Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

PROOF same model, same effort, same provider, same codebase, same prompt claude code vs pi + fff extension vs opencode 0.17.3

neogoose_btw's profile picture

Dmitriy Kovalenko

19,254 subscribers

614,488 Aufrufe • vor 4 Monaten •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

music model battle Suno (v6) vs ElevenLabs (Music v2) > same prompt > same lyrics > same settings vote for your favorite 👇
1:23

music model battle Suno (v6) vs ElevenLabs (Music v2) > same prompt > same lyrics > same settings vote for your favorite 👇

Matthieu

15,926 Aufrufe • vor 1 Monat

Perfect demonstration of how the harness affects results. - The exact same model - The exact same prompt (both one shot) - The exact same provider w/ same quant - Even the same system prompt The only difference is the harness. *Everyone* underestimates the harness.
0:54

Perfect demonstration of how the harness affects results. - The exact same model - The exact same prompt (both one shot) - The exact same provider w/ same quant - Even the same system prompt The only difference is the harness. *Everyone* underestimates the harness.

Justin Schroeder

80,590 Aufrufe • vor 1 Monat

Kimi K2.5 - Same Prompt - OpenCode vs KIMI CLI vs Claude Code, any differences? 🤔 Create a single-page website for "PHANTOM PROTOCOL" a fictional tactical shooter video game. Design capabilities of this model are out of scale! 🥇 Final results at the end of the video. 🧵
1:20

Kimi K2.5 - Same Prompt - OpenCode vs KIMI CLI vs Claude Code, any differences? 🤔 Create a single-page website for "PHANTOM PROTOCOL" a fictional tactical shooter video game. Design capabilities of this model are out of scale! 🥇 Final results at the end of the video. 🧵

Ivan Fioravanti ᯅ

44,652 Aufrufe • vor 8 Monaten

Can an open-weight coding agent + harness match Claude Code at training a domain-specific model? Same one-line prompt. ~13 min e2e. Pushed to Hugging Face. Pi + @moonshotai Kimi K2.6 vs Claude Code + Opus 4.7. Task: classify NC session laws (1866-1967) as Jim Crow or not
4:48

Can an open-weight coding agent + harness match Claude Code at training a domain-specific model? Same one-line prompt. ~13 min e2e. Pushed to Hugging Face. Pi + @moonshotai Kimi K2.6 vs Claude Code + Opus 4.7. Task: classify NC session laws (1866-1967) as Jim Crow or not

Daniel van Strien

75,883 Aufrufe • vor 5 Monaten

2022 vs 2025 Same script , Same vachan
0:27

2022 vs 2025 Same script , Same vachan

खुरपेंच

39,732 Aufrufe • vor 11 Monaten

GPT Astra vs GPT-6.1 Sol vs Sonnet 5.5 vs Opus 5.5. Which AI understands 3D best? I gave all four the exact same task: build an AK-47 from scratch. Same prompt. Same environment. Which one wins?
0:21

GPT Astra vs GPT-6.1 Sol vs Sonnet 5.5 vs Opus 5.5. Which AI understands 3D best? I gave all four the exact same task: build an AK-47 from scratch. Same prompt. Same environment. Which one wins?

Luckey Faraday

68,151 Aufrufe • vor 13 Tagen

iPhone vs Xiaomi. Looks same same but different
0:55

iPhone vs Xiaomi. Looks same same but different

Elodie Brielle

1,657,943 Aufrufe • vor 8 Monaten

iPhone vs Xiaomi. Looks same same but different
0:55

iPhone vs Xiaomi. Looks same same but different

Didi

2,994,133 Aufrufe • vor 10 Monaten

Claude Code vs Agent Zero, same model: Claude Opus 5 High, released yesterday. Build a working Web OS from scratch. Terminal, apps, two games. Claude Code: 9:58, 80.3k tokens Agent Zero: 11:34, 59.7k tokens That's 26% fewer tokens for the same result. Full test at the end
3:42

Claude Code vs Agent Zero, same model: Claude Opus 5 High, released yesterday. Build a working Web OS from scratch. Terminal, apps, two games. Claude Code: 9:58, 80.3k tokens Agent Zero: 11:34, 59.7k tokens That's 26% fewer tokens for the same result. Full test at the end

Agent Zero

847,203 Aufrufe • vor 2 Monaten

Game 70 vs Cleveland Guardians- Same old, same old
4:37

Game 70 vs Cleveland Guardians- Same old, same old

Chris Castellani

41,929 Aufrufe • vor 4 Monaten

Gemini 4 Argon vs Claude Sonnet 5.5 vs Gpt 6 Astra vs Opus 5.5 Same prompt: "Build a night train." What do you guys think? 👀
0:25

Gemini 4 Argon vs Claude Sonnet 5.5 vs Gpt 6 Astra vs Opus 5.5 Same prompt: "Build a night train." What do you guys think? 👀

Tony

48,847 Aufrufe • vor 4 Tagen

I'm becoming a real Droid fan now! Here we have Calude Code vs Droid in Lego San Andreas glm-5-turbo edition! - 0-shot - same prompt, same model, same reasoning - stealing vehicle doesn't work in cc version - time of the day simulated in Droid version! Look at the image! 🤯
1:00

I'm becoming a real Droid fan now! Here we have Calude Code vs Droid in Lego San Andreas glm-5-turbo edition! - 0-shot - same prompt, same model, same reasoning - stealing vehicle doesn't work in cc version - time of the day simulated in Droid version! Look at the image! 🤯

Ivan Fioravanti ᯅ

17,953 Aufrufe • vor 7 Monaten

FIRST MODEL I MADE VS LATEST MODEL! same exact camera inputs
0:36

FIRST MODEL I MADE VS LATEST MODEL! same exact camera inputs

Pipi 🦇💀

83,897 Aufrufe • vor 11 Monaten

Lombard vs Volpe same play same positioning … the difference tho #yankees
0:40

Lombard vs Volpe same play same positioning … the difference tho #yankees

JoezMcfly🇩🇴

205,063 Aufrufe • vor 2 Monaten

Sonnet 5.5 vs Sol 6 on same prompts same price point
2:08

Sonnet 5.5 vs Sol 6 on same prompts same price point

Chetaslua

157,525 Aufrufe • vor 21 Tagen

Same task, same robot, same prompt. One run is approved. The other is rejected. That difference is what decides whether a model learns anything.
1:04

Same task, same robot, same prompt. One run is approved. The other is rejected. That difference is what decides whether a model learns anything.

PrismaX

12,815 Aufrufe • vor 2 Monaten

Nah, this can’t be real. Same GPT-5.6 Sol. Same task. Same thinking level. I switched from regular Codex to the Claude Code harness, and the result instantly became way better. Claude Code is somehow making every model cook. GPT-5.6 SOL WAS ALREADY TOP TIER!! 😭
0:33

Nah, this can’t be real. Same GPT-5.6 Sol. Same task. Same thinking level. I switched from regular Codex to the Claude Code harness, and the result instantly became way better. Claude Code is somehow making every model cook. GPT-5.6 SOL WAS ALREADY TOP TIER!! 😭

OmedTheVibeCoder

127,040 Aufrufe • vor 2 Monaten

stop shipping sloppy ui... no one likes it i used the same prompt. same model. right one used appllama mcp + skills prompt ↓
0:34

stop shipping sloppy ui... no one likes it i used the same prompt. same model. right one used appllama mcp + skills prompt ↓

jaimin

42,386 Aufrufe • vor 27 Tagen

lee jiwoo same same but different nov 2021 (16yo) vs december 2025 (20yo)
0:24

lee jiwoo same same but different nov 2021 (16yo) vs december 2025 (20yo)

reebam

111,341 Aufrufe • vor 9 Monaten