Gemini 3.1 Pro Preview leads on the shared-benchmark average
Ahead on 5 of 6 shared benchmarks, averaging 6.0 points higher
Summarised only from the 6 percentage-scale benchmarks scored by every selected model; details are below. A further 1 historical, reverse-direction or differently scaled metrics are excluded; indexes, cost and time are not added to accuracy percentages.
“Best available” takes each model’s best recorded non-parallel result in the metric’s stated direction per benchmark, so it may combine modes into a virtual configuration that does not exist. Read it with the mode breakdown.
Gemini 3.1 Pro Preview
Google Deep Mind
Gemini 3.0 Pro (Preview 11-2025)
Google Deep Mind
Benchmark-by-benchmark comparison. Changing the thinking mode or tool filters updates the chart and table below.
“Best available” picks the best non-parallel result in the metric’s stated direction separately for each benchmark. The resulting series can combine several reasoning levels and is not one reproducible runtime configuration. Choose a mode filter to compare like-for-like runs.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Each axis is the mean percentage score of one benchmark domain. It is an average, not a capability rating.
Relative edge: AI Agent - 工具使用 +10.4 / Relative gap: 数学推理 -1.6
Relative edge: 数学推理 +1.6 / Relative gap: AI Agent - 工具使用 -10.4
Method: for each model and benchmark, all scores in the current mode scope are averaged (not the best score), then those benchmark scores are averaged within each domain. Only benchmarks scored on a 0-100 scale by at least two of the selected models count — Elo and rating-scale benchmarks such as Codeforces or Arena are excluded, because averaging a 1500 rating with an 85% accuracy produces a meaningless number. Missing values are not counted as zero, and the averages are unweighted, so domains with harder benchmarks read lower.
Every model and runtime mode, benchmark by benchmark. Values are comparable along a row, not between different benchmarks.
15 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3.0 Pro (Preview 11-2025) |
|---|---|---|
77.10Thinking Level · High | 31.10Thinking Enabled | |
51.40Thinking Level · High ｜ Tools | 45.80Thinking Level · High ｜ Tools | |
77.13Thinking Level · High | 73.39Thinking Level · High | |
94.30Thinking Level · High | 91.90Thinking Enabled | |
91.70Thinking Level · High ｜ Tools | 92.00Thinking Enabled | |
80.60Thinking Level · High ｜ Tools | 76.20Thinking Enabled | |
79.60Standard Mode | 76.40Thinking Enabled | |
90.80Thinking Level · High ｜ Tools | 85.40Thinking Enabled ｜ Tools | |
99.30Thinking Level · High ｜ Tools | 98.00Thinking Level · High ｜ Tools | |
36.90Thinking Level · High | 38.00Thinking Enabled | |
16.70Standard Mode | 18.80Standard Mode | |
85.90Thinking Level · High ｜ Tools | 59.20Thinking Level · High ｜ Tools | |
78.20Thinking Level · High ｜ Tools | 70.30Standard Mode ｜ Tools | |
68.50Thinking Level · High ｜ Tools | 56.90Thinking Level · High ｜ Tools | |
86.70Thinking Enabled ｜ Tools | 70.70Thinking Enabled ｜ Tools |
Official list prices per model API, split by input and output. Unit: USD per 1M tokens.
Architecture, licensing and API modalities. "Not provided" means the field is missing from our database.
| Features & specs | Gemini 3.1 Pro PreviewGoogle Deep Mind | Gemini 3.0 Pro (Preview 11-2025)Google Deep Mind |
|---|---|---|
Core specsRelease | 2026-02-20 | 2025-11-18 |
Context length | 1M | 1000K |
Max output length | 65,536 tokens | 65,536 tokens |
Architecture | Undisclosed | Undisclosed |
Runtime modes | 低高 | 关闭16K32K4K64K8K开启深度 |
Availability & licensingCode availability | Not public | Not public |
Weight availability | Not public | Not public |
Use & commercial terms | Official service only; subject to provider terms | Official service only; subject to provider terms |
API modality supportText Input/Output | Input：YesOutput：Yes | Input：YesOutput：Yes |
Image Input/Output | Input：YesOutput：No | Input：YesOutput：No |
Audio Input/Output | Input：YesOutput：No | Input：YesOutput：Yes |
Video Input/Output | Input：YesOutput：No | Input：YesOutput：No |
ResourcesPaper / report | Gemini 3.1 Pro: A smarter model for your most complex tasks | A new era of intelligence with Gemini 3 |
DataLearner blog | Not provided | 大模型新王者！谷歌发布Gemini 3.0 Pro，各方面评测几乎都是第一，全球首个大模型匿名投票得分超1500分的模型，支持100万输入上下文！ |
