Model comparison
Gemini 2.5 Flash vs Qwen3 8B
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 33.7 on the Noometry Index. Qwen3 8B costs 2.7× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 6 categories and Qwen3 8B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Flash leads 47.5 to 37.9.
- The biggest single-benchmark swing is LMCA: 27.5% for Gemini 2.5 Flash and 8.8% for Qwen3 8B.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 131K.
- Qwen3 8B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Qwen3 8B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 39.3 | 33.7 |
| Released | 2025-04-17 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.30 | $0.18 |
| Output $ / M tokens | $2.50 | $0.70 |
| Results tracked | 54 | 11 |
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), Qwen3 8B: 34.0 (#248)
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| SciCode | — | 22.6% |
| WeirdML | 41.9% | — |
| LMArena Coding | 1424 | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Too close to call
Gemini 2.5 Flash: 30.8 (#74), Qwen3 8B: 30.2 (#78)
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 56.2% | 42.6% |
| Terminal-Bench | 17.1% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Gemini 2.5 Flash leads
Gemini 2.5 Flash: 18.1 (#286), Qwen3 8B: 16.6 (#303)
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| CritPt | 1.1% | 0% |
| DTBench | 76.5% | 59.7% |
| LMCA | 27.5% | 8.8% |
| Epoch Capabilities Index | 143.03 | 136.17 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| ARC-AGI-1 | 33.3% | — |
| Chess Puzzles | — | 5% |
| EnigmaEval | 2.7% | — |
| LMArena Hard Prompts | 1422 | — |
| ForecastBench | 60.6 | — |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), Qwen3 8B: 34.9 (#191)
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 56.1% |
| Omni-MATH | 38.5% | — |
| LMArena Math | 1415 | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Too close to call
Gemini 2.5 Flash: 36.4 (#168), Qwen3 8B: 36.1 (#173)
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| Vectara Hallucination Rate | 7.8% | 4.8% |
| GPQA Diamond | — | 56.8% |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| GPQA (HELM) | 39% | — |
| LMArena Expert | 1426 | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), Qwen3 8B: —
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Not comparable
Gemini 2.5 Flash: 52.3 (#88), Qwen3 8B: —
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1409 | — |
| LMArena Chinese | 1450 | — |
| LMArena French | 1433 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1385 | — |
| LMArena Russian | 1415 | — |
| LMArena Spanish | 1421 | — |
Instruction Following Not comparable
Gemini 2.5 Flash: 75.7 (#54), Qwen3 8B: —
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| IFEval | 89.8% | — |
| LMArena Instruction Following | 1405 | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), Qwen3 8B: 37.9 (#210)
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | 77.8% | 62.1% |
| LMArena Longer Query | 1419 | — |
Writing & Preference Not comparable
Gemini 2.5 Flash: 53.8 (#157), Qwen3 8B: —
| Benchmark | Gemini 2.5 Flash | Qwen3 8B |
|---|---|---|
| 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 Qwen3 8B?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 33.7 on the Noometry Index. Qwen3 8B costs 2.7× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or Qwen3 8B better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 34.0 in the Noometry coding category.
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 Qwen3 8B share?
8 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Qwen3 8B has 11.