Compare / Gemini 3.1 Pro Preview vs Gemini 3 Pro Preview
Gemini 3.1 Pro Preview vs Gemini 3 Pro Preview
Which is cheaper, which is more capable, and which does better at each kind of work, from 28 results on 6 sources that measured both models.
Of the 28 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).
Gemini 3.1 Pro Preview or Gemini 3 Pro Preview? The short answer
They score and cost about the same: pick on the results below that match your work.
- Gemini 3.1 Pro Preview scores higher on the Artificial Analysis Intelligence Index: 29.7 against 28.0.
- Gemini 3.1 Pro Preview is newer: released 19 Feb 2026, against 18 Nov 2025 for Gemini 3 Pro Preview.
- On third-party benchmarks, on the results both models have: Gemini 3.1 Pro Preview does better for reasoning and knowledge and writing.
Head to head
Every fact side by side
| Gemini 3.1 Pro Preview | Gemini 3 Pro Preview | |
|---|---|---|
| Price per million tokens | $2.00 in · $12.00 out | Not on sale |
| Blended (3 in : 1 out) | $4.50 | – |
| Cheapest host, blended | $4.50 (Google) | – |
| Cached input, per million | $0.20 cached input | – |
| Intelligence Index | 29.7 | 28.0 |
| Spring Prompt overall | 46 | – |
| Output speed, tokens a second | 130 | – |
| Context window | 1,048,576 tokens | – |
| Released | 19 Feb 2026 (newer) | 18 Nov 2025 |
| Weights | Closed | Closed |
| Developer based in | the US | the US |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
From our research
- Gemini 4 Argon review: Opus-level product data at a quarter of the cost, until you ask it to sell 14 Oct 2026
- BulletBench: we made 23 AI models play speed chess, and the clock was the judge 3 Jul 2026
- Claude vs Gemini vs GPT in a 12-Month Marketing Simulation 25 Mar 2026
- The AI Marketing Benchmark That Punishes Plausible-Sounding Strategy 20 Mar 2026
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | Gemini 3.1 Pro Preview | Gemini 3 Pro Preview |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 15 · 16 of 387 measured | 1,487 | 1,485 |
| Overall · Text factualityArena rating, higher is better 21 · 11 of 163 measured | 1,472 | 1,481 |
| Business, management and finance · TextArena rating, higher is better 23 · 28 of 380 measured | 1,477 | 1,474 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 57 · 63 of 249 measured | 29.7 | 28.0high reasoning |
| GPQA Diamond% of questions, higher is better 5 · 35 of 232 measured | 94.1% | 90.8%high reasoning |
| Humanity's Last Exam% of questions, higher is better 19 · 48 of 250 measured | 47.0% | 39.7%high reasoning |
| OpenHands Index reported by OpenHands Index · 3 results | ||
| Average% resolved, higher is better 9 · 19 of 34 measured | 60.6%openhands | 49.0%openhands |
| Front end (SWE-Bench Multimodal)% resolved, higher is better 4 · 11 of 34 measured | 44.1%openhands | 36.8%openhands |
| Greenfield (Commit0)% resolved, higher is better 14 · 14 of 34 measured | 25.0%openhands | 25.0%openhands |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 5 · 25 of 230 measured | 72.2low reasoning | 66.7high reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 99 · 176 of 230 measured | 19.0%low reasoning | 33.0%low reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 122 · 49 of 230 measured | 0.34low reasoning | 0.37high reasoning |
| Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results | ||
| Hallucination rate · Vectara% of summaries, lower is better 61 · 87 of 104 measured | 10.4% | 13.6% |
| Answer rate · Vectara% of documents, higher is better 55 · 55 of 104 measured | 99.4% | 99.4% |
| Vending-Bench 2 reported by Vending-Bench 2 · 1 result | ||
| Money after a yearUS dollars, higher is better 45 · 21 of 58 measured | $911.21 | $5,478 |
Show all 28 results (13 more)
| Measure | Gemini 3.1 Pro Preview | Gemini 3 Pro Preview |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 6 results | ||
| Creative writing · TextArena rating, higher is better 10 · 8 of 385 measured | 1,480 | 1,484 |
| Expert prompts · TextArena rating, higher is better 26 · 39 of 338 measured | 1,509 | 1,498 |
| Instruction following · TextArena rating, higher is better 17 · 26 of 387 measured | 1,480 | 1,473 |
| Overall · DocumentArena rating, higher is better 23 · 26 of 38 measured | 1,459 | 1,451 |
| Overall · SearchArena rating, higher is better 6 · 9 of 33 measured | 1,208arena search | 1,201arena search |
| Writing, literature and language · TextArena rating, higher is better 11 · 10 of 386 measured | 1,480 | 1,481 |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| IFBench% of instructions, higher is better 13 · 52 of 195 measured | 77.1% | 70.4%high reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 27 · 80 of 241 measured | 82.0% | 76.0%high reasoning |
| Terminal-Bench Hard% of tasks, higher is better 8 · 32 of 190 measured | 53.8% | 41.7%high reasoning |
| τ²-bench telecom% of tasks, higher is better 16 · 49 of 193 measured | 95.6% | 87.1%high reasoning |
| OpenHands Index reported by OpenHands Index · 3 results | ||
| Information gathering (GAIA)% resolved, higher is better 4 · 25 of 34 measured | 81.8%openhands | 44.2%openhands |
| Issue resolution (SWE-Bench)% resolved, higher is better 6 · 25 of 34 measured | 76.8%openhands | 70.6%openhands |
| Testing (SWT-Bench)% resolved, higher is better 9 · 17 of 34 measured | 75.1%openhands | 68.6%openhands |
Compare them with other models
Quick answers
Is Gemini 3.1 Pro Preview better than Gemini 3 Pro Preview?
They score and cost about the same: pick on the results below that match your work.
Which is better for agents and tool use, Gemini 3.1 Pro Preview or Gemini 3 Pro Preview?
Gemini 3.1 Pro Preview ranks 66 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 82 for Gemini 3 Pro Preview.
Which is better for professional work, Gemini 3.1 Pro Preview or Gemini 3 Pro Preview?
Gemini 3.1 Pro Preview ranks 36 of 51 models on sale for real tasks from banking, consulting and law, business documents and freelance projects, against 45 for Gemini 3 Pro Preview.
Which is better for reasoning and knowledge, Gemini 3.1 Pro Preview or Gemini 3 Pro Preview?
Gemini 3.1 Pro Preview ranks 29 of 187 models on sale for hard questions across science, maths and general knowledge, against 51 for Gemini 3 Pro Preview.
Which is better for writing, Gemini 3.1 Pro Preview or Gemini 3 Pro Preview?
Gemini 3.1 Pro Preview ranks 9 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 21 for Gemini 3 Pro Preview.
Which is better for sticking to the facts, Gemini 3.1 Pro Preview or Gemini 3 Pro Preview?
Gemini 3.1 Pro Preview ranks 33 of 139 models on sale for summarising without inventing things, and factual answers, against 62 for Gemini 3 Pro Preview.
Run Gemini 3.1 Pro Preview and Gemini 3 Pro Preview on your own prompt.
Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.