Gemini 2.5 Flash Lite vs Qwen3 30B A3B
Gemini 2.5 Flash Lite leads Qwen3 30B A3B on the Artificial Analysis Intelligence Index, 10.4 to 7.6, and Gemini 2.5 Flash Lite costs 1.3x less per output token ($0.40 vs $0.50 per million). Updated October 22, 2026; 14 benchmarks have a result for both.
Gemini 2.5 Flash Lite or Qwen3 30B A3B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Gemini 2.5 Flash Lite for output tokens 1.3x cheaper ($0.40 vs $0.50 per million) and a larger context window (1.05M against 41K tokens).
- Shared results
- 14
- Gemini 2.5 Flash Lite only
- 16
- Qwen3 30B A3B only
- 38
- Like-for-like categories
- 7 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
Gemini 2.5 Flash Lite
Gemini 2.5 Flash Lite leads, 10.4 against 7.6.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Gemini 2.5 Flash Lite has a GPQA Diamond result, 70.2%.
Directional only
Math
AIME
No call
Only Gemini 2.5 Flash Lite has a AIME result, 42.1%.
Directional only
Knowledge
MMLU Pro
No call
Only Gemini 2.5 Flash Lite has a MMLU Pro result, 79.1%.
Directional only
Web design
Design Arena: websites
No call
Only Qwen3 30B A3B has a Design Arena: websites result, 954.
Directional only
Long documents
Listed context window
Gemini 2.5 Flash Lite
Gemini 2.5 Flash Lite takes 1.05M tokens against 41K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 2.5 Flash Lite
Gemini 2.5 Flash Lite $0.0003, Qwen3 30B A3B $0.0004 per turn.
List prices
At a glance
- Coding index
- Gemini 2.5 Flash Lite not benchmarked, Qwen3 30B A3B not benchmarked.
- Widest category
- Math, 19.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- Long context reasoning (AA-LCR): Gemini 2.5 Flash Lite 55.7% against Qwen3 30B A3B 0.0%, 55.7 points apart on a 0 to 100 scale.
- Output price
- Gemini 2.5 Flash Lite $0.40 against Qwen3 30B A3B $0.50 per million output tokens, 1.3x apart.
- Context window
- Gemini 2.5 Flash Lite takes 1.05M tokens, Qwen3 30B A3B 41K.
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 | Gemini 2.5 Flash Lite | Bars | Qwen3 30B A3B | Ties |
|---|---|---|---|---|
| Coding | 1 | 1 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 2 | 0 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 1 | ||
| General | 4 | 0 | ||
| All shared boards | 8 | 6 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index11
| Benchmark | Gemini 2.5 Flash Lite | Qwen3 30B A3B | Leader |
|---|---|---|---|
| LiveCodeBench (Vals AI) | 71.4% | Not measured | Only Gemini 2.5 Flash Lite measured |
| LiveCodeBench (Artificial Analysis run) | 59.3% | 50.6% | Gemini 2.5 Flash Lite |
| Terminal-Bench Hard (Artificial Analysis run) | 4.5% | 6.8% | Qwen3 30B A3B |
| WeirdML | Not measured | 29.8% | Only Qwen3 30B A3B measured |
| LMArena Text: coding | Not measured | 1337 | Only Qwen3 30B A3B measured |
| LMArena Text: software and IT | Not measured | 1340 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Gemini 2.5 Flash Lite | Qwen3 30B A3B | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.4 | 7.6 | Gemini 2.5 Flash Lite |
| Epoch Capabilities Index | 133.8 | 137.3 | Qwen3 30B A3B |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemini 2.5 Flash Lite | Qwen3 30B A3B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 19.0% | 26.0% | Qwen3 30B A3B |
| Berkeley Function Calling Leaderboard (BFCL) | 36.9% | Not measured | Only Gemini 2.5 Flash Lite measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 2.5 Flash Lite | Qwen3 30B A3B | Leader |
|---|---|---|---|
| GPQA Diamond | 70.2% | Not measured | Only Gemini 2.5 Flash Lite measured |
| MMMU Pro (Vals AI) | 75.4% | Not measured | Only Gemini 2.5 Flash Lite measured |
| GPQA Diamond (Artificial Analysis run) | 62.5% | 61.6% | Gemini 2.5 Flash Lite |
| Humanity's Last Exam (Artificial Analysis run) | 6.8% | 6.2% | Gemini 2.5 Flash Lite |
| GPQA Diamond (Epoch AI run) | Not measured | 61.7% | Only Qwen3 30B A3B measured |
| LMArena Text: hard prompts | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: expert | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: hard prompts in English | Not measured | 1329 | Only Qwen3 30B A3B measured |
| Kagi LLM Benchmark | 40.5% | Not measured | Only Gemini 2.5 Flash Lite measured |
| Neither model has a result on the other 13 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemini 2.5 Flash Lite | Qwen3 30B A3B | Leader |
|---|---|---|---|
| AIME | 42.1% | Not measured | Only Gemini 2.5 Flash Lite measured |
| MGSM (Vals AI) | 89.5% | Not measured | Only Gemini 2.5 Flash Lite measured |
| AA Math Index | 53.3 | 72.3 | Qwen3 30B A3B |
| AIME 2025 (Artificial Analysis run) | 53.3% | 72.3% | Qwen3 30B A3B |
| OTIS Mock AIME | Not measured | 62.8% | Only Qwen3 30B A3B measured |
| LMArena Text: math | Not measured | 1355 | Only Qwen3 30B A3B measured |
| LMArena Text: mathematical work | Not measured | 1363 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemini 2.5 Flash Lite | Qwen3 30B A3B | Leader |
|---|---|---|---|
| MMLU Pro | 79.1% | Not measured | Only Gemini 2.5 Flash Lite measured |
| LegalBench (Vals AI) | 82.0% | Not measured | Only Gemini 2.5 Flash Lite measured |
| CorpFin (Vals AI) | 57.6% | Not measured | Only Gemini 2.5 Flash Lite measured |
| TaxEval (Vals AI) | 66.2% | Not measured | Only Gemini 2.5 Flash Lite measured |
| MortgageTax (Vals AI) | 57.6% | Not measured | Only Gemini 2.5 Flash Lite measured |
| MedQA (Vals AI) | 88.9% | Not measured | Only Gemini 2.5 Flash Lite measured |
| MedCode (Vals AI) | 34.2% | Not measured | Only Gemini 2.5 Flash Lite measured |
| MMLU Pro (Artificial Analysis run) | 75.9% | 77.7% | Qwen3 30B A3B |
| LMArena Text: science | Not measured | 1321 | Only Qwen3 30B A3B measured |
| LMArena Text: medicine and healthcare | Not measured | 1318 | Only Qwen3 30B A3B measured |
| LMArena Text: legal and government | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: business and finance | Not measured | 1309 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Gemini 2.5 Flash Lite | Qwen3 30B A3B | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 954 | Only Qwen3 30B A3B measured |
| Design Arena: UI components | Not measured | 943 | Only Qwen3 30B A3B measured |
| Design Arena: game dev | Not measured | 898 | Only Qwen3 30B A3B measured |
| Design Arena: data viz | Not measured | 967 | Only Qwen3 30B A3B measured |
| Design Arena: all code categories | Not measured | 941 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 4 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Gemini 2.5 Flash Lite | Qwen3 30B A3B | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 30.8% | Not measured | Only Gemini 2.5 Flash Lite measured |
| MedScribe (Vals AI) | 75.8% | Not measured | Only Gemini 2.5 Flash Lite measured |
| IFBench | 49.9% | 41.5% | Gemini 2.5 Flash Lite |
| Long context reasoning (AA-LCR) | 55.7% | 0.0% | Gemini 2.5 Flash Lite |
| DTBench | 62.8% | 60.3% | Gemini 2.5 Flash Lite |
| LMCA | 18.1% | 15.8% | Gemini 2.5 Flash Lite |
| Fiction.LiveBench | Not measured | 40.6% | Only Qwen3 30B A3B measured |
| Creative writing (Lech Mazur) | Not measured | 75.3% | Only Qwen3 30B A3B measured |
| LMArena Text | Not measured | 1317 | Only Qwen3 30B A3B measured |
| LMArena Text: instruction following | Not measured | 1283 | Only Qwen3 30B A3B measured |
| LMArena Text: creative writing | Not measured | 1271 | Only Qwen3 30B A3B measured |
| LMArena Text: English | Not measured | 1335 | Only Qwen3 30B A3B measured |
| LMArena Text: non-English | Not measured | 1295 | Only Qwen3 30B A3B measured |
| LMArena Text: Chinese | Not measured | 1347 | Only Qwen3 30B A3B measured |
| LMArena Text: German | Not measured | 1307 | Only Qwen3 30B A3B measured |
| LMArena Text: Japanese | Not measured | 1254 | Only Qwen3 30B A3B measured |
| LMArena Text: Korean | Not measured | 1261 | Only Qwen3 30B A3B measured |
| LMArena Text: French | Not measured | 1352 | Only Qwen3 30B A3B measured |
| LMArena Text: Spanish | Not measured | 1317 | Only Qwen3 30B A3B measured |
| LMArena Text: Russian | Not measured | 1291 | Only Qwen3 30B A3B measured |
| LMArena Text: Polish | Not measured | 1299 | Only Qwen3 30B A3B measured |
| LMArena Text: multi-turn | Not measured | 1307 | Only Qwen3 30B A3B measured |
| LMArena Text: longer queries | Not measured | 1312 | Only Qwen3 30B A3B measured |
| LMArena Text: writing and language | Not measured | 1290 | Only Qwen3 30B A3B measured |
| LMArena Text: entertainment and media | Not measured | 1258 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 2.5 Flash Lite | Qwen3 30B A3B | 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
Gemini 2.5 Flash Lite costs less
Repository review
50K input + 3K output tokens
Gemini 2.5 Flash Lite costs less
Agent loop
200K input + 10K output tokens
Gemini 2.5 Flash Lite 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 Gemini 2.5 Flash Lite | Qwen3 30B A3B |
|---|---|---|
| Maker | Qwen | |
| Weights | No public weights listed | Open weights |
| Released | July 22, 2025 | April 28, 2025 |
| Context window | 1.05M | 41K |
| Input $/Mtok | $0.10 | $0.12 |
| Output $/Mtok | $0.40 | $0.50 |
| 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 Gemini 2.5 Flash Lite better than Qwen3 30B A3B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemini 2.5 Flash Lite for output tokens 1.3x cheaper ($0.40 vs $0.50 per million) and a larger context window (1.05M against 41K tokens).
Which is cheaper, Gemini 2.5 Flash Lite or Qwen3 30B A3B?
Gemini 2.5 Flash Lite costs $0.10 per million input tokens and $0.40 per million output tokens; Qwen3 30B A3B costs $0.12 and $0.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemini 2.5 Flash Lite or Qwen3 30B A3B?
Gemini 2.5 Flash Lite, with 1.05M tokens against 41K.
How many benchmarks is the Gemini 2.5 Flash Lite vs Qwen3 30B A3B comparison based on?
14 benchmarks have a result for both models as of October 22, 2026. Gemini 2.5 Flash Lite's coding index rests on 0 independent benchmarks and Qwen3 30B A3B's on 0. Where only one model has a result, the page says so instead of naming a winner.