Gemini Flash

What hackers pick instead

• Claude OpusRecommended as a top coding model that fixes bugs and ships features with fewer mistakes than earlier LLMs, though critics cite weak architecture choices, usage limits and confident errors.3331recommend
• OpenAI GPTRecommended for strong coding, debugging and research help with good reasoning and token efficiency, though critics cite hallucinations, overcomplication, verbose output and high cost.1205recommend
• Claude SonnetA capable coding model that has improved noticeably with each version and is faster and cheaper than Opus, though it needs careful supervision and usage limits bite.854recommend
• DeepSeek V4 FlashA very cheap, fast model that people find close to frontier quality for coding and everyday tasks; critics say it errs more, loops, and needs steering.828recommend
• FableRecommended as a top coding model for hard, long-running tasks and large refactors, though critics cite over-engineered code, costly usage limits and safety guards that switch models mid-task.823recommend

Every quote

The 40 most detailed of 1353 comments. Each links to the original.

1. I appreciate that they are delivering on both of those, but personally I would appreciate if they could create an incremental knowledge improvement while holding price steady

   Mixed · May 2026 · in “Gemini 3.5: frontier intelligence with action”

2. Gemini does feel like code-red for basically every AI company like chatgpt,claude etc. too in my opinion if the underlying model is both fast and cheap and good enough

   Recommends · Dec 2025 · in “Gemini 3 Flash: Frontier intelligence built for speed”

3. if I can isolate a problem and put it into a straightforward prompt then Gemini 2.5 flash - the most basic and cheap commercial model - is actually very reliable

   Recommends · Oct 2026 · in “Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers”

4. I think it's good, they're raising the size (and price) of flash a bit and trying to position Flash as an actually useful coding / reasoning model.

   Recommends · Dec 2025 · in “Gemini 3 Flash: Frontier intelligence built for speed”

5. The model seems fast enough to solve your problem before Google finishes explaining which of its three products you need to open to access it.

   Mixed · Sep 2026 · in “Gemini 3.8 Flash and 3.8 Flash Cyber”

6. I wouldn't use Gemini 3 Flash or GPT 5.4 mini for anything except the most trivial work, although both are useful for basic exploratory work.

   Mixed · May 2026 · in “Show HN: State of the Art of Coding Models, According to Hacker News Commenters”

7. it's exceptionally good and fast as a HA assistant while being much cheaper than the electricity that would be needed to keep a 3090 awake

   Recommends · Mar 2026 · in “My Journey to a reliable and enjoyable locally hosted voice assistant”

8. Gemini 2.5 flash and 3 flash were highly underrated models that performed way better than the peers and we used the hell out of them.

   Recommends · Oct 2026 · in “Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5”

9. I have run this thousands times against Llama-4-Maverick-17B-128E-Instruct-FP8 and Gemini-3-Flash with consistently working results.

   Recommends · Feb 2026 · in “How LLMs Express JavaScript (experiment, results inside)”

10. I can get multiple sets of footnotes (critical + content notes) reliably recognized and categorized using gemini-3-flash-preview.

    Recommends · Feb 2026 · in “GLM-OCR: Accurate × Fast × Comprehensive”

11. Gemini 3 Flash nails it sometimes even better than the Pro version, with nearly the same times as 2.5 Pro does on that usecase.

    Recommends · Dec 2025 · in “Gemini 3 Flash: Frontier intelligence built for speed”

12. The auto-complete suggestions from FIM models (either open source or even something Gemini Flash) punch far above their weight.

    Recommends · Nov 2025 · in “Claude Opus 4.5”

13. i might consider 3.8 flash for simple side hobby projects or quick scaffolding but would not trust it for long agentic tasks

    Mixed · Sep 2026 · in “Gemini 3.8 Flash and 3.8 Flash Cyber”

14. 3.7 seems a game changer IMO. Gemini 3.7 flash is really really near frontier intelligence at an order of magnitude cheaper

    Recommends · Sep 2026 · in “Google Antigravity introduces Boost deep reasoning (/boost)”

15. in my tests it's actually LESS token efficient than 3.5 Flash, so despite the output price reduction, it still costs more

    Mixed · Jul 2026 · in “Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber”

16. It makes sense that Google focused on smaller, faster yet smart enough models that wouldn't break your bank on inference.

    Recommends · Aug 2026 · in “Gemini 3.7 Flash”

17. A model that is cheap, fast and good, combined with Android and gsuite integration seems like such powerful combination.

    Recommends · Dec 2025 · in “Gemini 3 Flash: Frontier intelligence built for speed”

18. I've been using gemini-3-flash the last few days and it is quite good, I'm not sure you need the biggest models anymore.

    Recommends · Dec 2025 · in “Get an AI code review in 10 seconds”

19. I set Gemini 3.8 Flash the task, using my own VERY shonky coding agent tool (llm-coding-agent) - and it did a solid job.

    Recommends · Sep 2026 · in “Gemini 3.8 Flash and 3.8 Flash Cyber”

20. Google's strategy of making their fast/relatively inexpensive models surprisingly powerful has been a welcomed surprise.

    Recommends · Sep 2026 · in “Gemini 3.8 Flash and 3.8 Flash Cyber”

21. the capability it has along with the thinking budgets make it superior to previous Pro models in both outcome and speed

    Recommends · Dec 2025 · in “Gemini 3 Flash: Frontier intelligence built for speed”

22. I have released applications on Gemini 3.5 flash that make real money and I don't see any particular reason to upgrade.

    Recommends · Sep 2026 · in “GPT-6 Astra”

23. gemini flash is usually finished. It's not SotA for coding, but it's fast and often "good enough" for normal tasks.

    Recommends · Jun 2026 · in “Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks”

24. Based on my experience, even Flash could sometime make mistakes including something as obvious as simple arithmetic

    Mixed · Oct 2026 · in “Gemini ending free use of Flash and Pro models”

25. For frontend work, the model/harness/tool combo of 3.8 flash extended/agy/chrome dev tools MCP is shockingly good

    Recommends · Oct 2026 · in “Gemini 4 Argon”

26. I do 90% of my work on 3.8 - flash - low. C, go , JS, bash , powershell generated content. Near perfect quality.

    Recommends · Oct 2026 · in “Gemini 4 Carbon”

27. Gemini 3.5 Flash is pretty competitive with the big guys, and it's small enough for Google to run it profitably

    Recommends · Jun 2026 · in “AI's Affordability Crisis”

28. Just last week I had Gemini 3.8 Flash and Antigravity take an existing STL of a part and swap out a piece of it

    Recommends · Sep 2026 · in “Benchmark: CadQuery vs. OpenSCAD for agentic CAD work”

29. a fast cheap model with large context (Gemini Flash, Claude Haiku) is more cost-effective than a frontier model

    Recommends · Apr 2026 · in “I'm Coding by Hand”

30. Gemini 3-pro-preview and 3-flash-preview, respectively top2 and top3, had 44% and 37% true positive and whooping 65% and 86% false positives.

    Criticizes · Feb 2026 · in “We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them”

31. Gemini 3.8 outputs 11k more tokens PER TASK on average in AAII than 3.7 putting it dead last in output tokens per task in the leaderboard.

    Criticizes · Sep 2026 · in “Gemini 3.8 Flash and 3.8 Flash Cyber”

32. high effort on gemini 3.5 flash caused it to over think, generating large amounts of tokens without a substantive improve in performance

    Criticizes · May 2026 · in “DeepSWE: A contamination-free benchmark for long-horizon coding agents”

33. for simple tasks that require a large context window, aka the typical usecase for 2.0 flash, it's still significantly more expensive

    Criticizes · Dec 2025 · in “Gemini 3 Flash: Frontier intelligence built for speed”

34. Google is lagging the big 3 (Anthropic, xAI, OpenAI) when it comes to frontier models for programming and hard problem solving.

    Criticizes · Aug 2026 · in “Gemini 3.7 Flash”

35. Haiku/Flash/small models are underpowered for literally anything where being non-false-positively correct on details matters

    Criticizes · Jun 2026 · in “Microsoft's MAI-Code-1-Flash Scores 51% SWE-Bench Pro with Just 5B Active Params”

36. 3.8 Flash suffers from far more hallucinations than 3.1 Pro and frequently ignores the context between consecutive messages.

    Criticizes · Oct 2026 · in “Gemini 4 Argon”

37. I spent 10 minutes with it in their new "agy" CLI tool and immediately found it is nowhere close to GPT 5.5 high in codex.

    Criticizes · May 2026 · in “Gemini 3.5 Flash”

38. Gemini 3.7 flash outputs so many tokens per answer it doesn't matter how fast its TPS is

    Criticizes · Sep 2026 · in “Gemini 3.8 Flash and 3.8 Flash Cyber”

39. I was disappointed with 3.6 flash

    Criticizes · Sep 2026 · in “Google Antigravity introduces Boost deep reasoning (/boost)”

40. a reasonably modern model (and I'm thinking in the range of gemini-flash, not Fable) in a well designed harness geared towards tutoring would handily and repeatedly outperform every single teacher

    Recommends · Jul 2026 · in “Building a real-time AI tutor for 5-year-olds”