Dark | Light
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

# ![$0004task Graphic](https://lunarcrush.com/gi/w:26/t:$0004task.png) $0004task

Qwen3-235b Instruct model's performance is under scrutiny after discrepancies were found in benchmark results. Community members are actively discussing the model's performance and open-source methods.

### About $0004task
A topic related to the discussion and evaluation of the Qwen3-235b Instruct model.  

### Insights [#](/topic/$0004task/insights)
- $0004task creators is up XXX% from the previous week.
- $0004task mentions is up XXX% from the previous week.

### Engagements: XXX [#](/topic/$0004task/interactions)
---
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/t:$0004task/c:line/m:interactions.svg)  
[Engagements 24-Hour Chart Data](/topic/$0004task/time-series/interactions.tsv)  
**Current Value**: XXX  
**Daily Average**: XXXXXX  
**1-Year High**: XXXXXXX on 2025-07-24  
**1-Year Low**: X on 2025-07-18  

| Social Network | X   |
| -------------- | -   |
| Engagements    | XXX |
  

  
  
### Mentions: X [#](/topic/$0004task/posts_active)
---
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/t:$0004task/c:line/m:posts_active.svg)  
[Mentions 24-Hour Chart Data](/topic/$0004task/time-series/posts_active.tsv)  
**Current Value**: X  
**Daily Average**: X  
**1 Week**: X +400%  
**1-Year High**: X on 2025-07-24  
**1-Year Low**: X on 2025-07-16  

| Social Network | X |
| -------------- | - |
| Mentions       | X |
  

  
  
### Creators: X [#](/topic/$0004task/contributors_active)
---
![Creators Line Chart](https://lunarcrush.com/gi/w:600/t:$0004task/c:line/m:contributors_active.svg)  
[Creators 24-Hour Chart Data](/topic/$0004task/time-series/contributors_active.tsv)  
X unique social accounts have posts mentioning $0004task in the last XX hours which is down XX% from X in the previous XX hours
**Daily Average**: X  
**1 Week**: X +400%  
**1-Year High**: X on 2025-07-24  
**1-Year Low**: X on 2025-07-16  

**Top topics mentioned**
In the posts about $0004task in the last XX hours

[$0003task](/topic/$0003task), [prize](/topic/prize), [arc](/topic/arc), [grok 4](/topic/grok-4), [greg](/topic/greg), [qwen](/topic/qwen), [gaib](/topic/gaib)

### Top Social Posts [#](/topic/$0004task/posts)
---
Top posts by engagements in the last XX hours

*Showing only X posts for non-authenticated requests. Use your API key in requests for full results.*

"Official verification of Qwen3-235b Instruct: it gets XX% on ARC-AGI-1 and XXX% on ARC-AGI-2 (semi-private sets). These numbers are in line with other SotA base models. Qwen3 stands out by being the cheapest base model we tested to score above XX% on ARC-AGI-1"  
[@fchollet](/creator/x/fchollet) on [X](/post/tweet/1948481171220037827) 2025-07-24 20:31:26 UTC 562.5K followers, 38.3K engagements


"decent if you compare it only to non-reasoning models but nowhere near the XX% the Qwen team reported but pretty bad against o4-mini or Gemini XXX Flash"  
[@scaling01](/creator/x/scaling01) on [X](/post/tweet/1948454702108062116) 2025-07-24 18:46:16 UTC 17.6K followers, 5782 engagements


"I was in contact with the Qwen team trying to reproduce their XX% results on ARC-AGI-1 but ultimately couldn't They open sourced their method and code if anyone wants to check it out and confirm We tested their model exactly the same as we test all other models (o3-high grok X etc.)"  
[@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1948454001886003328) 2025-07-24 18:43:29 UTC 41.7K followers, 135.2K engagements


"Qwen3-235b-a22b Instruct-2507 ARC-AGI Semi Private Eval * ARC-AGI-1: XX% $0.003/task * ARC-AGI-2: XXX% $0.004/task"  
[@arcprize](/creator/x/arcprize) on [X](/post/tweet/1948453132184494471) 2025-07-24 18:40:01 UTC 24.9K followers, 167.2K engagements

[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

$0004task Graphic $0004task

Qwen3-235b Instruct model's performance is under scrutiny after discrepancies were found in benchmark results. Community members are actively discussing the model's performance and open-source methods.

About $0004task

A topic related to the discussion and evaluation of the Qwen3-235b Instruct model.

Insights #

  • $0004task creators is up XXX% from the previous week.
  • $0004task mentions is up XXX% from the previous week.

Engagements: XXX #


Engagements Line Chart
Engagements 24-Hour Chart Data
Current Value: XXX
Daily Average: XXXXXX
1-Year High: XXXXXXX on 2025-07-24
1-Year Low: X on 2025-07-18

Social Network X
Engagements XXX

Mentions: X #


Mentions Line Chart
Mentions 24-Hour Chart Data
Current Value: X
Daily Average: X
1 Week: X +400%
1-Year High: X on 2025-07-24
1-Year Low: X on 2025-07-16

Social Network X
Mentions X

Creators: X #


Creators Line Chart
Creators 24-Hour Chart Data
X unique social accounts have posts mentioning $0004task in the last XX hours which is down XX% from X in the previous XX hours Daily Average: X
1 Week: X +400%
1-Year High: X on 2025-07-24
1-Year Low: X on 2025-07-16

Top topics mentioned In the posts about $0004task in the last XX hours

$0003task, prize, arc, grok 4, greg, qwen, gaib

Top Social Posts #


Top posts by engagements in the last XX hours

Showing only X posts for non-authenticated requests. Use your API key in requests for full results.

"Official verification of Qwen3-235b Instruct: it gets XX% on ARC-AGI-1 and XXX% on ARC-AGI-2 (semi-private sets). These numbers are in line with other SotA base models. Qwen3 stands out by being the cheapest base model we tested to score above XX% on ARC-AGI-1"
@fchollet on X 2025-07-24 20:31:26 UTC 562.5K followers, 38.3K engagements

"decent if you compare it only to non-reasoning models but nowhere near the XX% the Qwen team reported but pretty bad against o4-mini or Gemini XXX Flash"
@scaling01 on X 2025-07-24 18:46:16 UTC 17.6K followers, 5782 engagements

"I was in contact with the Qwen team trying to reproduce their XX% results on ARC-AGI-1 but ultimately couldn't They open sourced their method and code if anyone wants to check it out and confirm We tested their model exactly the same as we test all other models (o3-high grok X etc.)"
@GregKamradt on X 2025-07-24 18:43:29 UTC 41.7K followers, 135.2K engagements

"Qwen3-235b-a22b Instruct-2507 ARC-AGI Semi Private Eval * ARC-AGI-1: XX% $0.003/task * ARC-AGI-2: XXX% $0.004/task"
@arcprize on X 2025-07-24 18:40:01 UTC 24.9K followers, 167.2K engagements

$0004task
/topic/$0004task