Model comparison
Gemini 2.5 Flash vs Qwen2.5-VL 72B Instruct
Gemini 2.5 Flash is the stronger model overall, scoring 39.0 to 29.4 on the Noometry Index.
Last verified . 4 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 2 categories and Qwen2.5-VL 72B Instruct in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Gemini 2.5 Flash leads 30.6 to 18.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 56.8% for Gemini 2.5 Flash and 36% for Qwen2.5-VL 72B Instruct.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 131K.
- Qwen2.5-VL 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 39.0 | 29.4 |
| Released | 2025-04-17 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.30 | $2.80 |
| Output $ / M tokens | $2.50 | $8.40 |
| Results tracked | 54 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 2.5 Flash: 35.5 (#210), Qwen2.5-VL 72B Instruct: —
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| WeirdML | 41.9% | — |
| LMArena Coding | 1424 | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Gemini 2.5 Flash leads
Gemini 2.5 Flash: 30.6 (#67), Qwen2.5-VL 72B Instruct: 18.4 (#136)
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| OSWorld | — | 5% |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Qwen2.5-VL 72B Instruct leads
Gemini 2.5 Flash: 18.2 (#271), Qwen2.5-VL 72B Instruct: 20.0 (#228)
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 56.8% | 36% |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| LMArena Hard Prompts | 1422 | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.04 | — |
| ForecastBench | 60.6 | — |
Math Not comparable
Gemini 2.5 Flash: 38.1 (#87), Qwen2.5-VL 72B Instruct: —
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| LMArena Math | 1415 | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Not comparable
Gemini 2.5 Flash: 36.1 (#162), Qwen2.5-VL 72B Instruct: —
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
| LMArena Expert | 1426 | — |
Multimodal Gemini 2.5 Flash leads
Gemini 2.5 Flash: 41.2 (#31), Qwen2.5-VL 72B Instruct: 32.9 (#92)
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | 1254 | 1107 |
| GeoBench | 76% | 62% |
| SpatialViz-Bench | 36.9% | 33.3% |
| Video-MME | — | 73.5% |
| VPCT | 46.2% | — |
Multilingual Not comparable
Gemini 2.5 Flash: 52.5 (#83), Qwen2.5-VL 72B Instruct: —
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1410 | — |
| LMArena Chinese | 1450 | — |
| LMArena French | 1433 | — |
| LMArena German | 1419 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1385 | — |
| LMArena Russian | 1415 | — |
| LMArena Spanish | 1421 | — |
Instruction Following Not comparable
Gemini 2.5 Flash: 75.9 (#50), Qwen2.5-VL 72B Instruct: —
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| IFEval | 89.8% | — |
| LMArena Instruction Following | 1405 | — |
Long Context Not comparable
Gemini 2.5 Flash: 47.5 (#16), Qwen2.5-VL 72B Instruct: —
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Fiction.LiveBench | 77.8% | — |
| LMArena Longer Query | 1419 | — |
Writing & Preference Not comparable
Gemini 2.5 Flash: 54.0 (#153), Qwen2.5-VL 72B Instruct: —
| Benchmark | Gemini 2.5 Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1417 | — |
| LMArena Creative Writing | 1400 | — |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
| LMArena Multi-Turn | 1408 | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Qwen2.5-VL 72B Instruct?
Gemini 2.5 Flash is the stronger model overall, scoring 39.0 to 29.4 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or Qwen2.5-VL 72B Instruct?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 2.5 Flash and Qwen2.5-VL 72B Instruct share?
4 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.