 flash – 63,126 #3 mimo-v2.5 – 322,523 #4 minimax m3 – 702,900 lines of code #1 hy3 – 1,047 #2 mimo-v2.5 – 2,759 #3 deepseek v4 flash – 3,273 #4 minimax m3 – 3,354 scenes needing a second attempt #1 hy3 – 1 (engine) #1 mimo-v2.5 – 1 (turbine) #1 minimax m3 – 1 (turbine) #4 deepseek v4 flash – 2 (steam engine, turbine) observations: 1. the token spread is the real story – minimax burns 36x hy3's tokens and lands in the same place, one retry, ~3.3k lines 2. hy3 is the outlier on density: 1,047 lines total, fewest tokens, cheapest run, and only one scene needed a second pass. deepseek is the opposite trade – near-hy3 pricing but the most retries 3. mimo and minimax seem to overthink instead of writing the code. minimax spent 359.1k tokens on the steam engine and produced 1,346 lines – the tokens are going somewhere other than the file 4. the francis turbine broke three of the four. the spec that separates them is the one with 20 linked guide vanes and gpu particle advection, not the one with the most parts overall impression: none of these models excelled at any of the tasks we gave them. but they were close, and they were extremely cheap. the gap that matters isn't quality anymore – it's that hy3 ran all three scenes for less than two cents while the frontier labs charge dollars for the same work right now you pick these because they're good for the zero price you pay. soon that's something openai and anthropic will have to think about follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

17,145 просмотров • 28 дней назад

New LFM2.5-2.6B hits DeepSeek-V4 level on tool calling and runs 3.7x faster! We ran Liquid AI 's new LFM2.5-2.6B against DeepSeek-V4-Flash on one box with 4x RTX 5090. Both got the same three jobs, and each one only completes if the model fires every tool call Topics: -weather and local time in six cities -one budget into six currencies -four hotels checked and booked for one date Outputs: LFM2.5-2.6B: 35/35 tool-calls, 366 tok/s, 19s DeepSeek-V4-Flash: 35/35 tool-calls, 77 tok/s, 70s Both models made all 35 calls, and both fired twelve of them in one turn. LFM was trained for agents, and tool calling is where that shows. Strong result for a model you can run right on your phone
0:25

New LFM2.5-2.6B hits DeepSeek-V4 level on tool calling and runs 3.7x faster! We ran Liquid AI 's new LFM2.5-2.6B against DeepSeek-V4-Flash on one box with 4x RTX 5090. Both got the same three jobs, and each one only completes if the model fires every tool call Topics: -weather and local time in six cities -one budget into six currencies -four hotels checked and booked for one date Outputs: LFM2.5-2.6B: 35/35 tool-calls, 366 tok/s, 19s DeepSeek-V4-Flash: 35/35 tool-calls, 77 tok/s, 70s Both models made all 35 calls, and both fired twelve of them in one turn. LFM was trained for agents, and tool calling is where that shows. Strong result for a model you can run right on your phone

atomic.chat

108,609 просмотров • 5 дней назад

SGLang now supports DSpark, enabling confidence-driven, variable-length verification for speculative decoding 🎉 DSpark addresses a key bottleneck under load: instead of verifying every draft token, it verifies only where the draft model is confident, so the gains hold even as batch size scales. We heavily optimized variable-length verification in SGLang. Across batch sizes 1 to 256, DSpark gives the best throughput/latency tradeoff on DeepSeek-V4-Flash, ahead of both MTP and non-spec. At high concurrency, dynamic scheduling provides up to ~20% higher throughput compared to a fixed budget, while maintaining high verification quality across workloads. With fused kernels and zero-overhead scheduling, DeepSeek-V4-Pro reaches 383.7 tok/s at B=1 on B300. DSpark is now available in SGLang with support for Qwen3 and DeepSeek-V4. Thanks DeepSeek for open-sourcing! Blog with full technical details and commands to run below 👇
0:33

SGLang now supports DSpark, enabling confidence-driven, variable-length verification for speculative decoding 🎉 DSpark addresses a key bottleneck under load: instead of verifying every draft token, it verifies only where the draft model is confident, so the gains hold even as batch size scales. We heavily optimized variable-length verification in SGLang. Across batch sizes 1 to 256, DSpark gives the best throughput/latency tradeoff on DeepSeek-V4-Flash, ahead of both MTP and non-spec. At high concurrency, dynamic scheduling provides up to ~20% higher throughput compared to a fixed budget, while maintaining high verification quality across workloads. With fused kernels and zero-overhead scheduling, DeepSeek-V4-Pro reaches 383.7 tok/s at B=1 on B300. DSpark is now available in SGLang with support for Qwen3 and DeepSeek-V4. Thanks DeepSeek for open-sourcing! Blog with full technical details and commands to run below 👇

LMSYS Org

169,398 просмотров • 1 месяц назад

NVIDIA is giving away free access to 130+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek-v4-flash, GPT-OSS-120B and 110+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "minimaxai/minimax-m2.7" model = "zhipuai/glm-5.1" model = "moonshot-ai/kimi-2.5" model = "deepseek-ai/deepseek-v4-flash" model = "nvidia/nemotron-3-ultra-550b-a55b" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free
0:38

NVIDIA is giving away free access to 130+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek-v4-flash, GPT-OSS-120B and 110+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "minimaxai/minimax-m2.7" model = "zhipuai/glm-5.1" model = "moonshot-ai/kimi-2.5" model = "deepseek-ai/deepseek-v4-flash" model = "nvidia/nemotron-3-ultra-550b-a55b" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free

Mr. Buzzoni

195,973 просмотров • 2 месяцев назад

HERMES DESKTOP APP JUST GOT A NEW ULTRA MODE FOR DEEPSEEK V4 PRO – AND IT COSTS ABOUT $1 A DAY TO RUN If you're using Hermes desktop app, you're probably already running DeepSeek – it's one of the top models available. The update: → DeepSeek V4 Pro now has thinking mode, fast mode, and a brand new ultra mode → There's also an extra high mode, but the real upgrade is ultra The actual cost: roughly $1/day for a normal workflow. That's about $20-25/month – basically the same as before, just with a significantly faster mode unlocked. The verdict after a full day of testing: it flies through tool calling. Noticeably faster, same price range. If you're already paying for DeepSeek through Hermes, this is a free upgrade sitting in your settings right now. Update Hermes, grab the DeepSeek API if you don't have it yet, and try V4 Pro on ultra. Bookmark this, you'll want to come back to it later.
1:00

HERMES DESKTOP APP JUST GOT A NEW ULTRA MODE FOR DEEPSEEK V4 PRO – AND IT COSTS ABOUT $1 A DAY TO RUN If you're using Hermes desktop app, you're probably already running DeepSeek – it's one of the top models available. The update: → DeepSeek V4 Pro now has thinking mode, fast mode, and a brand new ultra mode → There's also an extra high mode, but the real upgrade is ultra The actual cost: roughly $1/day for a normal workflow. That's about $20-25/month – basically the same as before, just with a significantly faster mode unlocked. The verdict after a full day of testing: it flies through tool calling. Noticeably faster, same price range. If you're already paying for DeepSeek through Hermes, this is a free upgrade sitting in your settings right now. Update Hermes, grab the DeepSeek API if you don't have it yet, and try V4 Pro on ultra. Bookmark this, you'll want to come back to it later.

SCOTTY BEAM

24,032 просмотров • 22 дней назад

Okay… DeepSeek V4 Flash actually COOKED 😭 With OpenCode, I’d place it around GPT-5.6 Terra Max—and definitely above Luna Max in this test. Almost unlimited usage for around €9, by the way. This model is a MASSIVE success. Just don’t use the wrong harness.
0:32

Okay… DeepSeek V4 Flash actually COOKED 😭 With OpenCode, I’d place it around GPT-5.6 Terra Max—and definitely above Luna Max in this test. Almost unlimited usage for around €9, by the way. This model is a MASSIVE success. Just don’t use the wrong harness.

OmedTheVibeCoder

35,417 просмотров • 10 дней назад