Model comparison
Gemini 3.1 Flash Lite vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 2.0× less per token, which makes it the better buy when Qwen3.6 Plus'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 3.1 Flash Lite scores higher in 0 categories and Qwen3.6 Plus in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 41.9.
- The biggest single-benchmark swing is NYT Connections (extended): 8.2% for Gemini 3.1 Flash Lite and 60.3% for Qwen3.6 Plus.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 1M.
Side by side
| Gemini 3.1 Flash Lite | Qwen3.6 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 40.8 | 47.5 |
| Released | 2026-03-03 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.25 | $0.50 |
| Output $ / M tokens | $1.50 | $3 |
| Results tracked | 38 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Plus leads
Gemini 3.1 Flash Lite: 37.8 (#188), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1256 | 1461 |
| SciCode | 41.9% | 40.7% |
| LMArena Coding | 1400 | 1467 |
| ALE-Bench | 797.73 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| WeirdML | 52.2% | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Flash Lite: 30.2 (#79), Qwen3.6 Plus: —
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| DeepResearch Bench | 37.3% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
Gemini 3.1 Flash Lite: 22.9 (#186), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 8.2% | 60.3% |
| CritPt | 1.1% | 2.9% |
| Chess Puzzles | 25% | 17% |
| Thematic Generalization | 63.3% | 59.5% |
| LMArena Hard Prompts | 1407 | 1449 |
| DTBench | 76.8% | 81.9% |
| LMCA | 35% | 33.1% |
| Epoch Capabilities Index | 144.47 | 147.65 |
| Kagi LLM Benchmark | 67.2% | — |
| EnigmaEval | 3% | — |
| Mystery Game Puzzles | — | 12% |
| ForecastBench | 54.4 | — |
Math Qwen3.6 Plus leads
Gemini 3.1 Flash Lite: 40.7 (#90), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 38.2% |
| OTIS Mock AIME 2024-2025 | 80% | 93.3% |
| LMArena Math | 1428 | 1450 |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
Gemini 3.1 Flash Lite: 41.9 (#104), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 81.8% | 88.4% |
| LMArena Expert | 1398 | 1454 |
| Humanity's Last Exam | 8.6% | — |
| SimpleQA Verified | — | 44.1% |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 39.4 (#60), Qwen3.6 Plus: —
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Too close to call
Gemini 3.1 Flash Lite: 52.3 (#86), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1411 | 1424 |
| LMArena Chinese | 1461 | 1477 |
| LMArena French | 1424 | 1455 |
| LMArena German | 1429 | 1452 |
| LMArena Japanese | 1413 | 1389 |
| LMArena Korean | 1392 | 1379 |
| LMArena Russian | 1420 | 1434 |
| LMArena Spanish | 1421 | 1432 |
Instruction Following Qwen3.6 Plus leads
Gemini 3.1 Flash Lite: 72.7 (#131), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1377 | 1425 |
Long Context Qwen3.6 Plus leads
Gemini 3.1 Flash Lite: 42.5 (#122), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1394 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
Gemini 3.1 Flash Lite: 60.9 (#94), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Gemini 3.1 Flash Lite | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1416 | 1437 |
| LMArena Creative Writing | 1401 | 1404 |
| LMArena Multi-Turn | 1417 | 1438 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 2.0× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Flash Lite or Qwen3.6 Plus?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is Gemini 3.1 Flash Lite or Qwen3.6 Plus better for coding?
Qwen3.6 Plus scores higher on coding benchmarks: 40.8 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 1M.
How many benchmarks do Gemini 3.1 Flash Lite and Qwen3.6 Plus share?
30 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Qwen3.6 Plus has 37.