Gemma 3 4B vs Qwen2.5 VL 72B Instruct
Gemma 3 4B costs 13.3x less per output token than Qwen2.5 VL 72B Instruct ($0.075 vs $1.00 per million). Updated October 22, 2026; 1 benchmarks have a result for both.
Gemma 3 4B or Qwen2.5 VL 72B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Gemma 3 4B for output tokens 13.3x cheaper ($0.075 vs $1.00 per million) and a larger context window (131K against 128K tokens).
- Shared results
- 1
- Gemma 3 4B only
- 41
- Qwen2.5 VL 72B Instruct only
- 5
- Like-for-like categories
- 1 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Gemma 3 4B has a AA Intelligence Index result, 4.8.
Directional only
Long documents
Listed context window
Gemma 3 4B
Gemma 3 4B takes 131K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 3 4B
Gemma 3 4B $0.0001, Qwen2.5 VL 72B Instruct $0.0013 per turn.
List prices
At a glance
- Coding index
- Gemma 3 4B not benchmarked, Qwen2.5 VL 72B Instruct not benchmarked.
- Widest category
- Reasoning, 10.8 points apart on average over 1 shared benchmark.
- Widest single gap
- Kagi LLM Benchmark: Gemma 3 4B 25.2% against Qwen2.5 VL 72B Instruct 36.0%, 10.8 points apart on a 0 to 100 scale.
- Output price
- Gemma 3 4B $0.075 against Qwen2.5 VL 72B Instruct $1.00 per million output tokens, 13.3x apart.
- Context window
- Gemma 3 4B takes 131K tokens, Qwen2.5 VL 72B Instruct 128K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemma 3 4B | Bars | Qwen2.5 VL 72B Instruct | Ties |
|---|---|---|---|---|
| Reasoning | 0 | 1 | ||
| All shared boards | 0 | 1 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index6 boards, none shared
| Benchmark | Gemma 3 4B | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| AA Coding Index | 2.7 | Not measured | Only Gemma 3 4B measured |
| LiveCodeBench (Artificial Analysis run) | 11.2% | Not measured | Only Gemma 3 4B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 0.8% | Not measured | Only Gemma 3 4B measured |
| LMArena Text: coding | 1230 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: software and IT | 1269 | Not measured | Only Gemma 3 4B measured |
| SciCode | 0.0% | Not measured | Only Gemma 3 4B measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Gemma 3 4B | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 4.8 | Not measured | Only Gemma 3 4B measured |
| Epoch Capabilities Index | 115.9 | Not measured | Only Gemma 3 4B measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Gemma 3 4B | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 5.0% | Not measured | Only Gemma 3 4B measured |
| OSWorld | Not measured | 5.0% | Only Qwen2.5 VL 72B Instruct measured |
| Berkeley Function Calling Leaderboard (BFCL) | 19.6% | Not measured | Only Gemma 3 4B measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 3 4B | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 29.1% | Not measured | Only Gemma 3 4B measured |
| Humanity's Last Exam (Artificial Analysis run) | 5.3% | Not measured | Only Gemma 3 4B measured |
| GPQA Diamond (Epoch AI run) | 23.2% | Not measured | Only Gemma 3 4B measured |
| LMArena Text: hard prompts | 1253 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: expert | 1223 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: hard prompts in English | 1253 | Not measured | Only Gemma 3 4B measured |
| Kagi LLM Benchmark | 25.2% | 36.0% | Qwen2.5 VL 72B Instruct |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Gemma 3 4B | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| AA Math Index | 12.7 | Not measured | Only Gemma 3 4B measured |
| AIME 2025 (Artificial Analysis run) | 12.7% | Not measured | Only Gemma 3 4B measured |
| OTIS Mock AIME | 7.5% | Not measured | Only Gemma 3 4B measured |
| LMArena Text: math | 1239 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: mathematical work | 1256 | Not measured | Only Gemma 3 4B measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Gemma 3 4B | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 41.7% | Not measured | Only Gemma 3 4B measured |
| GeoBench | Not measured | 62.0% | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Text: science | 1306 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: medicine and healthcare | 1342 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: legal and government | 1327 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: business and finance | 1311 | Not measured | Only Gemma 3 4B measured |
| Neither model has a result on the other 12 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 3 4B | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index18 boards, none shared
| Benchmark | Gemma 3 4B | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| IFBench | 28.3% | Not measured | Only Gemma 3 4B measured |
| Long context reasoning (AA-LCR) | 6.7% | Not measured | Only Gemma 3 4B measured |
| DTBench | 50.9% | Not measured | Only Gemma 3 4B measured |
| LMCA | 2.8% | Not measured | Only Gemma 3 4B measured |
| LMArena Text | 1291 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: instruction following | 1239 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: creative writing | 1270 | Not measured | Only Gemma 3 4B measured |
| LMArena Vision | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Text: English | 1300 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: non-English | 1273 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: German | 1281 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: Russian | 1294 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: multi-turn | 1255 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: longer queries | 1273 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: writing and language | 1288 | Not measured | Only Gemma 3 4B measured |
| LMArena Text: entertainment and media | 1233 | Not measured | Only Gemma 3 4B measured |
| LMArena Vision: English | Not measured | 1115 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Vision: Chinese | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 28 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 3 4B | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemma 3 4B costs less
Repository review
50K input + 3K output tokens
Gemma 3 4B costs less
Agent loop
200K input + 10K output tokens
Gemma 3 4B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemma 3 4B | Qwen2.5 VL 72B Instruct |
|---|---|---|
| Maker | Qwen | |
| Weights | Open weights | Open weights |
| Released | March 13, 2025 | February 1, 2025 |
| Context window | 131K | 128K |
| Input $/Mtok | $0.045 | $0.80 |
| Output $/Mtok | $0.075 | $1.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 3 4B better than Qwen2.5 VL 72B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 4B for output tokens 13.3x cheaper ($0.075 vs $1.00 per million) and a larger context window (131K against 128K tokens).
Which is cheaper, Gemma 3 4B or Qwen2.5 VL 72B Instruct?
Gemma 3 4B costs $0.045 per million input tokens and $0.075 per million output tokens; Qwen2.5 VL 72B Instruct costs $0.80 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 3 4B or Qwen2.5 VL 72B Instruct?
Gemma 3 4B, with 131K tokens against 128K.
How many benchmarks is the Gemma 3 4B vs Qwen2.5 VL 72B Instruct comparison based on?
1 benchmarks have a result for both models as of October 22, 2026. Gemma 3 4B's coding index rests on 0 independent benchmarks and Qwen2.5 VL 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.