Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

🚨 DeepSeek V4 GA vs Fable 5 I gave both models the exact same 3D game generation prompt The results surprised me In my test, DeepSeek V4 GA produced the stronger output > Better environment generation > Stronger implementation > Excellent price-to-performance Which one do you prefer? 👇

Salio

3,858 subscribers

31,520 Aufrufe • vor 18 Tagen •via X (Twitter)

Wissenschaft & Technologie Gaming Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

I gave both Fable 5 and Opus 5 the exact same prompt: "Build an ultra-realistic flight simulator." The results weren't what I expected. Which one do you prefer?

I gave both Fable 5 and Opus 5 the exact same prompt: "Build an ultra-realistic flight simulator." The results weren't what I expected. Which one do you prefer?

Samuel Rondot

475,266 Aufrufe • vor 14 Tagen

🚨 Deepseek V4 pro GA is being tested to few users > this is the output on the same prompt that was used for kimi k3 and GPT sol 5.6 in the quoted video > The details are solid , addition of tents , campfire and everything this model looks promising

🚨 Deepseek V4 pro GA is being tested to few users > this is the output on the same prompt that was used for kimi k3 and GPT sol 5.6 in the quoted video > The details are solid , addition of tents , campfire and everything this model looks promising

Chetaslua

172,573 Aufrufe • vor 21 Tagen

🚨 More DeepSeek V4 Pro GA Leaks and it's looking seriously impressive. It also looks like DeepSeek may have heavily distilled from Fable 5 the coding style, iteration behavior, and overall output feel very similar. It was tested it on the same prompt used for Kimi K3 and GPT-5.6 Sol, and the result had strong scene composition, solid environmental detail, and surprisingly good design choices. Still early, but this could become one of the most disruptive coding models yet. 👀🔥 cc huangserva

🚨 More DeepSeek V4 Pro GA Leaks and it's looking seriously impressive. It also looks like DeepSeek may have heavily distilled from Fable 5 the coding style, iteration behavior, and overall output feel very similar. It was tested it on the same prompt used for Kimi K3 and GPT-5.6 Sol, and the result had strong scene composition, solid environmental detail, and surprisingly good design choices. Still early, but this could become one of the most disruptive coding models yet. 👀🔥 cc huangserva

WorldofAI

28,063 Aufrufe • vor 21 Tagen

Claude Fable 5 created this horror game with the same prompt we tested Fusion on. Do not fall for OpenRouters fraudulent marketing scheme. The capability of Fusion is NO WHERE close to that of Fable 5. Stringing together Opus 4.8, GPT 5.5, and DeepSeek V4 does not give you a better model. OpenRouter should be sued for false marketing.

Claude Fable 5 created this horror game with the same prompt we tested Fusion on. Do not fall for OpenRouters fraudulent marketing scheme. The capability of Fusion is NO WHERE close to that of Fable 5. Stringing together Opus 4.8, GPT 5.5, and DeepSeek V4 does not give you a better model. OpenRouter should be sued for false marketing.

BridgeMind

31,064 Aufrufe • vor 1 Monat

🚨 Deepseek V4 pro < api is sus> i have read multiple reports on x that it is routing to fable 5 , if it is right then we can see the jump in performance normal If it is not routing to fable 5 < quite impossible > then they made better model than kimi k3 , here is output

🚨 Deepseek V4 pro < api is sus> i have read multiple reports on x that it is routing to fable 5 , if it is right then we can see the jump in performance normal If it is not routing to fable 5 < quite impossible > then they made better model than kimi k3 , here is output

Chetaslua

99,585 Aufrufe • vor 20 Tagen

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.

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 Aufrufe • vor 1 Monat

🚨GPT 5.6 Pro vs Fable 5 this is the first real competition that cover game logic , ui , 3d aspects Fable 5 mogs 5.6 pro in every aspects watch video same prompt different results , no external assets used Thanks to pozitiv4ik for the prompt and test , follow him everyone😾

🚨GPT 5.6 Pro vs Fable 5 this is the first real competition that cover game logic , ui , 3d aspects Fable 5 mogs 5.6 pro in every aspects watch video same prompt different results , no external assets used Thanks to pozitiv4ik for the prompt and test , follow him everyone😾

Chetaslua

300,590 Aufrufe • vor 1 Monat

This is probably my most important post about DeepSeek V4 Flash. Do NOT judge this model after testing only one harness. Pi, Claude Code, and OpenCode produced dramatically different results—and OpenCode completely changed my verdict. You really need to read the details below.

This is probably my most important post about DeepSeek V4 Flash. Do NOT judge this model after testing only one harness. Pi, Claude Code, and OpenCode produced dramatically different results—and OpenCode completely changed my verdict. You really need to read the details below.

OmedTheVibeCoder

66,918 Aufrufe • vor 7 Tagen

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

Chris

250,405 Aufrufe • vor 1 Monat

I didn't expect DeepSeek v4 PRO (not Flash) to run well on the Mac Studio M3 Ultra with 512GB of RAM. This is 2 bit quantized with the same DwarfStar recipe used for Flash. 433GB GGUF file. 130 t/s prefill, 13 t/s generation. Prefill in the video is low because small prompt.

I didn't expect DeepSeek v4 PRO (not Flash) to run well on the Mac Studio M3 Ultra with 512GB of RAM. This is 2 bit quantized with the same DwarfStar recipe used for Flash. 433GB GGUF file. 130 t/s prefill, 13 t/s generation. Prefill in the video is low because small prompt.

antirez

171,478 Aufrufe • vor 2 Monaten

Your AI sucks. And it's not the model. It's you. "Make it better" isn't a prompt, it's a guessing game. I changed one step in my process and the output quality completely flipped. Same ideas, same models, totally different results.

Your AI sucks. And it's not the model. It's you. "Make it better" isn't a prompt, it's a guessing game. I changed one step in my process and the output quality completely flipped. Same ideas, same models, totally different results.

Flick

322,001 Aufrufe • vor 22 Tagen

Seedance 2.0 vs. Kling 3.0: Who delivers the most realistic emotional expressions? I put both models through the same test using one character, one reference image, and the exact same prompt. Each generated four emotions: anger, sadness, happiness, and disgust. Which AI video model handled the emotions better ?

Seedance 2.0 vs. Kling 3.0: Who delivers the most realistic emotional expressions? I put both models through the same test using one character, one reference image, and the exact same prompt. Each generated four emotions: anger, sadness, happiness, and disgust. Which AI video model handled the emotions better ?

FATHELA ESQ

38,646 Aufrufe • vor 1 Monat

MiniMax M3 is now available on AI/ML API! To test it, we asked several leading models to oneshot Doodle Jump from the scratch. The results ended up looking far closer than the price tags. MiniMax M3: $0.05 Qwen 3.7 Max: $0.08 DeepSeek V4 Pro: $0.10 GPT-5.5: $0.42 Curious which one you'd pick in a blind comparison. We also offer it 50% off for a limited time. Find docs, guides for setting it up & prompt below

MiniMax M3 is now available on AI/ML API! To test it, we asked several leading models to oneshot Doodle Jump from the scratch. The results ended up looking far closer than the price tags. MiniMax M3: $0.05 Qwen 3.7 Max: $0.08 DeepSeek V4 Pro: $0.10 GPT-5.5: $0.42 Curious which one you'd pick in a blind comparison. We also offer it 50% off for a limited time. Find docs, guides for setting it up & prompt below

AI/ML API

549,042 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 19 Tagen

GPT-5.6 Sol vs Fable 5. I put both through my hardest frontend test: a 3D globe dashboard. Same prompt. Same reference image. Sol on the left. Fable on the right. GPT-5.6 Sol is a major leap from 5.5. Fable 5 still wins on spacing, balance, and first-pass polish. For me, Sol comes close at half the cost.

GPT-5.6 Sol vs Fable 5. I put both through my hardest frontend test: a 3D globe dashboard. Same prompt. Same reference image. Sol on the left. Fable on the right. GPT-5.6 Sol is a major leap from 5.5. Fable 5 still wins on spacing, balance, and first-pass polish. For me, Sol comes close at half the cost.

Kai

198,439 Aufrufe • vor 29 Tagen

GLM-5.2 is legit. It produces games easily and as accurately as SOTA closed-source models. My GLM 5.2 versus Fable 5 comparison is close, but I prefer Fable 5 just a little. Both games are equal in nearly all respects, but Fable 5 produced slightly better graphics and more challenging gameplay. Both needed 2 shots to get all the prompt instructions correct.

GLM-5.2 is legit. It produces games easily and as accurately as SOTA closed-source models. My GLM 5.2 versus Fable 5 comparison is close, but I prefer Fable 5 just a little. Both games are equal in nearly all respects, but Fable 5 produced slightly better graphics and more challenging gameplay. Both needed 2 shots to get all the prompt instructions correct.

David Hendrickson

18,779 Aufrufe • vor 1 Monat

Before Claude Fable 5 got banned, I turned all my fine-tuning research and experiments into a product: (A CLI for data generation to fine-tune AI models). Finetuner uses Codex 5.5 or Opus 4.8 as the orchestrator and Chinese models (DeepSeek v4 Pro, Kimi K2.7, MiMo v2.5, etc.) to generate dataset rows. This system is unique because these are not Python-script-paraphrased datasets. Each and every row is handcrafted by Chinese models based on the orchestrator model's instructions. Now anyone can generate datasets to fine-tune small language models (1B to 30B models). I achieved 10x lower costs and 5x better dataset quality. Releasing the product in a few days. (I'll open-source the skills.)

Before Claude Fable 5 got banned, I turned all my fine-tuning research and experiments into a product: (A CLI for data generation to fine-tune AI models). Finetuner uses Codex 5.5 or Opus 4.8 as the orchestrator and Chinese models (DeepSeek v4 Pro, Kimi K2.7, MiMo v2.5, etc.) to generate dataset rows. This system is unique because these are not Python-script-paraphrased datasets. Each and every row is handcrafted by Chinese models based on the orchestrator model's instructions. Now anyone can generate datasets to fine-tune small language models (1B to 30B models). I achieved 10x lower costs and 5x better dataset quality. Releasing the product in a few days. (I'll open-source the skills.)

CJ Zafir

39,716 Aufrufe • vor 1 Monat

$China just made Silicon Valley's entire AI industry look like a scam. The US government spent 3 years trying to stop China from building competitive AI. But this backfired HORRIBLY. Here's what happened: Yesterday, a Chinese startup called DeepSeek released a new AI model called V4. It matches the performance of OpenAI and Anthropic's best models. At 1/7th the price. And for the first time ever, it was built on Chinese chips. NOT American ones. That last part is the one that terrifies the west. For context: Since 2022, the US has banned the export of advanced AI chips to China. The entire strategy was built on the assumption that if China can't access Nvidia's best hardware, they can't build frontier AI. But DeepSeek just proved that assumption wrong. Their V4 model was trained and runs on Huawei's Ascend chips. Huawei spent months working directly with DeepSeek to make sure V4 runs across their entire line of AI processors. Jensen Huang even predicted this on a recent podcast: "The day that DeepSeek comes out on Huawei first, that is a horrible outcome for our nation." That day was yesterday. And the numbers are crazy: DeepSeek V4 costs $3.48 per million output tokens. OpenAI's latest model GPT-5.5 costs $30. Anthropic's Claude charges $25. Same ballpark performance. 7x cheaper. Uber's CTO just admitted they burned through their ENTIRE 2026 AI budget in 4 months using Anthropic's tools. If Uber had used DeepSeek instead, that same budget would have lasted 7 YEARS. 4 months vs 7 years. Same work getting done. But the pricing isn't even the big thing here. The real story is what DeepSeek did with their technical report: They published the benchmarks where they LOSE. Every AI company cherry-picks the tests where their model wins. DeepSeek ran the full comparison against GPT-5.4 and Google's Gemini, found they trail frontier models by 3 to 6 months, and printed it anyway. They literally don't care because the price gap makes the performance gap irrelevant for 90% of use cases. So the US export controls didn't slow China down. They ACCELERATED China's independence. Because Chinese developers were FORCED to train models with limited resources, they had to figure out how to make AI radically more efficient. That constraint became their competitive advantage. Every generation of DeepSeek has gotten dramatically cheaper to train. V4 continues the trend. Meanwhile US companies are going the OPPOSITE direction: OpenAI's GPT-5.5 Pro costs $180 per million output tokens. That's 51x more expensive than DeepSeek V4 for comparable work. The Commerce Secretary confirmed this week that ZERO Nvidia advanced chip shipments have actually gone through to China despite being approved in January. So China built frontier AI anyway. Without American chips. At a fraction of the cost. And the market response tells you everything: Chinese chipmaker SMIC surged 10%. Huahong Semiconductor jumped 15%. DeepSeek's Chinese AI competitors Zhipu AI and MiniMax dropped 9% because V4 is destroying them too. DeepSeek is making Silicon Valley's pricing model look like a scam. US tech companies spent $650 billion on AI infrastructure this year. DeepSeek just showed the world you can match their output for pennies. The export controls were supposed to be America's ace card. Instead they taught China how to win without American chips, at American prices nobody can compete with. Jensen Huang was right. This is a horrible outcome. But it's the outcome America built for itself.$

China just made Silicon Valley's entire AI industry look like a scam. The US government spent 3 years trying to stop China from building competitive AI. But this backfired HORRIBLY. Here's what happened: Yesterday, a Chinese startup called DeepSeek released a new AI model called V4. It matches the performance of OpenAI and Anthropic's best models. At 1/7th the price. And for the first time ever, it was built on Chinese chips. NOT American ones. That last part is the one that terrifies the west. For context: Since 2022, the US has banned the export of advanced AI chips to China. The entire strategy was built on the assumption that if China can't access Nvidia's best hardware, they can't build frontier AI. But DeepSeek just proved that assumption wrong. Their V4 model was trained and runs on Huawei's Ascend chips. Huawei spent months working directly with DeepSeek to make sure V4 runs across their entire line of AI processors. Jensen Huang even predicted this on a recent podcast: "The day that DeepSeek comes out on Huawei first, that is a horrible outcome for our nation." That day was yesterday. And the numbers are crazy: DeepSeek V4 costs $3.48 per million output tokens. OpenAI's latest model GPT-5.5 costs $30. Anthropic's Claude charges $25. Same ballpark performance. 7x cheaper. Uber's CTO just admitted they burned through their ENTIRE 2026 AI budget in 4 months using Anthropic's tools. If Uber had used DeepSeek instead, that same budget would have lasted 7 YEARS. 4 months vs 7 years. Same work getting done. But the pricing isn't even the big thing here. The real story is what DeepSeek did with their technical report: They published the benchmarks where they LOSE. Every AI company cherry-picks the tests where their model wins. DeepSeek ran the full comparison against GPT-5.4 and Google's Gemini, found they trail frontier models by 3 to 6 months, and printed it anyway. They literally don't care because the price gap makes the performance gap irrelevant for 90% of use cases. So the US export controls didn't slow China down. They ACCELERATED China's independence. Because Chinese developers were FORCED to train models with limited resources, they had to figure out how to make AI radically more efficient. That constraint became their competitive advantage. Every generation of DeepSeek has gotten dramatically cheaper to train. V4 continues the trend. Meanwhile US companies are going the OPPOSITE direction: OpenAI's GPT-5.5 Pro costs $180 per million output tokens. That's 51x more expensive than DeepSeek V4 for comparable work. The Commerce Secretary confirmed this week that ZERO Nvidia advanced chip shipments have actually gone through to China despite being approved in January. So China built frontier AI anyway. Without American chips. At a fraction of the cost. And the market response tells you everything: Chinese chipmaker SMIC surged 10%. Huahong Semiconductor jumped 15%. DeepSeek's Chinese AI competitors Zhipu AI and MiniMax dropped 9% because V4 is destroying them too. DeepSeek is making Silicon Valley's pricing model look like a scam. US tech companies spent $650 billion on AI infrastructure this year. DeepSeek just showed the world you can match their output for pennies. The export controls were supposed to be America's ace card. Instead they taught China how to win without American chips, at American prices nobody can compete with. Jensen Huang was right. This is a horrible outcome. But it's the outcome America built for itself.

Ricardo

280,768 Aufrufe • vor 3 Monaten

The AI price war is ON. > DeepSeek just dropped V4 Flash 0731 (big capability jump, $0.28/M output) > OpenAI cut GPT-5.6 Luna by 80% to $1.20/M (OpenRouter is currently offering 50% off, bringing it to $0.60/M) Same budget tier now, so I ran both through 3 canvas tests: 🧊 Rubik's cube: DeepSeek nails every rotation. Luna's turns are buggy, stickers fly off mid-move. 🎆 Fireworks: both fine, but Luna lags hard when the burst explodes. 🖊️ Pen writing "Hello": neither is legible. DeepSeek's cursive is looser, but Luna gave up on animating, it rendered a static image. GPT-5.6 is great at coding — but IMO only on Sol. In the same pricing tier, DeepSeek clearly beats Luna.

The AI price war is ON. > DeepSeek just dropped V4 Flash 0731 (big capability jump, $0.28/M output) > OpenAI cut GPT-5.6 Luna by 80% to $1.20/M (OpenRouter is currently offering 50% off, bringing it to $0.60/M) Same budget tier now, so I ran both through 3 canvas tests: 🧊 Rubik's cube: DeepSeek nails every rotation. Luna's turns are buggy, stickers fly off mid-move. 🎆 Fireworks: both fine, but Luna lags hard when the burst explodes. 🖊️ Pen writing "Hello": neither is legible. DeepSeek's cursive is looser, but Luna gave up on animating, it rendered a static image. GPT-5.6 is great at coding — but IMO only on Sol. In the same pricing tier, DeepSeek clearly beats Luna.

stevibe

268,155 Aufrufe • vor 8 Tagen

A 3B model just cleared a puzzle that a 1.6 TRILLION param model couldn't. You've seen this benchmark before: my sliding-puzzle test. Same Kimi & DeepSeek runs as last time. The only new thing: I dropped VibeThinker-3B in for a side-by-side. > VibeThinker → 3B > DeepSeek V4 Flash → 284B > Kimi K2.6 → 1T > DeepSeek V4 Pro → 1.6T Shuffle depths 5, 10, 12, 15, 18, 22. One wrong move scrambles the whole board, so it's pure long-chain reasoning. ✅ VibeThinker-3B: solved all six. Never lost the thread. ⚠️ The giants started cracking at depth 15: Flash, Pro, and even Kimi each blew a run, scrambling the board past the move cap. As VibeThinker was not trained for tool calling, I had it emit X and ran the move. Bigger generalist ≠ smarter.

A 3B model just cleared a puzzle that a 1.6 TRILLION param model couldn't. You've seen this benchmark before: my sliding-puzzle test. Same Kimi & DeepSeek runs as last time. The only new thing: I dropped VibeThinker-3B in for a side-by-side. > VibeThinker → 3B > DeepSeek V4 Flash → 284B > Kimi K2.6 → 1T > DeepSeek V4 Pro → 1.6T Shuffle depths 5, 10, 12, 15, 18, 22. One wrong move scrambles the whole board, so it's pure long-chain reasoning. ✅ VibeThinker-3B: solved all six. Never lost the thread. ⚠️ The giants started cracking at depth 15: Flash, Pro, and even Kimi each blew a run, scrambling the board past the move cap. As VibeThinker was not trained for tool calling, I had it emit X and ran the move. Bigger generalist ≠ smarter.

stevibe

32,494 Aufrufe • vor 1 Monat