Model comparison
Gemini 2.5 Flash vs Qwen-14B
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 31.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 6 categories and Qwen-14B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.5 Flash leads 53.8 to 27.6.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Qwen-14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 39.3 | 31.4 |
| Released | 2025-04-17 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 54 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Gemini 2.5 Flash: 35.8 (#220), Qwen-14B: 31.2 (#288)
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| LMArena Coding | 1424 | 1071 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| WeirdML | 41.9% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.8 (#74), Qwen-14B: —
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Qwen-14B leads
Gemini 2.5 Flash: 18.1 (#286), Qwen-14B: 19.6 (#257)
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1027 |
| Epoch Capabilities Index | 143.03 | 113.03 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| BIG-Bench Hard | — | 55% |
| ForecastBench | 60.6 | — |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), Qwen-14B: 31.2 (#227)
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| LMArena Math | 1415 | 1068 |
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Gemini 2.5 Flash: 36.4 (#168), Qwen-14B: —
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
| LMArena Expert | 1426 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), Qwen-14B: —
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Gemini 2.5 Flash leads
Gemini 2.5 Flash: 52.3 (#88), Qwen-14B: 27.5 (#275)
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1409 | 1041 |
| LMArena Chinese | 1450 | 1077 |
| LMArena French | 1433 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1385 | — |
| LMArena Russian | 1415 | — |
| LMArena Spanish | 1421 | — |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.7 (#54), Qwen-14B: 52.4 (#289)
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1031 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), Qwen-14B: 31.3 (#280)
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1419 | 1028 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Gemini 2.5 Flash leads
Gemini 2.5 Flash: 53.8 (#157), Qwen-14B: 27.6 (#299)
| Benchmark | Gemini 2.5 Flash | Qwen-14B |
|---|---|---|
| LMArena Text | 1417 | 1051 |
| LMArena Creative Writing | 1400 | 1028 |
| LMArena Multi-Turn | 1408 | 1022 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Qwen-14B?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 31.4 on the Noometry Index.
Is Gemini 2.5 Flash or Qwen-14B better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 31.2 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Flash and Qwen-14B share?
11 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Qwen-14B has 18.