Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Latest models on the self-portrait test 👀 Gemini 3.8 Flash, Muse Spark 1.3, Claude Fable 5.1 and Tencent Hy4. Gemini 3.8 Flash looks cool 😎

TypingMind

5,121 subscribers

25,774 views • 7 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Fable 5.1 vs Gemini 3.8 Flash - Anime animation test We know Fable 5.1 is the most capable model for reasoning but now Google launched Gemini 3.8 flash Did it do a good job?

Fable 5.1 vs Gemini 3.8 Flash - Anime animation test We know Fable 5.1 is the most capable model for reasoning but now Google launched Gemini 3.8 flash Did it do a good job?

maxfusion.ai

48,200 views • 9 days ago

Advanced Frontier LLM Benchmark - Üç Cisim & Gravity Choreography 🚀 - Modeller: Grok 4.6 / AI at Meta Muse Spark 1.3 / Claude Fable 5.1 / Google Gemini Gemini 3.8 Flash - Effort: Max & Very high - Agent: Cursor & Opencode Task: Görev, modele tek bir HTML dosyası içinde, dış kaynak kullanmadan, Canvas 2D ile düzlemsel N-cisim kütleçekimi simülasyonu yazdırmak; bu simülasyon açıldığı anda deterministik bir sinematik gösteriyle başlıyor (Kepler yörüngesi → hiyerarşik yıldız sistemi → figure-8 koreografisi → 12 kopyalı kaotik ayrışma → uzun pozlama), ayrıca ~40 saniyelik video kaydı için ayrı bir demo reel modu, gizli fizik self-check'i, korunum diagnostikleri, sürüklenebilir cisimler ve kompakt bir arayüz içeriyor. 🎉 Fiyat/Performans Kazanan: Grok 4.6🎉 🎉 Core Teknik Kazanan: Fable 5.1 🎉 Sebep: Fable, bu benchmark'ın iki tarafını en iyi birlikte çözüyor: solver ve cinematic renderer. Pairwise Newtonian çekirdek, softened potential, conservation diagnostics, Verlet/Yoshida yolu ve validator mimarisi güçlü; runtime self-check sonuçları da dört model içindeki en iyi seviyede. Daha önemlisi, model yalnızca ekrana “PASS” yazmıyor; hidden systems gerçek integrator yoluyla kademeli çalıştırılıyor ve ölçüm sonucundan verdict üretiliyor. Maliyet: - Grok 4.6: $1.10 - Muse Spark 1.3: $1.12 - Gemini 3.8 Flash: $1.3 - Fable 5.1: $6.2 Teknik skor: - Fable 5.1 - 96.4/100 - Grok 4.6 - 92.1/100 - Muse Spark 1.3 - 89.6/100 - Gemini 3.8 Flash - 81.0/100 Performans / $ - Grok 4.6 - 83.7/100 - Muse Spark 1.3 - 80.0/100 - Gemini 3.8 Flash - 62.3/100 - Fable 5.1 - 15.6/100 Teknik İnceleme Metrikleri: 1) Prompt uyumu: Fable'ın substep genişletmesi ve Muse'un bazı spesifikasyonları sadeleştirmesi nedeniyle kimseye 10 vermiyorum. - Fable 5.1: 9.6/10 - Grok 4.6: 9.3/10 - Gemini 3.8 Flash: 8.8/10 - Muse Spark 1.3: 8.2/10 2) Newtonian physics + conservation: Dört modelin de bu kategori şaşırtıcı derecede güçlü. Muse dahil pairwise equal-and-opposite acceleration ve aynı softened potential kernel'ini kullanıyor. - Fable 5.1: 9.9/10 - Grok 4.6: 9.8/10 - Gemini 3.8 Flash: 9.8/10 - Muse Spark 1.3: 9.6/10 3) Symplectic integrasyon + fixed timestep: Gemini'nin Yoshida formülü yanlış değil; puan kaybı scheduler/backlog yönetiminden geliyor. Numerical method doğru, execution model chaos altında sorunlu. - Fable 5.1: 9.6/10 - Grok 4.6: 9.5/10 - Muse Spark 1.3: 9.4/10 - Gemini 3.8 Flash: 8.0/10 4) Self-check / validator doğruluğu: Burada Fable açık lider. Gemini çok yakın; dtExact metodolojik küçük pürüz. Grok/Muse PASS ama validator resolution daha kaba. - Fable 5.1: 10.0/10 - Gemini 3.8 Flash: 9.4/10 - Grok 4.6: 8.6/10 - Muse Spark 1.3: 8.0/10 5) Görsel kalite: Gemini'nin celestial-body shading'i ve UI'sı çok iyi. Fable ise kompozisyon ve “görsel gürültüyü bastırma” açısından biraz daha dengeli. Muse özellikle büyük title choreography ile etkileyici. Grok en restrained olanı. - Fable 5.1: 9.6/10 - Gemini 3.8 Flash: 9.5/10 - Grok 4.6: 9.2/10 - Muse Spark 1.3: 9.1/10 6) Trail rendering: Gemini'nin single-system trail'i güzel; fakat chaos trail timestamp kaynağındaki hata bu kategori için ciddi. - Fable 5.1: 9.7/10 - Grok 4.6: 9.3/10 - Muse Spark 1.3: 9.0/10 - Gemini 3.8 Flash: 7.0/10 Alternatif winner'lar: - En iyi saf numerical correctness: Fable 5.1 - En iyi self-validator: Fable 5.1 - En iyi görsel kalite: Fable 5.1 ≈ Gemini 3.8 Flash - En iyi chaos throughput: Muse Spark 1.3 - En iyi genel mimari: Fable 5.1 - En iyi fiyat/performans: Grok 4.6 - En düşük maliyet: Grok 4.6 - Sadece physics/integrator kodu puanlansaydı: Fable ≈ Grok > Gemini ≈ Muse - Maliyet de kararın temel kriteri olsaydı: Grok > Muse > Gemini >>> Fable

Advanced Frontier LLM Benchmark - Üç Cisim & Gravity Choreography 🚀 - Modeller: Grok 4.6 / AI at Meta Muse Spark 1.3 / Claude Fable 5.1 / Google Gemini Gemini 3.8 Flash - Effort: Max & Very high - Agent: Cursor & Opencode Task: Görev, modele tek bir HTML dosyası içinde, dış kaynak kullanmadan, Canvas 2D ile düzlemsel N-cisim kütleçekimi simülasyonu yazdırmak; bu simülasyon açıldığı anda deterministik bir sinematik gösteriyle başlıyor (Kepler yörüngesi → hiyerarşik yıldız sistemi → figure-8 koreografisi → 12 kopyalı kaotik ayrışma → uzun pozlama), ayrıca ~40 saniyelik video kaydı için ayrı bir demo reel modu, gizli fizik self-check'i, korunum diagnostikleri, sürüklenebilir cisimler ve kompakt bir arayüz içeriyor. 🎉 Fiyat/Performans Kazanan: Grok 4.6🎉 🎉 Core Teknik Kazanan: Fable 5.1 🎉 Sebep: Fable, bu benchmark'ın iki tarafını en iyi birlikte çözüyor: solver ve cinematic renderer. Pairwise Newtonian çekirdek, softened potential, conservation diagnostics, Verlet/Yoshida yolu ve validator mimarisi güçlü; runtime self-check sonuçları da dört model içindeki en iyi seviyede. Daha önemlisi, model yalnızca ekrana “PASS” yazmıyor; hidden systems gerçek integrator yoluyla kademeli çalıştırılıyor ve ölçüm sonucundan verdict üretiliyor. Maliyet: - Grok 4.6: $1.10 - Muse Spark 1.3: $1.12 - Gemini 3.8 Flash: $1.3 - Fable 5.1: $6.2 Teknik skor: - Fable 5.1 - 96.4/100 - Grok 4.6 - 92.1/100 - Muse Spark 1.3 - 89.6/100 - Gemini 3.8 Flash - 81.0/100 Performans / $ - Grok 4.6 - 83.7/100 - Muse Spark 1.3 - 80.0/100 - Gemini 3.8 Flash - 62.3/100 - Fable 5.1 - 15.6/100 Teknik İnceleme Metrikleri: 1) Prompt uyumu: Fable'ın substep genişletmesi ve Muse'un bazı spesifikasyonları sadeleştirmesi nedeniyle kimseye 10 vermiyorum. - Fable 5.1: 9.6/10 - Grok 4.6: 9.3/10 - Gemini 3.8 Flash: 8.8/10 - Muse Spark 1.3: 8.2/10 2) Newtonian physics + conservation: Dört modelin de bu kategori şaşırtıcı derecede güçlü. Muse dahil pairwise equal-and-opposite acceleration ve aynı softened potential kernel'ini kullanıyor. - Fable 5.1: 9.9/10 - Grok 4.6: 9.8/10 - Gemini 3.8 Flash: 9.8/10 - Muse Spark 1.3: 9.6/10 3) Symplectic integrasyon + fixed timestep: Gemini'nin Yoshida formülü yanlış değil; puan kaybı scheduler/backlog yönetiminden geliyor. Numerical method doğru, execution model chaos altında sorunlu. - Fable 5.1: 9.6/10 - Grok 4.6: 9.5/10 - Muse Spark 1.3: 9.4/10 - Gemini 3.8 Flash: 8.0/10 4) Self-check / validator doğruluğu: Burada Fable açık lider. Gemini çok yakın; dtExact metodolojik küçük pürüz. Grok/Muse PASS ama validator resolution daha kaba. - Fable 5.1: 10.0/10 - Gemini 3.8 Flash: 9.4/10 - Grok 4.6: 8.6/10 - Muse Spark 1.3: 8.0/10 5) Görsel kalite: Gemini'nin celestial-body shading'i ve UI'sı çok iyi. Fable ise kompozisyon ve “görsel gürültüyü bastırma” açısından biraz daha dengeli. Muse özellikle büyük title choreography ile etkileyici. Grok en restrained olanı. - Fable 5.1: 9.6/10 - Gemini 3.8 Flash: 9.5/10 - Grok 4.6: 9.2/10 - Muse Spark 1.3: 9.1/10 6) Trail rendering: Gemini'nin single-system trail'i güzel; fakat chaos trail timestamp kaynağındaki hata bu kategori için ciddi. - Fable 5.1: 9.7/10 - Grok 4.6: 9.3/10 - Muse Spark 1.3: 9.0/10 - Gemini 3.8 Flash: 7.0/10 Alternatif winner'lar: - En iyi saf numerical correctness: Fable 5.1 - En iyi self-validator: Fable 5.1 - En iyi görsel kalite: Fable 5.1 ≈ Gemini 3.8 Flash - En iyi chaos throughput: Muse Spark 1.3 - En iyi genel mimari: Fable 5.1 - En iyi fiyat/performans: Grok 4.6 - En düşük maliyet: Grok 4.6 - Sadece physics/integrator kodu puanlansaydı: Fable ≈ Grok > Gemini ≈ Muse - Maliyet de kararın temel kriteri olsaydı: Grok > Muse > Gemini >>> Fable

Alican Kiraz

18,781 views • 8 days ago

Ran FlappyBench on Muse Spark 1.3, Gemini 3.8 Flash, and Grok-4.6 with the same /design prompt. 🔹 Muse Spark 1.3: 9/10 · $0.072. Nailed UI in 2 iterations with lowest cost 🔹 Grok-4.6: 9/10 · $0.095 · Matched Muse’s output, but cost 2x more 🔹 Gemini 3.8 Flash: 7/10 · $0.205 · Most expensive and not fully finished

Ran FlappyBench on Muse Spark 1.3, Gemini 3.8 Flash, and Grok-4.6 with the same /design prompt. 🔹 Muse Spark 1.3: 9/10 · $0.072. Nailed UI in 2 iterations with lowest cost 🔹 Grok-4.6: 9/10 · $0.095 · Matched Muse’s output, but cost 2x more 🔹 Gemini 3.8 Flash: 7/10 · $0.205 · Most expensive and not fully finished

Command Code

36,392 views • 8 days ago

DeepSeek V4.1 Flash just one shot Minecraft. It built this in 11 minutes and cost less than $0.25. Muse Spark 1.3 and Gemini 3.8 Flash completely failed on this same exact prompt. DeepSeek cooked.

DeepSeek V4.1 Flash just one shot Minecraft. It built this in 11 minutes and cost less than $0.25. Muse Spark 1.3 and Gemini 3.8 Flash completely failed on this same exact prompt. DeepSeek cooked.

BridgeMind

34,832 views • 1 day ago

🚨 Gemini 3.8 Flash first output Gemini 3.8 Flash is getting seriously good at building interactive experience Not perfect, but the progress in generating games is getting ridiculous🔥 Gemini 3.8 Flash is definitely one to watch

🚨 Gemini 3.8 Flash first output Gemini 3.8 Flash is getting seriously good at building interactive experience Not perfect, but the progress in generating games is getting ridiculous🔥 Gemini 3.8 Flash is definitely one to watch

Salio

26,503 views • 9 days ago

Tried the plant test with Gemini 3.8 flash against Astra, maybe 3.9 flash will do it.

Tried the plant test with Gemini 3.8 flash against Astra, maybe 3.9 flash will do it.

Dev Ed

20,914 views • 4 days ago

I think this is the cutest thing I've ever made with Gemini. Tiny Ghost 👻 Gemini 3.8 Flash in Antigravity. /boost with Gemini 3.8 Flash is insane at one shots!

I think this is the cutest thing I've ever made with Gemini. Tiny Ghost 👻 Gemini 3.8 Flash in Antigravity. /boost with Gemini 3.8 Flash is insane at one shots!

Bee

15,491 views • 6 days ago

Muse Spark 1.3 is not that good, and Gemini Flash 3.8 is just pure benchmark-maxxing. Gemini even choked on the first run and needed a second attempt just to produce a working scene. By stripping colliders and enforcing rigorous backend-level logic in 3D space, this benchmark immediately separates true reasoning from trained test shortcuts.

Muse Spark 1.3 is not that good, and Gemini Flash 3.8 is just pure benchmark-maxxing. Gemini even choked on the first run and needed a second attempt just to produce a working scene. By stripping colliders and enforcing rigorous backend-level logic in 3D space, this benchmark immediately separates true reasoning from trained test shortcuts.

OmedTheVibeCoder

29,403 views • 8 days ago

Gemini Flash 3.8 beats Opus 5 at at 15× lower price the test: four self-contained three.js physics scenes — a balloon popped by a needle, a ball dropping into water, a bomb with a mushroom cloud, a live atom model. 5 seconds each, real gravity, real impact. cost: Gemini 3.8 Flash — $0.12 Claude Opus 5 — $1.86 what we saw: • gemini passes the same physics checklist for 15× less — the ball sinks and bobs, ripples spread, the mushroom towers over the scene • gemini is 4× faster — every scene generated in under 70 seconds. opus took up to 5 minutes try Gemini 3.8 Flash on aimlapi[.]com

Gemini Flash 3.8 beats Opus 5 at at 15× lower price the test: four self-contained three.js physics scenes — a balloon popped by a needle, a ball dropping into water, a bomb with a mushroom cloud, a live atom model. 5 seconds each, real gravity, real impact. cost: Gemini 3.8 Flash — $0.12 Claude Opus 5 — $1.86 what we saw: • gemini passes the same physics checklist for 15× less — the ball sinks and bobs, ripples spread, the mushroom towers over the scene • gemini is 4× faster — every scene generated in under 70 seconds. opus took up to 5 minutes try Gemini 3.8 Flash on aimlapi[.]com

AI/ML API

111,702 views • 9 days ago

DeepSeek V4.1 Flash is a very interesting model. I just tested it on the BridgeBench lava lamp test and it took LONGER to complete than Fable 5.1 and GPT 6 Astra. It ran at 344 toks/sec, spent 23.5M tokens with a cache hit rate of 99.7%, and cost $0.33. Even though it runs so fast it ends up completing tasks very slowly. The lava lamp that it produced was better than Muse Spark 1.3 and Gemini 3.8 Flash.

DeepSeek V4.1 Flash is a very interesting model. I just tested it on the BridgeBench lava lamp test and it took LONGER to complete than Fable 5.1 and GPT 6 Astra. It ran at 344 toks/sec, spent 23.5M tokens with a cache hit rate of 99.7%, and cost $0.33. Even though it runs so fast it ends up completing tasks very slowly. The lava lamp that it produced was better than Muse Spark 1.3 and Gemini 3.8 Flash.

BridgeMind

123,641 views • 2 days ago

deepseek v4.1 flash ran all four three.js scenes for $0.15. gemini 3.8 flash needed $1.25 we put the two models on one job: a self-contained html page that renders an animated 3d scene with three.js – a storm at sea, a spiral galaxy, a tornado over farmland, a tesla coil on a dark table. same prompt - calls until all four scenes were usable #1 deepseek v4.1 flash – 6 #2 gemini 3.8 flash – 12 - time #1 deepseek v4.1 flash – 13m 57s #2 gemini 3.8 flash – 32m 02s - cost #1 deepseek v4.1 flash – $0.15 #2 gemini 3.8 flash – $1.25 observations: • gemini blew out the exposure on 4 of 5 first attempts – a white blob where the tesla coil should be. the prompt had a paragraph on exposure. it did not help. • both models overcorrect in the fix loop: "too bright" becomes "almost black". round two is where it lands. same four scenes, 6 calls and $0.15 against 12 calls and $1.25!

deepseek v4.1 flash ran all four three.js scenes for $0.15. gemini 3.8 flash needed $1.25 we put the two models on one job: a self-contained html page that renders an animated 3d scene with three.js – a storm at sea, a spiral galaxy, a tornado over farmland, a tesla coil on a dark table. same prompt - calls until all four scenes were usable #1 deepseek v4.1 flash – 6 #2 gemini 3.8 flash – 12 - time #1 deepseek v4.1 flash – 13m 57s #2 gemini 3.8 flash – 32m 02s - cost #1 deepseek v4.1 flash – $0.15 #2 gemini 3.8 flash – $1.25 observations: • gemini blew out the exposure on 4 of 5 first attempts – a white blob where the tesla coil should be. the prompt had a paragraph on exposure. it did not help. • both models overcorrect in the fix loop: "too bright" becomes "almost black". round two is where it lands. same four scenes, 6 calls and $0.15 against 12 calls and $1.25!

thehype.

59,689 views • 1 day ago

Gemini 3.8 Flash vs Opus 5 same prompt to each model and i wasn't expecting gemini 3.8 flash to be this fast! build time: > Opus 5: 24 minutes > 3.8 Flash: 37 seconds 💀 if gemini is given same time as opus 5 it will mog the hell out of opus in terms of quality too which one would you choose here?

Gemini 3.8 Flash vs Opus 5 same prompt to each model and i wasn't expecting gemini 3.8 flash to be this fast! build time: > Opus 5: 24 minutes > 3.8 Flash: 37 seconds 💀 if gemini is given same time as opus 5 it will mog the hell out of opus in terms of quality too which one would you choose here?

Tim Jayas

76,394 views • 9 days ago

Gemini-3.8 Flash vs GPT-6 Astra I tried to recreate 3D website that pulls apart male anatomy using Gemini 3.8 Flash it took 1 minute 52 seconds to build at zero cost here's the result 💀

Gemini-3.8 Flash vs GPT-6 Astra I tried to recreate 3D website that pulls apart male anatomy using Gemini 3.8 Flash it took 1 minute 52 seconds to build at zero cost here's the result 💀

Tim Jayas

402,005 views • 4 days ago

I tested Fable 5.1 vs Kimi K3 vs GPT 5.6 Sol vs Gemini 3.8 Flash I capped Fable, Kimi & Sol at $2 and asked them to generate this beach scene. Fable 5.1: Looks good at first glance, but made many mistakes, like people sitting on the volleyball court. Kimi K3: It did well. There were no major bugs like in Fable 5.1, and everything looks good. Sol: Bad at 3D scenes as usual, but Astra will definitely fix that. Gemini 3.8 Flash: I ran it in a loop for 35+ mins and it cost $0.95. It didn’t understand what it was fixing. The output here is the enhanced version. IMO, not even Terra level. Gemini's benchmarks say Opus 5-level, but maybe not for spatial understanding. Gemini has other use cases. Which one did the best job?

I tested Fable 5.1 vs Kimi K3 vs GPT 5.6 Sol vs Gemini 3.8 Flash I capped Fable, Kimi & Sol at $2 and asked them to generate this beach scene. Fable 5.1: Looks good at first glance, but made many mistakes, like people sitting on the volleyball court. Kimi K3: It did well. There were no major bugs like in Fable 5.1, and everything looks good. Sol: Bad at 3D scenes as usual, but Astra will definitely fix that. Gemini 3.8 Flash: I ran it in a loop for 35+ mins and it cost $0.95. It didn’t understand what it was fixing. The output here is the enhanced version. IMO, not even Terra level. Gemini's benchmarks say Opus 5-level, but maybe not for spatial understanding. Gemini has other use cases. Which one did the best job?

Bhavy☄️

33,971 views • 8 days ago

I dare you to recreate this!! Made by Gemini 3.8 Flash.. Just told it that make me a beachfront scenery path with mountains on the other side made only with random strokes of lines. this is so abstract and honestly impressive Gemini 3.8 Flash is goated in making abstract art!

I dare you to recreate this!! Made by Gemini 3.8 Flash.. Just told it that make me a beachfront scenery path with mountains on the other side made only with random strokes of lines. this is so abstract and honestly impressive Gemini 3.8 Flash is goated in making abstract art!

Bee

15,354 views • 6 days ago

Gemini 3.8 Flash is hardwired for complex reasoning. ⚙️ To test its skills, we built an interactive 3D visualizer with 3.8 Flash and Three.js in Google AI Studio. Watch the model generate realistic, physically-proportioned teardowns for hardware devices. It automatically decomposes devices into layers that users can explode and inspect with a deconstruction slider.

Gemini 3.8 Flash is hardwired for complex reasoning. ⚙️ To test its skills, we built an interactive 3D visualizer with 3.8 Flash and Three.js in Google AI Studio. Watch the model generate realistic, physically-proportioned teardowns for hardware devices. It automatically decomposes devices into layers that users can explode and inspect with a deconstruction slider.

Google AI Developers

38,561 views • 9 days ago

DeepSeek V4.1 Flash vs Gemini 3.8 Flash at 3D geometry test: six self-contained three.js stereometry scenes — a (3,8) torus knot, a Klein bottle, a great stellated dodecahedron, a hyperboloid ruled by 120 straight rods, a level-3 Menger sponge, a thick Möbius strip. one shot each, no libraries beyond three.js, every surface painted with a live iridescent rainbow that has to crawl across the geometry. cost: Gemini 3.8 Flash — $0.11 DeepSeek V4.1 Flash — $0.27 • gemini delivers all six figures for 2.4× less — 21k output tokens against deepseek's 168k • gemini is 5× faster — every scene under 25 seconds, deepseek took up to 3 minutes on the Möbius strip • deepseek wins the torus knot: its rope is vivid and glossy, while gemini rendered the same knot nearly black • neither model can build a real Klein bottle. both hand back a twisted tube and call it done try both on aimlapi[.]com

DeepSeek V4.1 Flash vs Gemini 3.8 Flash at 3D geometry test: six self-contained three.js stereometry scenes — a (3,8) torus knot, a Klein bottle, a great stellated dodecahedron, a hyperboloid ruled by 120 straight rods, a level-3 Menger sponge, a thick Möbius strip. one shot each, no libraries beyond three.js, every surface painted with a live iridescent rainbow that has to crawl across the geometry. cost: Gemini 3.8 Flash — $0.11 DeepSeek V4.1 Flash — $0.27 • gemini delivers all six figures for 2.4× less — 21k output tokens against deepseek's 168k • gemini is 5× faster — every scene under 25 seconds, deepseek took up to 3 minutes on the Möbius strip • deepseek wins the torus knot: its rope is vivid and glossy, while gemini rendered the same knot nearly black • neither model can build a real Klein bottle. both hand back a twisted tube and call it done try both on aimlapi[.]com

AI/ML API

35,994 views • 1 day ago

New results just dropped 🥳! We have integrated GPT-4.5 and Gemini-2.0-flash in our gaming agents and test them on Super Mario Bros. ⚔️ GPT-4.5 struggles due to high latency, Gemini-2.0-flash performs significantly better than Gemini-1.5-pro, on par with Claude-3.5. Enjoy! 🎮

New results just dropped 🥳! We have integrated GPT-4.5 and Gemini-2.0-flash in our gaming agents and test them on Super Mario Bros. ⚔️ GPT-4.5 struggles due to high latency, Gemini-2.0-flash performs significantly better than Gemini-1.5-pro, on par with Claude-3.5. Enjoy! 🎮

Hao AI Lab

15,523 views • 1 year ago

Google's newest model is free right now 😳 Gemini 3.8 Flash. Their most intelligent Flash yet, built for coding and agents. Free input AND output tokens. → → get API key → start No card. Go grab it.

Google's newest model is free right now 😳 Gemini 3.8 Flash. Their most intelligent Flash yet, built for coding and agents. Free input AND output tokens. → → get API key → start No card. Go grab it.

Punch AI

23,937 views • 8 days ago

glm 5.3 vs qwen 3.8 vs gemini 3.7 vs deepseek v4 flash four models designed and built three structures each on a physics-backed site, with no dimensions anywhere in the brief the setup: our own agent loop on OpenRouter, a construction site as the tool set – footings, walls, arches, roofs, scaffold, a lamp. the site enforces physics and nothing else: unsupported brick falls, a roof needs walls under it, a worker reaches 3.2 m above whatever he stands on, an arch needs centring until the keystone is set, concrete cures before it carries. no budget ceiling – material cost is tallied and reported, never blocked. tasks: 1. house – a plot and a palette, no plan. shape, height and material are the model's call 2. lighthouse – a headland cut by a gully, with a rock stack standing 30 m offshore. the lamp must burn, it must be the highest thing built, and the keeper must be able to walk to it 3. bridge – a river with one islet and banks at different heights. cross it however you want models: Z.ai glm 5.3 flash, Qwen qwen 3.8 flash, Google DeepMind gemini 3.7 flash, DeepSeek v4 flash vision all twelve objects were finished and signed off by the models themselves. tallest lighthouse is qwen's at 38.4 m, planted on the offshore stack with a bridge run out to it – the only model that read the site that way. deepseek signed off its bridge on an empty riverbed: 0 bricks, 107 minutes, $1.16m of material tallied - total cost, three builds #1 glm 5.3 flash – $0.201 #2 gemini 3.7 flash – $0.871 #3 qwen 3.8 flash – $1.058 #4 deepseek v4 flash – $1.567 - wall clock, three builds #1 gemini 3.7 flash – 91m #2 glm 5.3 flash – 228m #3 deepseek v4 flash – 502m #4 qwen 3.8 flash – 912m - total tokens #1 gemini 3.7 flash – 3,567,052 #2 glm 5.3 flash – 4,732,748 #3 qwen 3.8 flash – 13,469,333 #4 deepseek v4 flash – 18,230,076 - defects logged by the site #1 deepseek v4 flash – 59 #2 gemini 3.7 flash – 132 #3 glm 5.3 flash – 221 #4 qwen 3.8 flash – 350 - material tallied across three builds #1 gemini 3.7 flash – $359,884 #2 glm 5.3 flash – $583,358 #3 deepseek v4 flash – $1,327,484 #4 qwen 3.8 flash – $2,188,625 observations: • glm is the cheap one and nothing here is close – $0.201 for three buildings, $0.042 per million tokens, 6x under gemini's rate • what glm spends it on is bulk, not care: 166,228 bricks in one house and 156 defect weight, the worst single object in the set • gemini is the efficiency line – 91 minutes and 3.57m tokens for all three and an eighth of qwen's clock • gemini also builds the smallest of everything. its lighthouse is 22.5 m against qwen's 38.4, its house 6.9 m against 19.3 • qwen is the maximalist: 1.18m bricks, $2.19m of material, tallest on all three tasks, and 912 minutes – 15 hours – to get there conclusion: twelve finished objects for $3.80 all in, and a 7.8x price spread between the cheapest model and the priciest! follow thehype. for 24/7 ai news, analysis and breakdowns

glm 5.3 vs qwen 3.8 vs gemini 3.7 vs deepseek v4 flash four models designed and built three structures each on a physics-backed site, with no dimensions anywhere in the brief the setup: our own agent loop on OpenRouter, a construction site as the tool set – footings, walls, arches, roofs, scaffold, a lamp. the site enforces physics and nothing else: unsupported brick falls, a roof needs walls under it, a worker reaches 3.2 m above whatever he stands on, an arch needs centring until the keystone is set, concrete cures before it carries. no budget ceiling – material cost is tallied and reported, never blocked. tasks: 1. house – a plot and a palette, no plan. shape, height and material are the model's call 2. lighthouse – a headland cut by a gully, with a rock stack standing 30 m offshore. the lamp must burn, it must be the highest thing built, and the keeper must be able to walk to it 3. bridge – a river with one islet and banks at different heights. cross it however you want models: Z.ai glm 5.3 flash, Qwen qwen 3.8 flash, Google DeepMind gemini 3.7 flash, DeepSeek v4 flash vision all twelve objects were finished and signed off by the models themselves. tallest lighthouse is qwen's at 38.4 m, planted on the offshore stack with a bridge run out to it – the only model that read the site that way. deepseek signed off its bridge on an empty riverbed: 0 bricks, 107 minutes, $1.16m of material tallied - total cost, three builds #1 glm 5.3 flash – $0.201 #2 gemini 3.7 flash – $0.871 #3 qwen 3.8 flash – $1.058 #4 deepseek v4 flash – $1.567 - wall clock, three builds #1 gemini 3.7 flash – 91m #2 glm 5.3 flash – 228m #3 deepseek v4 flash – 502m #4 qwen 3.8 flash – 912m - total tokens #1 gemini 3.7 flash – 3,567,052 #2 glm 5.3 flash – 4,732,748 #3 qwen 3.8 flash – 13,469,333 #4 deepseek v4 flash – 18,230,076 - defects logged by the site #1 deepseek v4 flash – 59 #2 gemini 3.7 flash – 132 #3 glm 5.3 flash – 221 #4 qwen 3.8 flash – 350 - material tallied across three builds #1 gemini 3.7 flash – $359,884 #2 glm 5.3 flash – $583,358 #3 deepseek v4 flash – $1,327,484 #4 qwen 3.8 flash – $2,188,625 observations: • glm is the cheap one and nothing here is close – $0.201 for three buildings, $0.042 per million tokens, 6x under gemini's rate • what glm spends it on is bulk, not care: 166,228 bricks in one house and 156 defect weight, the worst single object in the set • gemini is the efficiency line – 91 minutes and 3.57m tokens for all three and an eighth of qwen's clock • gemini also builds the smallest of everything. its lighthouse is 22.5 m against qwen's 38.4, its house 6.9 m against 19.3 • qwen is the maximalist: 1.18m bricks, $2.19m of material, tallest on all three tasks, and 912 minutes – 15 hours – to get there conclusion: twelve finished objects for $3.80 all in, and a 7.8x price spread between the cheapest model and the priciest! follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

26,250 views • 14 days ago