Model comparison
Gemini 3.5 Flash Lite vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 1.6× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 3 categories and Qwen3.5 397B-A17B in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 397B-A17B leads 46.1 to 25.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Gemini 3.5 Flash Lite and 88.9% for Qwen3.5 397B-A17B.
- Gemini 3.5 Flash Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 262K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 41.5 | 46.0 |
| Released | 2026-07-21 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.30 | $0.60 |
| Output $ / M tokens | $2.50 | $3.60 |
| Results tracked | 39 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.5 Flash Lite: 42.4 (#104), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1440 | 1400 |
| LMArena Coding | 1453 | 1465 |
| SciCode | 41.3% | — |
| WeirdML | 39% | — |
| ALE-Bench | 765.27 | — |
Agentic & Tool Use Qwen3.5 397B-A17B leads
Gemini 3.5 Flash Lite: 25.7 (#107), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | 29.3% | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| GDP.pdf | 10% | — |
Reasoning Qwen3.5 397B-A17B leads
Gemini 3.5 Flash Lite: 27.8 (#114), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| NYT Connections (extended) | 60.4% | 58.9% |
| Chess Puzzles | 22% | 13% |
| LMArena Hard Prompts | 1441 | 1448 |
| Mystery Game Puzzles | 19% | 18% |
| DTBench | 83.5% | 87.5% |
| LMCA | 37.6% | 37.9% |
| Epoch Capabilities Index | 145.13 | 146.65 |
| ARC-AGI-2 | 10.3% | — |
| Kagi LLM Benchmark | — | 73.7% |
| ARC-AGI-1 | 53.5% | — |
| CritPt | 0% | — |
| Thematic Generalization | — | 65.1% |
Math Qwen3.5 397B-A17B leads
Gemini 3.5 Flash Lite: 25.9 (#264), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 26% | 31.2% |
| OTIS Mock AIME 2024-2025 | 71.1% | 88.9% |
| LMArena Math | 1433 | 1454 |
| FrontierMath Tier 4 | 0% | — |
| ProofBench | 13% | — |
Knowledge Qwen3.5 397B-A17B leads
Gemini 3.5 Flash Lite: 50.1 (#72), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 83.3% | 86.4% |
| LMArena Expert | 1435 | 1462 |
Multimodal Too close to call
Gemini 3.5 Flash Lite: 41.1 (#40), Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | 1268 | 1263 |
Multilingual Too close to call
Gemini 3.5 Flash Lite: 53.5 (#63), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1427 | 1430 |
| LMArena Chinese | 1469 | 1500 |
| LMArena French | 1451 | 1461 |
| LMArena German | 1454 | 1447 |
| LMArena Japanese | 1427 | 1426 |
| LMArena Korean | 1407 | 1384 |
| LMArena Russian | 1443 | 1429 |
| LMArena Spanish | 1442 | 1441 |
Instruction Following Too close to call
Gemini 3.5 Flash Lite: 74.8 (#85), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1420 | 1424 |
Long Context Too close to call
Gemini 3.5 Flash Lite: 43.9 (#84), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1435 | 1442 |
Writing & Preference Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 64.2 (#57), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Gemini 3.5 Flash Lite | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1435 | 1438 |
| LMArena Creative Writing | 1420 | 1401 |
| EQ-Bench Creative Writing | 1559 | 1478 |
| LMArena Multi-Turn | 1445 | 1446 |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 1.6× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.5 Flash Lite or Qwen3.5 397B-A17B?
Gemini 3.5 Flash Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is Gemini 3.5 Flash Lite or Qwen3.5 397B-A17B better for coding?
They score almost the same on coding (42.4 vs 42.0); test both on your own repository before choosing.
Which has the bigger context window?
Gemini 3.5 Flash Lite does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3.5 Flash Lite and Qwen3.5 397B-A17B share?
30 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and Qwen3.5 397B-A17B has 36.