Model comparison
Gemini 2.5 Flash-Lite vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 36.4 on the Noometry Index.
Last verified . 24 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 3 categories and Qwen3-30B-A3B in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-30B-A3B leads 41.7 to 32.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 40.5% for Gemini 2.5 Flash-Lite and 54.9% for Qwen3-30B-A3B.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash-Lite | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 36.4 | 38.5 |
| Released | 2025-06-17 | 2025-04-28 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 41K |
| Max output | 66K | 16K |
| Input $ / M tokens | $0.10 | $0.12 |
| Output $ / M tokens | $0.40 | $0.50 |
| Results tracked | 33 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 2.5 Flash-Lite: 38.0 (#167), Qwen3-30B-A3B: 37.0 (#188)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| WeirdML | 35.2% | 29.8% |
| LMArena Coding | 1373 | 1416 |
| SciCode | — | 33.3% |
| ALE-Bench | 325.9 | — |
Agentic & Tool Use Qwen3-30B-A3B leads
Gemini 2.5 Flash-Lite: 27.8 (#89), Qwen3-30B-A3B: 29.5 (#75)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | 41.4% |
Reasoning Too close to call
Gemini 2.5 Flash-Lite: 21.5 (#196), Qwen3-30B-A3B: 21.6 (#193)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 54.9% |
| LMArena Hard Prompts | 1377 | 1398 |
| DTBench | 62.8% | 69.3% |
| LMCA | 18.1% | 22.4% |
| Epoch Capabilities Index | 133.93 | 139.63 |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
Math Too close to call
Gemini 2.5 Flash-Lite: 35.5 (#144), Qwen3-30B-A3B: 36.0 (#133)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1373 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| Omni-MATH | 48% | — |
Knowledge Qwen3-30B-A3B leads
Gemini 2.5 Flash-Lite: 32.1 (#206), Qwen3-30B-A3B: 41.7 (#96)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1373 | 1395 |
| GPQA Diamond | — | 70.1% |
| MMLU-Pro | 53.7% | — |
| Confabulations | — | 12.3% |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
Multimodal Not comparable
Gemini 2.5 Flash-Lite: 28.6 (#109), Qwen3-30B-A3B: —
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
Multilingual Too close to call
Gemini 2.5 Flash-Lite: 49.5 (#129), Qwen3-30B-A3B: 49.8 (#126)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1369 | 1372 |
| LMArena Chinese | 1404 | 1434 |
| LMArena French | 1388 | 1419 |
| LMArena German | 1390 | 1379 |
| LMArena Japanese | 1359 | 1338 |
| LMArena Korean | 1358 | 1333 |
| LMArena Russian | 1373 | 1369 |
| LMArena Spanish | 1396 | 1403 |
Instruction Following Qwen3-30B-A3B leads
Gemini 2.5 Flash-Lite: 70.2 (#163), Qwen3-30B-A3B: 72.2 (#137)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1366 | 1364 |
| IFEval | 81% | — |
Long Context Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 33.3 (#257), Qwen3-30B-A3B: 31.0 (#278)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | 47.2% | 40.6% |
| LMArena Longer Query | 1373 | 1379 |
Writing & Preference Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 57.0 (#130), Qwen3-30B-A3B: 55.9 (#138)
| Benchmark | Gemini 2.5 Flash-Lite | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1379 | 1384 |
| LMArena Creative Writing | 1366 | 1318 |
| LMArena Multi-Turn | 1367 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| WildBench | 81.8% | — |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 36.4 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash-Lite or Qwen3-30B-A3B?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.
Is Gemini 2.5 Flash-Lite or Qwen3-30B-A3B better for coding?
They score almost the same on coding (38.0 vs 37.0); test both on your own repository before choosing.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 41K.
How many benchmarks do Gemini 2.5 Flash-Lite and Qwen3-30B-A3B share?
24 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Qwen3-30B-A3B has 32.