The opinions, the patterns, and the posts behind them.
13 models tracked6 vendors · Source: X
96 classified mentions · 8 excluded (1 cannot determine)Newest post Oct 4, 2026
THE BIG PICTURE
How the conversation is changing
PositiveNegative
40%positive (38)
16%negative (15)
40 neutral · 3 mixedNo comparable previous period
Share of classified mentions · UTCCollected opinions, unweighted by likes or reposts
READ THE EVIDENCE
In their own words
positiveJev confidence 71.0%
@OpenAI @OpenAI @thsottiaux it's maddening. I had the whole day GPT-6.1 SOL and Luna working on a proyect...and still working... I'm quite sure with Antigravity Gemini 3.8 flash high it would had finished it in less than 2 hours.
The uncertainty about the speed is not good for planning
Jev classification details
Overall: Positive71.0% confidence
Praise, endorsement, or a favorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
76.0%
Negative
5.0%
Neutral
0.0%
Mixed
16.0%
Not discussed
0.0%
Cannot determine
3.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Positive
71.0%
Reasoning
Not discussed
97.0%
Speed
Positive
59.0%
Cost
Not discussed
100.0%
Coding
Positive
39.0%
Refers to Gemini 3.8 FlashYes · 90.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 97.0%
Google's September spam update is still rolling out with ranking swings around Sep 4, 15, and 23. AI Mode now runs on Gemini 3.8 Flash. #SEO #AISearch https://t.co/eTU3SC1sEe
Jev classification details
Overall: Neutral97.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
0.0%
Neutral
98.0%
Mixed
0.0%
Not discussed
2.0%
Cannot determine
0.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
97.0%
Reasoning
Not discussed
99.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Not discussed
100.0%
Refers to Gemini 3.8 FlashYes · 100.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
negativeJev confidence 82.0%
I am suffering from these kinds of outputs from gemini-3.8-flash. @GoogleDeepMind, please launch Gemini 4 Argon as soon as possible and save me. https://t.co/Aec7vvbAD8 https://t.co/w6g7pqbH4v
Jev classification details
Overall: Negative82.0% confidence
Criticism, disappointment, or an unfavorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
86.0%
Neutral
1.0%
Mixed
0.0%
Not discussed
0.0%
Cannot determine
13.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Negative
82.0%
Reasoning
Not discussed
59.0%
Speed
Not discussed
92.0%
Cost
Not discussed
100.0%
Coding
Not discussed
82.0%
Refers to Gemini 3.8 FlashYes · 98.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 74.0%
Just for fun, I gave Claude Opus 5.5 Ultracode (@AnthropicAI) and Gemini 3.8 Flash High (@GeminiApp) the same prompt and full creative freedom: build a living world that evolves 24/7 on its own. All code written by AI. Non-commercial, no ads. Live: https://t.co/ma76CKyI1t https://t.co/RMCI1imXfy
Jev classification details
Overall: Neutral74.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
1.0%
Negative
0.0%
Neutral
79.0%
Mixed
0.0%
Not discussed
9.0%
Cannot determine
11.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
74.0%
Reasoning
Not discussed
91.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Neutral
60.0%
Refers to Gemini 3.8 FlashYes · 33.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
positiveJev confidence 56.0%
Here are some new visualizations made with Gemini 3.8 Flash.
Heres a copper fern spiral! https://t.co/40Xdz8zDDn
Jev classification details
Overall: Positive56.0% confidence
Praise, endorsement, or a favorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
63.0%
Negative
0.0%
Neutral
27.0%
Mixed
0.0%
Not discussed
3.0%
Cannot determine
7.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Positive
56.0%
Reasoning
Not discussed
99.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Not discussed
100.0%
Refers to Gemini 3.8 FlashYes · 100.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 85.0%
@ai_for_success Voice - Gemini 3.8 flash tts
Music - lyria 3.5 and lyria realtime
Jev classification details
Overall: Neutral85.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
1.0%
Negative
0.0%
Neutral
87.0%
Mixed
0.0%
Not discussed
10.0%
Cannot determine
2.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
85.0%
Reasoning
Not discussed
100.0%
Speed
Not discussed
99.0%
Cost
Not discussed
100.0%
Coding
Not discussed
100.0%
Refers to Gemini 3.8 FlashYes · 88.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
negativeJev confidence 93.0%
- Installed Antigravity 2.0
- Started a project using Gemini 3.8 Flash
- After some time it proposes me first script to run in Proxmox shell
- I pass the script to Opus: is it correct?
- No, it has errors
- I pass the feedback to Gemini
- You're right it has errors
Embarrassing
Jev classification details
Overall: Negative93.0% confidence
Criticism, disappointment, or an unfavorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
95.0%
Neutral
3.0%
Mixed
1.0%
Not discussed
0.0%
Cannot determine
1.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Negative
93.0%
Reasoning
Not discussed
93.0%
Speed
Not discussed
99.0%
Cost
Not discussed
100.0%
Coding
Negative
94.0%
Refers to Gemini 3.8 FlashYes · 98.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 73.0%
Fully AI-generated 3D Asteroids game with procedural models in Godot 4! 🚀💥
Built using Gemini 3.8 Flash (medium) in Antigravity, hooked up to the scad-gltf MCP server.
🎮 Play the Web build here:
https://t.co/8rEUumcDpV
#GodotEngine #GameDev #Gemini #OpenSCAD #IndieDev #MCP https://t.co/UdeXusnI5q
Jev classification details
Overall: Neutral73.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
20.0%
Negative
0.0%
Neutral
78.0%
Mixed
0.0%
Not discussed
2.0%
Cannot determine
0.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
73.0%
Reasoning
Not discussed
99.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Positive
58.0%
Refers to Gemini 3.8 FlashYes · 99.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
positiveJev confidence 99.0%
@NovaXCode Meh, Gemini punches above its weight in day-to-day usage.
Gemini 3.8 flash has:
- A more pleasant personality than claude/gpt
- The best ai humor i've seen so far
- Can generate anagrams better & faster than 6.1sol
- smarter than other free models (sonnet 5.5/gpt)
- great vision
Jev classification details
Overall: Positive99.0% confidence
Praise, endorsement, or a favorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
100.0%
Negative
0.0%
Neutral
0.0%
Mixed
0.0%
Not discussed
0.0%
Cannot determine
0.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Positive
99.0%
Reasoning
Not discussed
88.0%
Speed
Positive
62.0%
Cost
Not discussed
98.0%
Coding
Not discussed
99.0%
Refers to Gemini 3.8 FlashYes · 100.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 39.0%
Send It is powered by some of the best AI models available.
Build with Claude Sonnet 5.5, Claude Fable 5.1, GPT-6 Astra, Gemini 3.8 Flash, Grok 4.7 and more.
Pick the model. Prompt your idea. Send it. https://t.co/lalhYFeCbv
Jev classification details
Overall: Neutral39.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
48.0%
Negative
0.0%
Neutral
49.0%
Mixed
0.0%
Not discussed
2.0%
Cannot determine
1.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
39.0%
Reasoning
Not discussed
99.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Not discussed
100.0%
Refers to Gemini 3.8 FlashYes · 99.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 71.0%
Hey @grok, remove the one that hallucinates the most from these:
GPT-6 Sol,
Claude Opus 5.5,
Gemini 3.8 Flash,
DeepSeek-V4 Pro,
Qwen3.8,
GLM-5.3,
Sonnet 5.5,
Fable 5,
or Grok 4.7. 👀
Which one are you removing? https://t.co/FL6dKwShbs
Jev classification details
Overall: Neutral71.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
4.0%
Neutral
75.0%
Mixed
0.0%
Not discussed
7.0%
Cannot determine
14.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
71.0%
Reasoning
Not discussed
80.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Not discussed
100.0%
Refers to Gemini 3.8 FlashYes · 55.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 78.0%
@itsPaulAi Is Gemini flash 3.8 better than Sonnet 5.5 at execution?
I was doing the other way, Gemini 3.8 flash for frontend and Sonnet 5.5 for execution
Although the Claude models limits are gone with just few prompts
Jev classification details
Overall: Neutral78.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
2.0%
Negative
3.0%
Neutral
82.0%
Mixed
4.0%
Not discussed
1.0%
Cannot determine
8.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
78.0%
Reasoning
Not discussed
82.0%
Speed
Not discussed
87.0%
Cost
Not discussed
100.0%
Coding
Neutral
90.0%
Refers to Gemini 3.8 FlashYes · 99.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
Page 1 of 8 · 96 mentions
1 of 1 enabled models have a recorded collection outcome with target 50 in the last 7 days. Search exhaustion and page limits can produce fewer records.Target reached · 100 / 50 accepted · target reached · Last successful collection Oct 4, 2026
Last collection attempt Oct 5, 2026 · partially completedNew analyses use TypeSafe Jev