Model comparison
Gemini 3.1 Flash Lite vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 4.3× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 3 categories and Qwen3 Max in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 41.9.
- The biggest single-benchmark swing is NYT Connections (extended): 8.2% for Gemini 3.1 Flash Lite and 30.1% for Qwen3 Max.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 262K.
Side by side
| Gemini 3.1 Flash Lite | Qwen3 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 40.8 | 43.7 |
| Released | 2026-03-03 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.25 | $1.20 |
| Output $ / M tokens | $1.50 | $6 |
| Results tracked | 38 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Gemini 3.1 Flash Lite: 37.8 (#188), Qwen3 Max: 43.0 (#93)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1400 | 1456 |
| ALE-Bench | 797.73 | 370.45 |
| LMArena WebDev | 1256 | — |
| SciCode | 41.9% | — |
| WeirdML | 52.2% | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Flash Lite: 30.2 (#79), Qwen3 Max: —
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| DeepResearch Bench | 37.3% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Too close to call
Gemini 3.1 Flash Lite: 22.9 (#186), Qwen3 Max: 22.6 (#190)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 72.5% |
| NYT Connections (extended) | 8.2% | 30.1% |
| Chess Puzzles | 25% | 4% |
| LMArena Hard Prompts | 1407 | 1448 |
| DTBench | 76.8% | 82.1% |
| LMCA | 35% | 28.3% |
| Epoch Capabilities Index | 144.47 | 142.38 |
| CritPt | 1.1% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| Mystery Game Puzzles | — | 5% |
| ForecastBench | 54.4 | — |
Math Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 40.7 (#90), Qwen3 Max: 38.7 (#131)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 18.9% |
| OTIS Mock AIME 2024-2025 | 80% | 73.3% |
| LMArena Math | 1428 | 1446 |
| MATH Level 5 | — | 97.1% |
Knowledge Qwen3 Max leads
Gemini 3.1 Flash Lite: 41.9 (#104), Qwen3 Max: 48.1 (#78)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 81.8% | 72.6% |
| LMArena Expert | 1398 | 1455 |
| Humanity's Last Exam | 8.6% | — |
| SimpleQA Verified | — | 48.7% |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 39.4 (#60), Qwen3 Max: —
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Qwen3 Max leads
Gemini 3.1 Flash Lite: 52.3 (#86), Qwen3 Max: 53.7 (#62)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1411 | 1429 |
| LMArena Chinese | 1461 | 1478 |
| LMArena French | 1424 | 1449 |
| LMArena German | 1429 | 1463 |
| LMArena Japanese | 1413 | 1397 |
| LMArena Korean | 1392 | 1399 |
| LMArena Russian | 1420 | 1428 |
| LMArena Spanish | 1421 | 1462 |
Instruction Following Qwen3 Max leads
Gemini 3.1 Flash Lite: 72.7 (#131), Qwen3 Max: 74.8 (#87)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1377 | 1419 |
Long Context Too close to call
Gemini 3.1 Flash Lite: 42.5 (#122), Qwen3 Max: 41.6 (#134)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1394 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Gemini 3.1 Flash Lite: 60.9 (#94), Qwen3 Max: 62.4 (#76)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3 Max |
|---|---|---|
| LMArena Text | 1416 | 1439 |
| LMArena Creative Writing | 1401 | 1402 |
| LMArena Multi-Turn | 1417 | 1446 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 4.3× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Flash Lite or Qwen3 Max?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Gemini 3.1 Flash Lite or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3.1 Flash Lite and Qwen3 Max share?
27 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Qwen3 Max has 33.