Gemini 4 Carbon vs GPT 6.1 Sol
Comparar modelos
GPT 6.1 Sol is more worth it — 41% vs 39%
How we score worth-it? →Google's strongest frontier model — tops Intelligence Index v5, state-of-the-art cybersecurity + long coding. Gated to cyber defenders.
- So more capable and the same price? I can at least appreciate that.— hn ↗
- Huge progress, wow — first place on the terminal bench science benchmark.— blog ↗
- I've been using Gemini 4 in AI Studio, and its human-like writing is in a league of its own; if Carbon is that strong, I'd consider upgrading to the Ultra plan.— blog ↗
- Impressive. — Elon Musk, replying to Sundar Pichai's Gemini 4 Carbon announcement.— x ↗
- You have once again announced a model we cannot use — I cannot fathom what motivates a lab whose recent releases haven't been competitive to shoot themselves in the foot like this.— hn ↗
- This model is not for you or me. This model is for Google AI engineers to put on their perf review at the end of the year.— hn ↗
- The benchmarks of a model that hasn't been released yet are definitely suspicious. Google should stop releasing models that aren't actually available.— hn ↗
- Without being able to access Carbon at announcement, there's no way to know the Carbon we get later is the same thing as what has been benchmarked.— hn ↗
- Even paying customers still can't use it!— hn ↗
“More capable and the same price — I can at least appreciate that.”
“Huge progress — first place on the terminal bench science benchmark.”
“You have once again announced a model we cannot use.”
Bills run high on agent tasks
- GPT 6.1 Sol is already the new Terra IMO. Same pricing as old Terra and competitive performance with even Astra on strictly coding-oriented tasks.— hn
- If I were to grade those models from 1-10 (10 = top tier), I'd give deepseek a solid 6.5 and 6.1 sol a 7.5-8.0 maybe.— hn
- GPT 6.1 Sol is an excellent model. It has some weaknesses (frontend design) but also strengths (computer use / control, great for automated E2E QA).— hn
- GPT 6.1 Sol can now beat games 100% vision-only — Pokémon is no longer a difficult challenge, and it beat Final Fantasy VII vision-only surprisingly quickly.— hn
- I genuinely prefer OpenAI models for coding. GPT models are generally better at following the system prompt, tool use, and skill use.— hn
- This wasn't my experience. GPT 6.1 Sol is ~6-7x more expensive for similar intelligence.— hn
- Agent reliability regression: incorrect goal interpretation, prolonged execution, and failure to self-correct.— github
- GPT-6.1 Sol at xhigh regresses in instruction following and task completion.— github
- GPT-6.1 Sol sessions lose coherence, slow down and repeatedly restart the same plan.— github
- Opus 5.5 is an order of magnitude better at design and design nuances than GPT 6.1 Sol, surprisingly.— hn
“The actual value king from OpenAI. Does 90% of what Astra does for way less.”
“Agent tasks are where it shines — cheap enough to run all day without watching the meter.”
“It's not the sharpest on hard reasoning, but for everyday work it's plenty.”
FAQ
Is Gemini 4 Carbon or GPT 6.1 Sol more worth it?
GPT 6.1 Sol is more worth it, with a 41% worth-it score vs 39% for Gemini 4 Carbon.
How much does Gemini 4 Carbon cost vs GPT 6.1 Sol?
Gemini 4 Carbon: $2/$10 per 1M (→$4/$20 Dec 1) · GPT 6.1 Sol: $2/$10 per 1M tokens.
What do users say about Gemini 4 Carbon vs GPT 6.1 Sol?
Gemini 4 Carbon: More capable and the same price — I can at least appreciate that.. GPT 6.1 Sol: The actual value king from OpenAI. Does 90% of what Astra does for way less..