Compare / Gemini 2.5 Flash-Lite vs Gemma 3 4B

Gemini 2.5 Flash-Lite vs Gemma 3 4B

Which is cheaper, which is more capable, and which does better at each kind of work, from 17 results on 3 sources that measured both models.

GoogleGemini 2.5 Flash-Lite Released 17 Jun 2025 · $0.10 in · $0.40 out
GoogleGemma 3 4B Released 11 Mar 2025 · $0.040 in · $0.050 out
Gemini 2.5 Flash-Lite wins 16Gemma 3 4B wins 1

Of the 17 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 Flash-Lite or Gemma 3 4B? The short answer

Pick Gemini 2.5 Flash-Lite if quality matters most: it scores higher (Intelligence Index 8.5 against 4.8). Pick Gemma 3 4B if cost matters more: it costs 4.1 times less per token.

  • Gemma 3 4B is cheaper: $0.042 against $0.18 per million tokens, 4.1 times less.
  • Gemini 2.5 Flash-Lite scores higher on the Artificial Analysis Intelligence Index: 8.5 against 4.8.
  • Gemini 2.5 Flash-Lite is newer: released 17 Jun 2025, against 11 Mar 2025 for Gemma 3 4B.
  • On third-party benchmarks, on the results both models have: Gemini 2.5 Flash-Lite does better for agents and tool use, reasoning and knowledge and sticking to the facts.

Head to head

8.5
Intelligence Index
4.8
$0.18
Price per million tokens, blendedlower is better
$0.042
1,048,576
Context window, tokens
131,072

Every fact side by side

Gemini 2.5 Flash-LiteGemma 3 4B
Price per million tokens$0.10 in · $0.40 out$0.040 in · $0.050 out
Blended (3 in : 1 out)$0.18$0.042
Cheapest host, blended–$0.042 (Parasail, BF16)
Cached input, per million$0.010 cached input–
Intelligence Index8.54.8
Spring Prompt overall––
Output speed, tokens a second––
Context window1,048,576 tokens131,072 tokens
Released17 Jun 2025 (newer)11 Mar 2025
WeightsClosedOpen
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.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 89 of 159 158 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 147 of 187 181 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality not measured 157 of 169
Sticking to the factsSummarising without inventing things, and factual answers 2 of 139 32 of 139

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 Flash-LiteGemma 3 4B
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 196 · 246 of 249 measured 8.5thinking reasoning 4.8
GPQA Diamond% of questions, higher is better 177 · 227 of 232 measured 62.5%thinking reasoning 29.1%
Humanity's Last Exam% of questions, higher is better 182 · 194 of 250 measured 6.8%thinking reasoning 5.3%
Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 3 results
Overall accuracy · BFCL% correct, higher is better 39 · 74 of 81 measured 36.9%bfcl fc 19.6%bfcl prompt
Irrelevance detection · BFCL% correct, higher is better 7 · 71 of 81 measured 93.3%bfcl prompt 53.9%bfcl prompt
Memory · BFCL% correct, higher is better 31 · 53 of 81 measured 20.7%bfcl fc 8.6%bfcl prompt
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 3 · 28 of 104 measured 3.3% 6.4%
Answer rate · Vectara% of documents, higher is better 50 · 103 of 104 measured 99.5% 67.3%
Show all 17 results (9 more)
MeasureGemini 2.5 Flash-LiteGemma 3 4B
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 106 · 187 of 195 measured 49.9%thinking reasoning 28.3%
Long-context reasoning (AA-LCR)% of questions, higher is better 150 · 226 of 241 measured 55.7%thinking reasoning 6.7%
Terminal-Bench Hard% of tasks, higher is better 156 · 180 of 190 measured 4.5%thinking reasoning 0.8%
τ²-bench telecom% of tasks, higher is better 169 · 187 of 193 measured 19.0%no reasoning 5.0%
Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 5 results
Multi-turn tasks · BFCL% correct, higher is better 47 · 75 of 81 measured 13.5%bfcl fc 0.4%bfcl prompt
Relevance detection · BFCL% correct, higher is better 74 · 1 of 81 measured 50.0%bfcl prompt 100.0%bfcl prompt
Single-turn calls (curated) · BFCL% correct, higher is better 29 · 74 of 81 measured 86.6%bfcl fc 61.1%bfcl prompt
Single-turn calls (user-contributed) · BFCL% correct, higher is better 60 · 64 of 81 measured 65.8%bfcl fc 60.8%bfcl prompt
Web search · BFCL% correct, higher is better 32 · 56 of 81 measured 21.0%bfcl fc 1.0%bfcl prompt

Quick answers

Is Gemini 2.5 Flash-Lite better than Gemma 3 4B?

Pick Gemini 2.5 Flash-Lite if quality matters most: it scores higher (Intelligence Index 8.5 against 4.8). Pick Gemma 3 4B if cost matters more: it costs 4.1 times less per token.

Which is cheaper, Gemini 2.5 Flash-Lite or Gemma 3 4B?

Gemma 3 4B is cheaper: $0.042 against $0.18 per million tokens, 4.1 times less.

Which is better for agents and tool use, Gemini 2.5 Flash-Lite or Gemma 3 4B?

Gemini 2.5 Flash-Lite ranks 89 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 158 for Gemma 3 4B.

Which is better for reasoning and knowledge, Gemini 2.5 Flash-Lite or Gemma 3 4B?

Gemini 2.5 Flash-Lite ranks 147 of 187 models on sale for hard questions across science, maths and general knowledge, against 181 for Gemma 3 4B.

Which is better for sticking to the facts, Gemini 2.5 Flash-Lite or Gemma 3 4B?

Gemini 2.5 Flash-Lite ranks 2 of 139 models on sale for summarising without inventing things, and factual answers, against 32 for Gemma 3 4B.

Which has the bigger context window, Gemini 2.5 Flash-Lite or Gemma 3 4B?

Gemini 2.5 Flash-Lite: 1,048,576 tokens, against 131,072 for Gemma 3 4B.

Run Gemini 2.5 Flash-Lite and Gemma 3 4B 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.