Загрузка видео...

Не удалось загрузить видео

На главную

Which AI model should you use for OpenClaw? 🤖 I tested the top models on WildClaw benchmarks—Claude Opus vs GPT-4 vs MiniMax vs the new GLM-5. The results might surprise you (spoiler: speed & cost matter more than you think)

boxmining's profile picture

Boxmining

175,858 subscribers

14,938 просмотров • 4 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Spending too much on Claude Opus for OpenClaw? We tested MiniMax (official) at $0.30 vs $5 per million tokens. It's 95% as good BUT you need these tricks to make it work. We break down exactly how to optimize it & save hundreds.
13:12

Spending too much on Claude Opus for OpenClaw? We tested MiniMax (official) at $0.30 vs $5 per million tokens. It's 95% as good BUT you need these tricks to make it work. We break down exactly how to optimize it & save hundreds.

Boxmining

37,999 просмотров • 5 месяцев назад

🚨 Claude Opus 4.7 just dropped (Claude) and we tested it so you don't have to. Spoiler: it's basically Opus 4.6 with a price hike. We ran the benchmarks. We built the games. We hit the rate limits. The results? Not what Anthropic promised. 👇 Watch the full breakdown before you upgrade:
18:02

🚨 Claude Opus 4.7 just dropped (Claude) and we tested it so you don't have to. Spoiler: it's basically Opus 4.6 with a price hike. We ran the benchmarks. We built the games. We hit the rate limits. The results? Not what Anthropic promised. 👇 Watch the full breakdown before you upgrade:

Boxmining

11,571 просмотров • 4 месяцев назад

1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5 We gave 3 models the same prompt and compared one-shot outputs. The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s. Which output do you like best? GGUF:
0:21

1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5 We gave 3 models the same prompt and compared one-shot outputs. The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s. Which output do you like best? GGUF:

Unsloth AI

1,541,778 просмотров • 1 месяц назад

How does the #1 open Text Arena model hold up in agentic coding tasks? We tested GLM-5 in Code Arena with head-to-head SVG prompts vs. top frontier AI models. What do you think? Scores for Z.ai 's GLM-5 in Code Arena coming soon. Test out GLM-5 for yourself and get voting.
0:52

How does the #1 open Text Arena model hold up in agentic coding tasks? We tested GLM-5 in Code Arena with head-to-head SVG prompts vs. top frontier AI models. What do you think? Scores for Z.ai 's GLM-5 in Code Arena coming soon. Test out GLM-5 for yourself and get voting.

Arena.ai

115,220 просмотров • 6 месяцев назад

CLAUDE SONNET 5 vs. CLAUDE OPUS 4.8 RESULTS Prompt: "build a single html landing page about claude sonnet 5, the new AI model that just dropped from Anthropic." Claude Sonnet 5: - Tokens Used: 20.9k input, 14.2k output - Total Cost: $3.36 - Time elapsed: 2m 11s Claude Opus 4.8 Ultracode: - Tokens Used: 96.3k input, 73.8k output - Total cost: $20.66 - Time Elapsed: 20m 15s I ran both of them in UltraCode mode via the CLI. I think in terms of quality of output, Opus won. In terms of model speed and cost, Sonnet 5 won. What are your thoughts? Comment down below who you think won!
0:25

CLAUDE SONNET 5 vs. CLAUDE OPUS 4.8 RESULTS Prompt: "build a single html landing page about claude sonnet 5, the new AI model that just dropped from Anthropic." Claude Sonnet 5: - Tokens Used: 20.9k input, 14.2k output - Total Cost: $3.36 - Time elapsed: 2m 11s Claude Opus 4.8 Ultracode: - Tokens Used: 96.3k input, 73.8k output - Total cost: $20.66 - Time Elapsed: 20m 15s I ran both of them in UltraCode mode via the CLI. I think in terms of quality of output, Opus won. In terms of model speed and cost, Sonnet 5 won. What are your thoughts? Comment down below who you think won!

Mark Santos

325,900 просмотров • 1 месяц назад

Finally did the "opus vs codex" video I've been thinking about for months. tl;dr - I use both every day, and I think you should too.
54:09

Finally did the "opus vs codex" video I've been thinking about for months. tl;dr - I use both every day, and I think you should too.

Theo - t3.gg

146,643 просмотров • 6 месяцев назад

MiniMax M3 vs GLM-5.2 vs Kimi K2.7 in Lunar Lander contest! 🔥 Last test of the day before going back to learning & build phase with Local Models, Swift and Apple Core AI 💪 I took the opportunity to test the MiniMax Code app for macOS. Video below speeded up. Followed by Lunar Lander implementation from the various models. My ranking: 🥇 GLM 5.2 🥈 MiniMax M3 🥉 Kimi K2.7 Coding Prompt and final results in this gist:
0:42

MiniMax M3 vs GLM-5.2 vs Kimi K2.7 in Lunar Lander contest! 🔥 Last test of the day before going back to learning & build phase with Local Models, Swift and Apple Core AI 💪 I took the opportunity to test the MiniMax Code app for macOS. Video below speeded up. Followed by Lunar Lander implementation from the various models. My ranking: 🥇 GLM 5.2 🥈 MiniMax M3 🥉 Kimi K2.7 Coding Prompt and final results in this gist:

Ivan Fioravanti ᯅ

21,604 просмотров • 2 месяцев назад

They did it. Claude Opus 5 is BETTER than Fable 5 and half the price It's the smartest model ever made Plus you can actually use it without draining your bank account In this video I cover the best use cases for Opus, when I still use Fable, and where GPT 5.6 still wins:
10:52

They did it. Claude Opus 5 is BETTER than Fable 5 and half the price It's the smartest model ever made Plus you can actually use it without draining your bank account In this video I cover the best use cases for Opus, when I still use Fable, and where GPT 5.6 still wins:

Alex Finn

42,266 просмотров • 23 дней назад

🤖 Not all AI models are built equal for Hermes Agent. After 1 month of testing MIMO V2 Pro, GPT 5.4, Kimi 2.5, DeepSeek 3.2 & more. We ranked every model by Orchestrator, Executor & Auxiliary roles. Save this before you pick your next model. 👇
24:39

🤖 Not all AI models are built equal for Hermes Agent. After 1 month of testing MIMO V2 Pro, GPT 5.4, Kimi 2.5, DeepSeek 3.2 & more. We ranked every model by Orchestrator, Executor & Auxiliary roles. Save this before you pick your next model. 👇

Boxmining

46,308 просмотров • 3 месяцев назад

Opus 4.8 vs GLM 5.2 everyone is praising Glm on my timeline, so i had to test it myself > both models were given the same prompt > GLM was super fast and used like 2% of my weekly limit > Opus took over 20 mins and used like 3% of weekly limits which one do you think won?
0:41

Opus 4.8 vs GLM 5.2 everyone is praising Glm on my timeline, so i had to test it myself > both models were given the same prompt > GLM was super fast and used like 2% of my weekly limit > Opus took over 20 mins and used like 3% of weekly limits which one do you think won?

J A Z I I

48,108 просмотров • 1 месяц назад

GPT-5.4 is my new default model for OpenClaw. For the last 2 months, Opus was the only model I felt could really unlock OpenClaw for serious agent tasks. GPT-5.4 is the first one that got close enough in quality to change that. In practice, it feels ~60% faster (73 tok/s vs 46), costs about half as much, and gives ~5x longer context. That combination makes OpenClaw much more snappy as a default. I tested it side by side against Opus 4.6 on deep research + slide generation, and the outputs are inspectable too. Full video below:
7:21

GPT-5.4 is my new default model for OpenClaw. For the last 2 months, Opus was the only model I felt could really unlock OpenClaw for serious agent tasks. GPT-5.4 is the first one that got close enough in quality to change that. In practice, it feels ~60% faster (73 tok/s vs 46), costs about half as much, and gives ~5x longer context. That combination makes OpenClaw much more snappy as a default. I tested it side by side against Opus 4.6 on deep research + slide generation, and the outputs are inspectable too. Full video below:

Quinn Leng

131,551 просмотров • 5 месяцев назад

Claude Opus (Claude) is ACTUALLY getting dumber. We ran benchmarks — it scored 40% on tests it designed itself. ChatGPT 4.5 crushed it at 63%. Anthropic is quietly throttling Opus to save compute for their next model. Here's the proof 👇
12:06

Claude Opus (Claude) is ACTUALLY getting dumber. We ran benchmarks — it scored 40% on tests it designed itself. ChatGPT 4.5 crushed it at 63%. Anthropic is quietly throttling Opus to save compute for their next model. Here's the proof 👇

Boxmining

66,404 просмотров • 4 месяцев назад

MiniMax H3 vs Seedance 2.0 — right inside Pollo AI. Same prompt, same settings, completely different results. The only variable? The model. MiniMax H3 delivers smoother, more natural motion, while Seedance 2.0 goes bold with a cinematic, high-impact feel. It proves that within Pollo AI, the model you choose shapes the final output just as much as the prompt itself. Can't wait for Seedance 2.5 to land on Pollo AI — which model would you pick for your next ad? 👇
0:30

MiniMax H3 vs Seedance 2.0 — right inside Pollo AI. Same prompt, same settings, completely different results. The only variable? The model. MiniMax H3 delivers smoother, more natural motion, while Seedance 2.0 goes bold with a cinematic, high-impact feel. It proves that within Pollo AI, the model you choose shapes the final output just as much as the prompt itself. Can't wait for Seedance 2.5 to land on Pollo AI — which model would you pick for your next ad? 👇

Lydia

57,997 просмотров • 10 дней назад

I just tested GLM 5.2, Claude opus 4.8, and GPT 5.5 to see which one could rebuild my personal site in that whimsical ascii style GLM 5.2 held its own and went toe to toe with the other 2 top tier models lowkey impressed, look at the hero section it built here
1:36

I just tested GLM 5.2, Claude opus 4.8, and GPT 5.5 to see which one could rebuild my personal site in that whimsical ascii style GLM 5.2 held its own and went toe to toe with the other 2 top tier models lowkey impressed, look at the hero section it built here

Ann Nguyen

33,577 просмотров • 1 месяц назад

So Alibaba has just released a coding plan with all the best open source models You’ve access to Qwen 3.5-Plus, Kimi K2.5, MiniMax M2.5, GLM-5, etc. And you can plug it to: - Claude Code (as I did) - OpenClaw - Codex - Cline… While being waaay cheaper than the paid plan of Codex, Claude & Cie. More below
0:36

So Alibaba has just released a coding plan with all the best open source models You’ve access to Qwen 3.5-Plus, Kimi K2.5, MiniMax M2.5, GLM-5, etc. And you can plug it to: - Claude Code (as I did) - OpenClaw - Codex - Cline… While being waaay cheaper than the paid plan of Codex, Claude & Cie. More below

Paul Couvert

88,333 просмотров • 5 месяцев назад

How to use 50+ API keys (models) for FREE on OpenClaw API??? - go to - login or register your account - click on "more models" - click on "use case" and select what you need it for - choose the model and open it - click on "view code" → "Generate API key" many models don't allow direct deploy, so use the "view code" button to generate API access basically Nvidia NIM gives you the ability to test almost any model from their list for FREE some of them are not worse than GPT 5.2 or Claude Opus 4.6, some might even perform better depending on the task how to understand if a model is efficient and compare it with others??? - go to - type the model name in search - click on "benchmarks" - you’ll see performance tests and rankings this way you can easily compare free models with paid ones of course there are RPM limits, on many models it’s around ~40 requests per minute each model is different, after generating the API key, RPM limits are shown in the top-right corner nothing stops you from using them, many work perfectly fine, super solid option for first tests and for learning OpenClaw or any other system where you need an AI API model
1:54

How to use 50+ API keys (models) for FREE on OpenClaw API??? - go to - login or register your account - click on "more models" - click on "use case" and select what you need it for - choose the model and open it - click on "view code" → "Generate API key" many models don't allow direct deploy, so use the "view code" button to generate API access basically Nvidia NIM gives you the ability to test almost any model from their list for FREE some of them are not worse than GPT 5.2 or Claude Opus 4.6, some might even perform better depending on the task how to understand if a model is efficient and compare it with others??? - go to - type the model name in search - click on "benchmarks" - you’ll see performance tests and rankings this way you can easily compare free models with paid ones of course there are RPM limits, on many models it’s around ~40 requests per minute each model is different, after generating the API key, RPM limits are shown in the top-right corner nothing stops you from using them, many work perfectly fine, super solid option for first tests and for learning OpenClaw or any other system where you need an AI API model

Ronin

58,846 просмотров • 5 месяцев назад

🧵 Here’s a comparison of @Grok Imagine vs Anoncoin - the top 2 AI video models on X. Spoiler: one still has a long way to catch up. Elon Musk what do you think?
0:30

🧵 Here’s a comparison of @Grok Imagine vs Anoncoin - the top 2 AI video models on X. Spoiler: one still has a long way to catch up. Elon Musk what do you think?

Anoncoin

13,016 просмотров • 11 месяцев назад

SEEDANCE 2 vs FAST vs MINI Seedance 2.0 mini just went live on CapCut and I tested the exact same storyboard for reference and prompt to see which one performs best. And the difference is actually crazy 😳 Which one do you think came out on top? 👀 #CapcutSeedance2
0:45

SEEDANCE 2 vs FAST vs MINI Seedance 2.0 mini just went live on CapCut and I tested the exact same storyboard for reference and prompt to see which one performs best. And the difference is actually crazy 😳 Which one do you think came out on top? 👀 #CapcutSeedance2

MrDejie

133,840 просмотров • 2 месяцев назад

The first real evidence that the days of LLM Scaling laws are over. Introducing SCOPE: the world's most efficient Neural Planner. 🔍📊 We tested SCOPE vs Frontier LLMs for planning tasks on TextCraft (text version of Minecraft) and here are the results: ⤵️ - SCOPE Runs 55x faster than GPT 3.5 (3 seconds vs 164 seconds) - SCOPE is 160,000 smaller than GPT 4o (11M parameters vs 1.8T parameters) - SCOPE is more accurate on Planning tasks (56%) than frontier LLM models The age of efficient AI models starts now. 🔗📌 Read the full write up here:
1:06

The first real evidence that the days of LLM Scaling laws are over. Introducing SCOPE: the world's most efficient Neural Planner. 🔍📊 We tested SCOPE vs Frontier LLMs for planning tasks on TextCraft (text version of Minecraft) and here are the results: ⤵️ - SCOPE Runs 55x faster than GPT 3.5 (3 seconds vs 164 seconds) - SCOPE is 160,000 smaller than GPT 4o (11M parameters vs 1.8T parameters) - SCOPE is more accurate on Planning tasks (56%) than frontier LLM models The age of efficient AI models starts now. 🔗📌 Read the full write up here:

Skyfall AI

49,052 просмотров • 7 месяцев назад

I couldn't believe the results of this benchmarking test. I blind-tested 6 frontier models — Sonnet 5, Opus 4.8, Fable 5, GPT 5.5, GLM 5.2, and Kimi 2.5 — on knowledge work, not engineering. Writing. Analysis. Design. Vibe coding. Subagent simulations. The stuff we actually do all day. Same prompts, each model running its own subagent, every output graded blind before the labels were revealed. The results: → GLM 5.2 (the dirt-cheap open-source model from China) took first → Sonnet 5 took second, beating Fable 5 for knowledge work → Opus 4.8 got whooped Then I had Composer 2.5 judge every output independently — and it picked Fable 5 almost across the board. My blind picks and the AI judge completely disagreed. Full breakdown, method, and prompts in the video below. Which model are you running as your daily driver right now?
18:49

I couldn't believe the results of this benchmarking test. I blind-tested 6 frontier models — Sonnet 5, Opus 4.8, Fable 5, GPT 5.5, GLM 5.2, and Kimi 2.5 — on knowledge work, not engineering. Writing. Analysis. Design. Vibe coding. Subagent simulations. The stuff we actually do all day. Same prompts, each model running its own subagent, every output graded blind before the labels were revealed. The results: → GLM 5.2 (the dirt-cheap open-source model from China) took first → Sonnet 5 took second, beating Fable 5 for knowledge work → Opus 4.8 got whooped Then I had Composer 2.5 judge every output independently — and it picked Fable 5 almost across the board. My blind picks and the AI judge completely disagreed. Full breakdown, method, and prompts in the video below. Which model are you running as your daily driver right now?

JJ Englert

10,737 просмотров • 1 месяц назад