Model comparison
Gemini 3 Flash Preview vs Qwen3 Max
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 43.7 on the Noometry Index.
Last verified . 29 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 8 categories and Qwen3 Max in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 22.6.
- The biggest single-benchmark swing is NYT Connections (extended): 83.1% for Gemini 3 Flash Preview and 30.1% for Qwen3 Max.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 262K.
Side by side
| Gemini 3 Flash Preview | Qwen3 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 52.3 | 43.7 |
| Released | 2025-12-17 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.50 | $1.20 |
| Output $ / M tokens | $3 | $6 |
| Results tracked | 59 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), Qwen3 Max: 43.0 (#93)
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1460 | 1456 |
| ALE-Bench | 1,367 | 370.45 |
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |
| WeirdML | 61.6% | — |
Agentic & Tool Use Not comparable
Gemini 3 Flash Preview: 38.7 (#29), Qwen3 Max: —
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | 3,635 | 71.56 |
| Terminal-Bench | 64.3% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), Qwen3 Max: 22.6 (#190)
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| NYT Connections (extended) | 83.1% | 30.1% |
| Chess Puzzles | 40% | 4% |
| LMArena Hard Prompts | 1465 | 1448 |
| Mystery Game Puzzles | 26% | 5% |
| DTBench | 89.1% | 82.1% |
| LMCA | 43.1% | 28.3% |
| Epoch Capabilities Index | 151.8 | 142.38 |
| ARC-AGI-2 | 33.6% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | — | 72.5% |
| ARC-AGI-1 | 84.7% | — |
| ForecastBench | 58.5 | — |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), Qwen3 Max: 38.7 (#131)
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 18.9% |
| OTIS Mock AIME 2024-2025 | 95.6% | 73.3% |
| LMArena Math | 1473 | 1446 |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 15% | — |
| MATH Level 5 | — | 97.1% |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), Qwen3 Max: 48.1 (#78)
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 89.4% | 72.6% |
| SimpleQA Verified | 66.8% | 48.7% |
| LMArena Expert | 1462 | 1455 |
| Vectara Hallucination Rate | 13.5% | — |
Multimodal Not comparable
Gemini 3 Flash Preview: 45.5 (#16), Qwen3 Max: —
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), Qwen3 Max: 53.7 (#62)
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1458 | 1429 |
| LMArena Chinese | 1511 | 1478 |
| LMArena French | 1477 | 1449 |
| LMArena German | 1497 | 1463 |
| LMArena Japanese | 1489 | 1397 |
| LMArena Korean | 1443 | 1399 |
| LMArena Russian | 1480 | 1428 |
| LMArena Spanish | 1469 | 1462 |
Instruction Following Too close to call
Gemini 3 Flash Preview: 75.7 (#56), Qwen3 Max: 74.8 (#87)
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1437 | 1419 |
Long Context Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 44.4 (#67), Qwen3 Max: 41.6 (#134)
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1452 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.5 (#45), Qwen3 Max: 62.4 (#76)
| Benchmark | Gemini 3 Flash Preview | Qwen3 Max |
|---|---|---|
| LMArena Text | 1466 | 1439 |
| LMArena Creative Writing | 1457 | 1402 |
| LMArena Multi-Turn | 1471 | 1446 |
Frequently asked questions
Is Gemini 3 Flash Preview better than Qwen3 Max?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 43.7 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or Qwen3 Max?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Gemini 3 Flash Preview or Qwen3 Max better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 43.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3 Flash Preview and Qwen3 Max share?
29 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Qwen3 Max has 33.