Model comparison
Gemini 2.5 Flash vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 39.3 on the Noometry Index.
Last verified . 23 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 4 categories and Qwen3.5 35B-A3B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.8 to 36.4.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 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 262K.
- Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 39.3 | 42.0 |
| Released | 2025-04-17 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.30 | $0.25 |
| Output $ / M tokens | $2.50 | $2 |
| Results tracked | 54 | 28 |
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), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Coding | 1424 | 1410 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1254 |
| SciCode | — | 29.3% |
| WeirdML | 41.9% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.8 (#74), Qwen3.5 35B-A3B: —
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Qwen3.5 35B-A3B leads
Gemini 2.5 Flash: 18.1 (#286), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 1.1% | 0.6% |
| LMArena Hard Prompts | 1422 | 1400 |
| DTBench | 76.5% | 80% |
| LMCA | 27.5% | 29.5% |
| Epoch Capabilities Index | 143.03 | 142.52 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| ARC-AGI-1 | 33.3% | — |
| Chess Puzzles | — | 10% |
| EnigmaEval | 2.7% | — |
| ForecastBench | 60.6 | — |
Math Too close to call
Gemini 2.5 Flash: 39.9 (#98), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 70% |
| LMArena Math | 1415 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Qwen3.5 35B-A3B leads
Gemini 2.5 Flash: 36.4 (#168), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| Vectara Hallucination Rate | 7.8% | 10.5% |
| LMArena Expert | 1426 | 1408 |
| GPQA Diamond | — | 83.5% |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), Qwen3.5 35B-A3B: —
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| 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), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1409 | 1378 |
| LMArena Chinese | 1450 | 1457 |
| LMArena French | 1433 | 1412 |
| LMArena German | 1418 | 1367 |
| LMArena Japanese | 1405 | 1325 |
| LMArena Korean | 1385 | 1356 |
| LMArena Russian | 1415 | 1376 |
| LMArena Spanish | 1421 | 1392 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.7 (#54), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1379 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1419 | 1389 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Qwen3.5 35B-A3B leads
Gemini 2.5 Flash: 53.8 (#157), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Gemini 2.5 Flash | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1417 | 1395 |
| LMArena Creative Writing | 1400 | 1346 |
| LMArena Multi-Turn | 1408 | 1390 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 39.3 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or Qwen3.5 35B-A3B better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 33.8 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 Qwen3.5 35B-A3B share?
23 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Qwen3.5 35B-A3B has 28.