The opinions, the patterns, and the posts behind them.
13 models tracked6 vendors · Source: X
94 classified mentions · 9 excluded (1 cannot determine)Newest post Oct 4, 2026
THE BIG PICTURE
How the conversation is changing
PositiveNegative
52%positive (49)
5%negative (5)
39 neutral · 1 mixedNo comparable previous period
Share of classified mentions · UTCCollected opinions, unweighted by likes or reposts
READ THE EVIDENCE
In their own words
neutralJev confidence 87.0%
Opus 5.5 vs Sonnet 5.5, same prompt: Orbit Ward: a tiny planet comet deflector and its own trailer
one HTML file, no assets
Opus 5.5: 37m 53s, 955 lines, $5.69
Sonnet 5.5: 35m 58s, 1,170 lines, $3.76
top is Opus 5.5, bottom is Sonnet 5.5. costs are estimated API prices https://t.co/Bjp71tROIZ
Jev classification details
Overall: Neutral87.0% 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
90.0%
Mixed
5.0%
Not discussed
1.0%
Cannot determine
4.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
87.0%
Reasoning
Not discussed
94.0%
Speed
Neutral
78.0%
Cost
Neutral
79.0%
Coding
Neutral
45.0%
Refers to Claude Sonnet 5.5Yes · 95.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 50.0%
So Sonnet 5.5 is better than Opus 5.5 which is better than Fable 5.1????
I thought they were about performance?
Jev classification details
Overall: Neutral50.0% 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
7.0%
Negative
20.0%
Neutral
58.0%
Mixed
1.0%
Not discussed
1.0%
Cannot determine
13.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
50.0%
Reasoning
Not discussed
97.0%
Speed
Not discussed
97.0%
Cost
Not discussed
100.0%
Coding
Not discussed
99.0%
Refers to Claude Sonnet 5.5Yes · 88.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
positiveJev confidence 99.0%
Sonnet 5.5 is incredible at GameDev
The Mario Kart test was done in around an hour on Extra
This is absolutely beautiful https://t.co/lZZiabGM5R
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
99.0%
Speed
Not discussed
27.0%
Cost
Not discussed
100.0%
Coding
Positive
95.0%
Refers to Claude Sonnet 5.5Yes · 90.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
negativeJev confidence 52.0%
@SimonasLTU1 This makes no sense unless Sonnet 5.5 used a lot more tokens than Opus.
Jev classification details
Overall: Negative52.0% 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
61.0%
Neutral
6.0%
Mixed
0.0%
Not discussed
1.0%
Cannot determine
32.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Negative
52.0%
Reasoning
Not discussed
81.0%
Speed
Not discussed
91.0%
Cost
Not discussed
82.0%
Coding
Not discussed
96.0%
Refers to Claude Sonnet 5.5Yes · 78.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 82.0%
I made a short film called Slow Me Down.
A dad vibe codes a game for his daughter. He makes his own character weaker so she always wins.
One day, she asks Claude why her dad always loses.
Made with Sonnet 5.5 using real Claude Code sessions. https://t.co/eaV3xXpPLv
Jev classification details
Overall: Neutral82.0% 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
6.0%
Negative
0.0%
Neutral
86.0%
Mixed
0.0%
Not discussed
7.0%
Cannot determine
1.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
82.0%
Reasoning
Not discussed
98.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Neutral
82.0%
Refers to Claude Sonnet 5.5Yes · 91.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
positiveJev confidence 99.0%
sonnet 5.5 + opus 5.5 is an insane coding stack
send this to Claude Code and watch it route every step to the right model.
steal this before everyone starts using it: https://t.co/XphvVFbatu https://t.co/fEPJmINlgv
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
99.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Positive
99.0%
Refers to Claude Sonnet 5.5Yes · 94.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
positiveJev confidence 48.0%
SONNET 5.5 + OPUS 5.5 + 14 DAYS on one centipede, and most people never find out what they were holding...
one centipede crawls the whole plan in 36 seconds: 5,746 steps, 106 lines lit up, every prompt you need on one page
nothing starts with a question, because day 0 is one https://t.co/MrRsdFz4QV https://t.co/inXZGakVBh
Jev classification details
Overall: Positive48.0% 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
57.0%
Negative
1.0%
Neutral
24.0%
Mixed
1.0%
Not discussed
2.0%
Cannot determine
15.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Positive
48.0%
Reasoning
Not discussed
75.0%
Speed
Not discussed
87.0%
Cost
Not discussed
75.0%
Coding
Not discussed
72.0%
Refers to Claude Sonnet 5.5Yes · 85.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 35.0%
since its literally more launchpads than memes nowadays i will prompt Sonnet 5.5 to create a launchpad with all the fees it gets https://t.co/ec3SfEtP1n
Jev classification details
Overall: Neutral35.0% 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
8.0%
Negative
28.0%
Neutral
45.0%
Mixed
1.0%
Not discussed
9.0%
Cannot determine
9.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
35.0%
Reasoning
Not discussed
87.0%
Speed
Not discussed
99.0%
Cost
Not discussed
76.0%
Coding
Not discussed
71.0%
Refers to Claude Sonnet 5.5Yes · 97.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 95.0%
Which model is better for coding? 👀
Claude Sonnet 5.5 or Claude Opus 5.5?
Which one are you using, and which gives you better results?
Jev classification details
Overall: Neutral95.0% 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
96.0%
Mixed
0.0%
Not discussed
2.0%
Cannot determine
2.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
95.0%
Reasoning
Not discussed
94.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Neutral
99.0%
Refers to Claude Sonnet 5.5Yes · 81.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
positiveJev confidence 99.0%
got a $20 Claude plan just to get me through the weekend
surprised how much usage you can get out of it with Sonnet 5.5
big difference from when I first started using Sonnet 3.5
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
99.0%
Speed
Not discussed
100.0%
Cost
Positive
98.0%
Coding
Not discussed
100.0%
Refers to Claude Sonnet 5.5Yes · 97.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
positiveJev confidence 52.0%
OPUS 5.5 + SONNET 5.5 + JEV + DOTS, and most of your AI bill is gone...
jev writes nothing, you hand it questions and it hands back a label, a score or a probability
that's why 100 emails get checked for fraud in 1.42 seconds, 96 of 100 right, for 7 cents total
someone ran https://t.co/XucU4nah5w https://t.co/4s2xrzNdR1
Jev classification details
Overall: Positive52.0% 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
61.0%
Negative
0.0%
Neutral
21.0%
Mixed
1.0%
Not discussed
8.0%
Cannot determine
9.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Positive
52.0%
Reasoning
Not discussed
97.0%
Speed
Not discussed
92.0%
Cost
Not discussed
64.0%
Coding
Not discussed
99.0%
Refers to Claude Sonnet 5.5Yes · 89.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 92.0%
Claude Opus 5.5 and Sonnet 5.5 just showed up in Antigravity. Paid plans only, and the old models are already on a timer. https://t.co/d73pzpLMGQ
Jev classification details
Overall: Neutral92.0% 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
3.0%
Neutral
93.0%
Mixed
2.0%
Not discussed
1.0%
Cannot determine
0.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
92.0%
Reasoning
Not discussed
100.0%
Speed
Not discussed
100.0%
Cost
Neutral
51.0%
Coding
Not discussed
100.0%
Refers to Claude Sonnet 5.5Yes · 97.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
Page 1 of 8 · 94 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