Compare / Gemini 2.5 Pro vs Gemini 3.8 Flash

Gemini 2.5 Pro vs Gemini 3.8 Flash

Which is cheaper, which is more capable, and which does better at each kind of work, from 20 results on 4 sources that measured both models.

GoogleGemini 2.5 Pro Released 25 Mar 2025 · $1.25 in · $10.00 out
GoogleGemini 3.8 Flash Released 2 Sep 2026 · $1.50 in · $7.50 out
Gemini 2.5 Pro wins 1Gemini 3.8 Flash wins 19

Of the 20 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331).

Gemini 2.5 Pro or Gemini 3.8 Flash? The short answer

Pick Gemini 3.8 Flash: it scores higher (Intelligence Index 40.9 against 16.1) at about the same price.

  • They cost about the same: $3.44 and $3.00 per million tokens (three input to one output).
  • Gemini 3.8 Flash scores higher on the Artificial Analysis Intelligence Index: 40.9 against 16.1.
  • Gemini 3.8 Flash is newer: released 2 Sep 2026, against 25 Mar 2025 for Gemini 2.5 Pro.
  • On third-party benchmarks, on the results both models have: Gemini 3.8 Flash does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.

Head to head

16.1
Intelligence Index
40.9
$3.44
Price per million tokens, blendedlower is better
$3.00
1,048,576
Context window, tokens
1,048,576

Every fact side by side

Gemini 2.5 ProGemini 3.8 Flash
Price per million tokens$1.25 in · $10.00 out$1.50 in · $7.50 out
Blended (3 in : 1 out)$3.44$3.00
Cheapest host, blended–$1.50 (Google)
Cached input, per million$0.12 cached input–
Intelligence Index16.140.9
Spring Prompt overall–57
Output speed, tokens a second–141
Context window1,048,576 tokens1,048,576 tokens
Released25 Mar 20252 Sep 2026 (newer)
WeightsClosedClosed
Developer based inthe USthe 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.

Product listingsTurning a sparse product feed and photos into listings that can go live not measured 25 of 35
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 29 of 35
User surveysPlanning a user survey and reading its results without being misled not measured 18 of 26
Marketing planningPlanning a year of ad spend without overspending not measured 13 of 35
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 118 of 159 35 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 11 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 102 of 187 15 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 44 of 169 3 of 169
Sticking to the factsSummarising without inventing things, and factual answers 39 of 139 12 of 139
Speed under pressureGood decisions against a real clock (fast chess) not measured 14 of 38

From our research

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.

MeasureGemini 2.5 ProGemini 3.8 Flash
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 74 · 7 of 387 measured 1,446 1,495high reasoning
Overall · Text factualityArena rating, higher is better 38 · 16 of 163 measured 1,462 1,477high reasoning
Business, management and finance · TextArena rating, higher is better 92 · 21 of 380 measured 1,437 1,481high reasoning
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 128 · 25 of 249 measured 16.1 40.9high reasoning
GPQA Diamond% of questions, higher is better 87 · 2 of 232 measured 84.4% 95.3%high reasoning
Humanity's Last Exam% of questions, higher is better 108 · 18 of 250 measured 22.5% 47.8%high reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 28 · 1 of 230 measured 65.2 78.6medium reasoning
Requested-length error · UGI% off the requested word count, lower is better 99 · 57 of 230 measured 19.0% 13.0%high reasoning
Style adherence · UGIscore from 0 to 1, higher is better 16 · 132 of 230 measured 0.40 0.34high reasoning
Vending-Bench 2 reported by Vending-Bench 2 · 1 result
Money after a yearUS dollars, higher is better 46 · 26 of 58 measured $573.64 $5,094
Show all 20 results (10 more)
MeasureGemini 2.5 ProGemini 3.8 Flash
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 45 · 7 of 385 measured 1,443 1,485high reasoning
Expert prompts · TextArena rating, higher is better 91 · 13 of 338 measured 1,458 1,526high reasoning
Instruction following · TextArena rating, higher is better 70 · 12 of 387 measured 1,438 1,486high reasoning
Writing, literature and language · TextArena rating, higher is better 53 · 8 of 386 measured 1,445 1,487high reasoning
Artificial Analysis reported by Artificial Analysis · 6 results
Terminal-Bench 2.1% of tasks, higher is better 85 · 8 of 131 measured 28.5% 87.6%high reasoning
Terminal-Bench 4.0% of tasks, higher is better 72 · 30 of 120 measured 0.0% 19.7%high reasoning
τ-bench banking% of tasks, higher is better 79 · 11 of 121 measured 9.7% 45.8%medium reasoning
Artificial Analysis Coding Indexindex score, higher is better 81 · 9 of 130 measured 33.3 76.3high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 123 · 7 of 241 measured 69.0% 84.0%medium reasoning
SciCode% of problems, higher is better 69 · 20 of 121 measured 46.3% 56.6%high reasoning

Quick answers

Is Gemini 2.5 Pro better than Gemini 3.8 Flash?

Pick Gemini 3.8 Flash: it scores higher (Intelligence Index 40.9 against 16.1) at about the same price.

Which is cheaper, Gemini 2.5 Pro or Gemini 3.8 Flash?

They cost about the same: $3.44 and $3.00 per million tokens (three input to one output).

Which is better for agents and tool use, Gemini 2.5 Pro or Gemini 3.8 Flash?

Gemini 3.8 Flash ranks 35 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 118 for Gemini 2.5 Pro.

Which is better for reasoning and knowledge, Gemini 2.5 Pro or Gemini 3.8 Flash?

Gemini 3.8 Flash ranks 15 of 187 models on sale for hard questions across science, maths and general knowledge, against 102 for Gemini 2.5 Pro.

Which is better for writing, Gemini 2.5 Pro or Gemini 3.8 Flash?

Gemini 3.8 Flash ranks 3 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 44 for Gemini 2.5 Pro.

Which is better for sticking to the facts, Gemini 2.5 Pro or Gemini 3.8 Flash?

Gemini 3.8 Flash ranks 12 of 139 models on sale for summarising without inventing things, and factual answers, against 39 for Gemini 2.5 Pro.

Run Gemini 2.5 Pro and Gemini 3.8 Flash 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.