Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 3 Pro Model Card [pdf]

storage.googleapis.com

Post reply on HN
Print view View original

171–180 of 359 posts

Re: Gemini 3 Pro Model Card [pdf]

#171

Post by jstummbillig »

danielcampos93 wrote: post #160
scrlk wrote: post #23

Benchmarks from page 4 of the model card: | Benchmark | 3 Pro | 2.5 Pro | Sonnet 4.5 | GPT-5.1 | |-----------------------|-----------|---------|------------|-----------| | Humanity's Last Exam | 37.5% | 21.6% | 13.7% | 26.5% | | ARC-AGI-2 | 31.1% | 4.9% | 13.6% | 17.6% | | GPQA Diamond | 91.9% | 86.4% | 83.4% | 88.1% | | AIME 2025 | | | | | | (no tools) | 95.0% | 88.0% | 87.0% | 94.0% | | (code execution) | 100% | -…

I would love to know what the increased token count is across these models for the benchmarks. I find the models continue to get better but as they do their token usage also does. Aka is model doing better or reasoning for longer?

I think that is always something that is being worked on in parallel. Recent paradigm seems to be the models understanding when they need to use more tokens dynamically (which seems to be very much in line with how computation should generally work).

Re: Gemini 3 Pro Model Card [pdf]

#172

Post by macrolime »

mynti wrote: post #75

It is interesting that the Gemini 3 beats every other model on these benchmarks, mostly by a wide margin, but not on SWE Bench. Sonnet is still king here and all three look to be basically on the same level. Kind of wild to see them hit such a wall when it comes to agentic coding

Pretty sure it will beat Sonnet by a wide margin in actual real-world usage.

Re: Gemini 3 Pro Model Card [pdf]

#173

Post by grodriguez100 »

embedding-shape wrote: post #38

Curiously, this website seems to be blocked in Spain for whatever reason, and the website's certificate is served by `allot.com/emailAddress=info@allot.com` which obviously fails... Anyone happen to know why? Is this website by any change sharing information on safe medical abortions or women's rights, something which has gotten websites blocked here before?

Is it possible to file a complaint with the ISP or directly with Allot ?

Re: Gemini 3 Pro Model Card [pdf]

#176

Post by KronisLV »

Alifatisk wrote: post #71
scrlk wrote: post #23

Benchmarks from page 4 of the model card: | Benchmark | 3 Pro | 2.5 Pro | Sonnet 4.5 | GPT-5.1 | |-----------------------|-----------|---------|------------|-----------| | Humanity's Last Exam | 37.5% | 21.6% | 13.7% | 26.5% | | ARC-AGI-2 | 31.1% | 4.9% | 13.6% | 17.6% | | GPQA Diamond | 91.9% | 86.4% | 83.4% | 88.1% | | AIME 2025 | | | | | | (no tools) | 95.0% | 88.0% | 87.0% | 94.0% | | (code execution) | 100% | -…

These numbers are impressive, at least to say. It looks like Google has produced a beast that will raise the bar even higher. What's even more impressive is how Google came into this game late and went from producing a few flops to being the leader at this (actually, they already achieved the title with 2.5 Pro). What makes me even more curious is the following > Model dependencies: This model is not a modification o…

I hope they keep the pricing similar to 2.5 Pro, currently I pay per token and that and GPT-5 are close to the sweet spot for me but Sonnet 4.5 feels too expensive for larger changes. I've also been moving around 100M tokens per week with Cerebras Code (they moved to GLM 4.6), but the flagship models still feel better when I need help with more advanced debugging or some exemplary refactoring to then feed as an example for a dumber/faster model.

Re: Gemini 3 Pro Model Card [pdf]

#177

Post by sigmoid10 »

dbbk wrote: post #141
Alifatisk wrote: post #71

Earlier quoted context omitted.

These numbers are impressive, at least to say. It looks like Google has produced a beast that will raise the bar even higher. What's even more impressive is how Google came into this game late and went from producing a few flops to being the leader at this (actually, they already achieved the title with 2.5 Pro). What makes me even more curious is the following > Model dependencies: This model is not a modification o…

And also, critically, being the only profitable company doing this.

It's not like they're making their money from this though. All AI work is heavily subsidised, for Alphabet it just happens that the funding comes from within the megacorp. If MS had fully absorbed OpenAI back when their board nearly sunk the boat, they'd be in the exact same situation today.

Re: Gemini 3 Pro Model Card [pdf]

#178

Post by dnw »

scrlk wrote: post #23

Benchmarks from page 4 of the model card: | Benchmark | 3 Pro | 2.5 Pro | Sonnet 4.5 | GPT-5.1 | |-----------------------|-----------|---------|------------|-----------| | Humanity's Last Exam | 37.5% | 21.6% | 13.7% | 26.5% | | ARC-AGI-2 | 31.1% | 4.9% | 13.6% | 17.6% | | GPQA Diamond | 91.9% | 86.4% | 83.4% | 88.1% | | AIME 2025 | | | | | | (no tools) | 95.0% | 88.0% | 87.0% | 94.0% | | (code execution) | 100% | -…

Looks like the best way to keep improving the models is to come up with really useful benchmarks and make them popular. ARC-AGI-2 is a big jump, I'd be curious to find out how that transfers over to everyday tasks in various fields.

Re: Gemini 3 Pro Model Card [pdf]

#180

Post by Snuggly73 »

trunch wrote: post #145
scrlk wrote: post #23

Benchmarks from page 4 of the model card: | Benchmark | 3 Pro | 2.5 Pro | Sonnet 4.5 | GPT-5.1 | |-----------------------|-----------|---------|------------|-----------| | Humanity's Last Exam | 37.5% | 21.6% | 13.7% | 26.5% | | ARC-AGI-2 | 31.1% | 4.9% | 13.6% | 17.6% | | GPQA Diamond | 91.9% | 86.4% | 83.4% | 88.1% | | AIME 2025 | | | | | | (no tools) | 95.0% | 88.0% | 87.0% | 94.0% | | (code execution) | 100% | -…

Which of the LiveCodeBench Pro and SWE-Bench Verified benchmarks comes closer to everyday coding assistant tasks? Because it seems to lead by a decent margin on the former and trails behind on the latter

Neither :(

LCB Pro are leet code style questions and SWE bench verified is heavily benchmaxxed very old python tasks.

Post reply on HN