Home Models Gemini 3 Pro Google, proprietary
Gemini 3 Pro Gemini 3 Pro by Google ranks 28th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.8. Its strongest category is multimodal, where it ranks 2nd.
Last verified October 10, 2026
Specifications
Noometry rank #28 of 354
Index score 54.8
Evidence Confirmed 67 results
Released November 18, 2025
Weights Proprietary
Reasoning Unknown
Context window —
Max output —
Input price Not listed
Output price Not listed
Blended price Not listed Output speed 1 tokens/s Kagi
Value Not ranked
Knowledge cutoff Unknown Category scores Each category score combines every public result we have in that category.
Gemini 3 Pro category scores Coding 51.6 Agentic & Tool Use 40.6 Reasoning 52.5 Math 49.9 Knowledge 64.4 Multimodal 57.6 Multilingual 56.9 Instruction Following 76.3 Long Context 44.0 Writing & Preference 66.4 30 40 50 60 70 80 Strengths and weaknesses Categories where Gemini 3 Pro places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories Gemini 3 Pro: strongest categories Category Score vs median Rank Multimodal 57.6 +19.0 #2 of 128, top 2% Knowledge 64.4 +27.1 #16 of 314, top 6% Multilingual 56.9 +9.5 #16 of 297, top 6%
Weakest categories Gemini 3 Pro: weakest categories Category Score vs median Rank Long Context 44.0 +3.1 #79 of 296, top 27% Math 49.9 +13.3 #59 of 327, top 19% Agentic & Tool Use 40.6 +10.3 #23 of 154, top 15%
Closest competitors The models ranked just above and below Gemini 3 Pro. When scores are this close, price and speed are often the better way to choose.
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding Gemini 3 Pro Coding benchmark results Benchmark Score Position Setting Source Date SWE-bench Verified 72.9% #21 of 32, top 66% Epoch AI 2026-02-13 SWE-bench Verified (bash only) 74.2% #5 of 39, top 13% SWE-bench 2025-11-18 LMArena WebDev 1440 #58 of 113, top 52% LMArena 2026-10-08 SWE-bench Multilingual 68.7% #5 of 13, top 39% SWE-bench 2026-02-13 GSO 18.6% #14 of 31, top 46% Epoch AI WeirdML 69.9% #19 of 119, top 16% Epoch AI LMArena Coding 1481 #45 of 294, top 16% LMArena 2026-10-08 ALE-Bench 1,177 #33 of 105, top 32% Epoch AI AlgoTune 1.83 #4 of 18, top 23% Epoch AI
Agentic & Tool Use Gemini 3 Pro Agentic & Tool Use benchmark results Benchmark Score Position Setting Source Date Terminal-Bench 69.4% #7 of 41, top 18% Epoch AI Berkeley Function Calling Leaderboard 72.5% #3 of 49, top 7% prompt Berkeley Function Calling Leaderboard GDPval 40.3% #5 of 11, top 46% Epoch AI Remote Labor Index 1.3% #13 of 14, top 93% Epoch AI τ²-bench Airline 80.5% #6 of 7, top 86% high τ²-bench 2026-03-02 τ²-bench Banking 18% #20 of 26, top 77% high τ²-bench 2026-03-02 τ²-bench Retail 75.9% #5 of 7, top 72% high τ²-bench 2026-03-02 τ²-bench Telecom 91% #4 of 7, top 58% high τ²-bench 2026-03-02 DeepResearch Bench 46.3% #14 of 24, top 59% low Epoch AI BALROG 58.1% #4 of 35, top 12% Epoch AI LMArena Search 1207 #10 of 32, top 32% LMArena 2026-08-24 METR Time Horizons 71% #8 of 32, top 25% Epoch AI Vending-Bench 2 5,478 #24 of 60, top 40% Epoch AI
Reasoning Gemini 3 Pro Reasoning benchmark results Benchmark Score Position Setting Source Date ARC-AGI-2 31.1% #40 of 83, top 49% Epoch AI SimpleBench 76.4% #6 of 77, top 8% Epoch AI Kagi LLM Benchmark 80.1% #8 of 99, top 9% Kagi LLM Benchmark NYT Connections (extended) 94.4% #6 of 91, top 7% Lech Mazur benchmarks ARC-AGI-1 75% #41 of 83, top 50% Epoch AI CritPt 6.9% #55 of 134, top 42% Epoch AI Chess Puzzles 31% #33 of 129, top 26% Epoch AI 2025-12-08 EnigmaEval 18.2% #8 of 38, top 22% Epoch AI LMArena Hard Prompts 1480 #33 of 297, top 12% LMArena 2026-10-08 Epoch Capabilities Index 152.92 #42 of 213, top 20% Epoch AI 2025-11-18 ForecastBench 61.2 #14 of 72, top 20% Epoch AI
Math Knowledge Multimodal Multilingual Instruction Following Long Context Writing & Preference Frequently asked questions How good is Gemini 3 Pro? Gemini 3 Pro by Google ranks 28th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.8. Its strongest category is multimodal, where it ranks 2nd.
Is Gemini 3 Pro open source? No. Gemini 3 Pro is proprietary and available only through Google's API and partner platforms.
How fast is Gemini 3 Pro? Gemini 3 Pro generated about 1 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are Gemini 3 Pro's strengths and weaknesses? Relative to other ranked models, Gemini 3 Pro places best in multimodal, knowledge, multilingual and lowest in long context, math, agentic & tool use.
What is Gemini 3 Pro best at? Its best category is multimodal, where it ranks 2nd on Noometry.
Cite this page Noometry. (2026). Gemini 3 Pro benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/gemini-3-pro
Quote Noometry with a link back to this page. It is also available in Markdown .
Google