Model comparison
Gemini 2.5 Flash vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 2.8× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Qwen3 Max in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 36.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 56.8% for Gemini 2.5 Flash and 72.5% for Qwen3 Max.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 262K.
Side by side
| Gemini 2.5 Flash | Qwen3 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 39.3 | 43.7 |
| Released | 2025-04-17 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.30 | $1.20 |
| Output $ / M tokens | $2.50 | $6 |
| Results tracked | 54 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Gemini 2.5 Flash: 35.8 (#220), Qwen3 Max: 43.0 (#93)
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1424 | 1456 |
| ALE-Bench | 661.88 | 370.45 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| WeirdML | 41.9% | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.8 (#74), Qwen3 Max: —
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | 548.84 | 71.56 |
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
Reasoning Qwen3 Max leads
Gemini 2.5 Flash: 18.1 (#286), Qwen3 Max: 22.6 (#190)
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 56.8% | 72.5% |
| LMArena Hard Prompts | 1422 | 1448 |
| DTBench | 76.5% | 82.1% |
| LMCA | 27.5% | 28.3% |
| Epoch Capabilities Index | 143.03 | 142.38 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| NYT Connections (extended) | — | 30.1% |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 4% |
| EnigmaEval | 2.7% | — |
| Mystery Game Puzzles | — | 5% |
| ForecastBench | 60.6 | — |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), Qwen3 Max: 38.7 (#131)
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 73.3% |
| LMArena Math | 1415 | 1446 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| Omni-MATH | 38.5% | — |
| MATH Level 5 | — | 97.1% |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Qwen3 Max leads
Gemini 2.5 Flash: 36.4 (#168), Qwen3 Max: 48.1 (#78)
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1426 | 1455 |
| GPQA Diamond | — | 72.6% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 48.7% |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), Qwen3 Max: —
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Qwen3 Max leads
Gemini 2.5 Flash: 52.3 (#88), Qwen3 Max: 53.7 (#62)
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1409 | 1429 |
| LMArena Chinese | 1450 | 1478 |
| LMArena French | 1433 | 1449 |
| LMArena German | 1418 | 1463 |
| LMArena Japanese | 1405 | 1397 |
| LMArena Korean | 1385 | 1399 |
| LMArena Russian | 1415 | 1428 |
| LMArena Spanish | 1421 | 1462 |
Instruction Following Too close to call
Gemini 2.5 Flash: 75.7 (#54), Qwen3 Max: 74.8 (#87)
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1405 | 1419 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), Qwen3 Max: 41.6 (#134)
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | 77.8% | 66.7% |
| LMArena Longer Query | 1419 | 1438 |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Gemini 2.5 Flash: 53.8 (#157), Qwen3 Max: 62.4 (#76)
| Benchmark | Gemini 2.5 Flash | Qwen3 Max |
|---|---|---|
| LMArena Text | 1417 | 1439 |
| LMArena Creative Writing | 1400 | 1402 |
| LMArena Multi-Turn | 1408 | 1446 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 2.8× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash or Qwen3 Max?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Gemini 2.5 Flash or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 2.5 Flash and Qwen3 Max share?
25 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Qwen3 Max has 33.