@shownotover

Benchmarking AI coding tools Claude, Codex, Gemini, and the rest Sharing real usage, resets, costs & news

 Europe
Joined July 2026
  • Tweets10.9K
  • Following2K
  • Followers4.1K
576Media
🚨 claude and codex users!! I asked OPUS 5.5 and GPT-6 ASTRA to make my own GTA hot pursuit 😂 Compared on a $200/month budget. Same one-shot prompt. I LOVE OPUS: the water, the chase, the variety. GPT-6 ASTRA (HIGH) vs OPUS 5.5 (HIGH) → Time: 23m39s vs 30m07s → TOTAL Tokens: 793K vs 3.27M Astra is STILL SLOW TPS (23.4 TPS vs OPUS 98.7 TPS) API COSTS would have been $5.40 for Astra vs $5.84 for Opus. Astra finished SOONER. OPUS made the BETTER looking one. YOU CAN DO ~100 similar runs per week with Claude. WEEKLY USAGE is 1.5% for Astra vs 1% for OPUS. Which one is better? What should we test next?
23
4
5
86
18,666
🚨 codex users!! Tibo gave another RESET for 10 AM PST 🔥 I still had 90% left!!! 😭 Here is YOUR timezone 👇 🇮🇳 India 11:30 PM 🇨🇳 China 2:00 AM 🇮🇩 Indonesia 1:00 AM 🇳🇬 Nigeria 7:00 PM 🇩🇪 Germany 7:00 PM
Tibo
@thsottiauxOct 22
Replying to @thsottiaux
Lands tomorrow before 10am PST.
16
5
2
47
21,018
🚨 Codex friends, Once AGAIN a RESET, like CLOCKWORK. Called it again 😂 I’ll ping when there’s a high chance of the next one in the next ~24 hours. What will you do with your limit, folks?
Tibo
@thsottiauxOct 17
Day 13/ Le limit reset
10
1
26
1,973
You do not need to be afraid of limits and costs anymore if you use DeepSeek... I am SHOCKED. xitter.cf/shownotover/status/211…
shownotover
@shownotoverOct 17
HOW the f*ck did DeepSeek just drop a model that’s better than OpenAI and way cheaper? 😂
1
2
294
HOW the f*ck did DeepSeek just drop a model that’s better than OpenAI and way cheaper? 😂
59
10
2
465
58,611
🚨 Codex friends, It seems like another RESET is COMING soon 😭 It’s MINDBLOWING how MANY we've gotten lately. Probably will get one in the next 24 hours or so. This time I am more prepared 🤺 How’s your WEEKLY looking right now, guys?
Tibo
@thsottiauxOct 16
Either we are out of ideas or we are cooking. Time will tell
41
4
1
138
38,948
This was maybe a tiny bit more than 24 hours, but still quite accurate. I hope you all used yours! I used mine quite nicely, and still maybe have a bit of time to BURN: 🔥🔥🔥 ENJOY fam! xitter.cf/shownotover/status/211…
shownotover
@shownotoverOct 17
🚨 Codex friends, Once AGAIN a RESET, like CLOCKWORK. Called it again 😂 I’ll ping when there’s a high chance of the next one in the next ~24 hours. What will you do with your limit, folks?
1
117
🚨 Gemini users and other friends! FINALLY, I’ve been waiting for this for a long time! Gemini ARGON is reachable from AntiGravity for PRO users 🎉 🚀 This should have happened OVERNIGHT. It was disabled yesterday I remember. Happy coding/testing everyone! And stay tuned for some of my own tests.
18
1
26
3,023
Did the comparison include antigravity? I do not see a BIG change (still not on par with OPUS) xitter.cf/shownotover/status/211…
shownotover
@shownotoverOct 17
🚨 Codex and Claude users!! ARGON vs OPUS 5.5: THE CLI REMATCH 👽🍔 SAME AS BEFORE: Aliens stop for burgers… then take the ENTIRE restaurant home 😂 Same prompt. Both HIGH. One initial prompt each. GEMINI ARGON — Antigravity CLI vs CLAUDE OPUS 5.5 — Claude Code (200USD plan both) → TIME: 26m04s vs 31m54s → TOKENS: 4.16M vs 5.35M → COST: ~$2.25 vs ~$6.63 → TPS: 76.0 vs 97.2 → WEEKLY: 2.25% vs Opus !!no visible change!!! Argon finished almost 6 minutes FASTER, lower API cost 👀 I STILL prefer OPUS’s visual quality… Which one tells the story better? The older Argon browser-chat result is at the bottom for visual comparison ONLY.
169
🚨 Codex and Claude users!! ARGON vs OPUS 5.5: THE CLI REMATCH 👽🍔 SAME AS BEFORE: Aliens stop for burgers… then take the ENTIRE restaurant home 😂 Same prompt. Both HIGH. One initial prompt each. GEMINI ARGON — Antigravity CLI vs CLAUDE OPUS 5.5 — Claude Code (200USD plan both) → TIME: 26m04s vs 31m54s → TOKENS: 4.16M vs 5.35M → COST: ~$2.25 vs ~$6.63 → TPS: 76.0 vs 97.2 → WEEKLY: 2.25% vs Opus !!no visible change!!! Argon finished almost 6 minutes FASTER, lower API cost 👀 I STILL prefer OPUS’s visual quality… Which one tells the story better? The older Argon browser-chat result is at the bottom for visual comparison ONLY.
14
2
23
4,684
🚨 CLAUDE AND GEMINI USERS!! 👽🍔 The story and the prompt: Aliens stop for burgers… but they LOVE the food on Earth too much 😂 A 15-second Three.js short. Both HIGH. GEMINI ARGON (browser chat) vs CLAUDE OPUS 5.5 (claude cli + toolings) → TIME: ~8–10 min vs 31m54s → TOKENS: Argon ~27.6K vs Opus 5.35M → API COST: Argon ~$0.92 vs Opus ~$6.63 → SPEED: Argon ~46–57 TPS vs Opus ~97.2 TPS WEEKLY: Argon was around ~1% vs Opus close to 0%!!! Argon finished around 3× FASTER, but I still like OPUS’s visual quality WAY more… We need a rematch in Antigravity when we poor Gemini Pro users get access to the CLI version 😂 Which one tells the story better? 👀 How do you like the new Gemini model?
29
2
3
44
6,810
Finally, we can do the same tests as Antigravity: xitter.cf/shownotover/status/211…
shownotover
@shownotoverOct 16
🚨 Gemini users and other friends! FINALLY, I’ve been waiting for this for a long time! Gemini ARGON is reachable from AntiGravity for PRO users 🎉 🚀 This should have happened OVERNIGHT. It was disabled yesterday I remember. Happy coding/testing everyone! And stay tuned for some of my own tests.
25
🚨 Codex users!!! WE GOT THE RESET from Tibo 🙏 100% again 😂 ♥️ Still had some left, BURNED it like CRAZY, and SHIPPED a new 3D engine + procedural gen. One of my better calls. Follow for more Codex, Claude, Gemini news + benchmarks. Appreciate you all 🙏
Tibo
@thsottiauxOct 15
Done and dusted
17
1
33
3,851
ok, another update; probably no reset for some time, to be fair: xitter.cf/shownotover/status/211…
shownotover
@shownotoverOct 15
🚨 Codex users!! Tibo just dropped Day 11 UPDATES. Pushed more compute and fixes, so the “model is at capacity” thing happens LESS. For me, this was NOT really an ISSUE; I might have been lucky with my timezone and location. Anyone still hitting it hard after this fix? Or is it actually better already? PS: Would you rather just get the resets than these capacity fixes? 😂 (no reset announcement from me this time tbh)
165
🚨 Codex users!! Tibo just dropped Day 11 UPDATES. Pushed more compute and fixes, so the “model is at capacity” thing happens LESS. For me, this was NOT really an ISSUE; I might have been lucky with my timezone and location. Anyone still hitting it hard after this fix? Or is it actually better already? PS: Would you rather just get the resets than these capacity fixes? 😂 (no reset announcement from me this time tbh)
Tibo
@thsottiauxOct 15
Day 11/ We've landed a series of changes and more compute to very significantly decrease the occurrence of the disruptive "Selected model is at capacity. Please try a different model". When it does happen, it should also eventually just continue by itself and not just block on it. Let us know if you still see it out there in the wild and we'll take a look.
11
3
1
40
15,809
🚨 codex users!!! RESET IS COMING!! AGAIN! Tibo’s on Day 10 of the challenge, so this could land anytime. I still have A LOT left 😭 I really feel it in my bones 😂, probably tomorrow or so. Let's burn our tokens, my friends.
49
2
1
237
77,675
Ok, my friends, I seriously hope the reset didn't catch you with an 80%+ weekly limit left. I was around 10-20%. I left my laptop in loop development overnight. Just to wake up to 100% again 😂 xitter.cf/shownotover/status/211…
shownotover
@shownotoverOct 15
🚨 Codex users!!! WE GOT THE RESET from Tibo 🙏 100% again 😂 ♥️ Still had some left, BURNED it like CRAZY, and SHIPPED a new 3D engine + procedural gen. One of my better calls. Follow for more Codex, Claude, Gemini news + benchmarks. Appreciate you all 🙏
139
Burned quite much in the past hours, so I am really expecting that reset to hit within the next 1- 2 days or so.
2
3
6,500
Reset is coming, I feel it: xitter.cf/shownotover/status/211…
shownotover
@shownotoverOct 14
🚨 codex users!!! RESET IS COMING!! AGAIN! Tibo’s on Day 10 of the challenge, so this could land anytime. I still have A LOT left 😭 I really feel it in my bones 😂, probably tomorrow or so. Let's burn our tokens, my friends.
253
🚨 Claude users and Gemini users!!! I’ve only tried Gemini Argon through chat, and I’m NOT convinced so far... Are we really calling this the best model ever??? What’s your experience? Help me out here pls!
29
2
2
26
2,641
Ok, tested them; not convinced so far. Need to test the CLI harness version: xitter.cf/shownotover/status/211…
shownotover
@shownotoverOct 14
🚨 CLAUDE AND GEMINI USERS!! 👽🍔 The story and the prompt: Aliens stop for burgers… but they LOVE the food on Earth too much 😂 A 15-second Three.js short. Both HIGH. GEMINI ARGON (browser chat) vs CLAUDE OPUS 5.5 (claude cli + toolings) → TIME: ~8–10 min vs 31m54s → TOKENS: Argon ~27.6K vs Opus 5.35M → API COST: Argon ~$0.92 vs Opus ~$6.63 → SPEED: Argon ~46–57 TPS vs Opus ~97.2 TPS WEEKLY: Argon was around ~1% vs Opus close to 0%!!! Argon finished around 3× FASTER, but I still like OPUS’s visual quality WAY more… We need a rematch in Antigravity when we poor Gemini Pro users get access to the CLI version 😂 Which one tells the story better? 👀 How do you like the new Gemini model?
1
2
237
How the f*ck did Claude suddenly get 100x better than Codex???
66
8
6
283
31,195
What do we think, guys?: xitter.cf/shownotover/status/211…
shownotover
@shownotoverOct 13
🚨 Claude users and Gemini users!!! I’ve only tried Gemini Argon through chat, and I’m NOT convinced so far... Are we really calling this the best model ever??? What’s your experience? Help me out here pls!
1
323
Load more