Model comparison
Gemini 2.0 Flash (Feb 2025) vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 34.8 on the Noometry Index.
Last verified . 37 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 37 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and Qwen3 235B-A22B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.5 to 32.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.8% for Gemini 2.0 Flash (Feb 2025) and 69.4% for Qwen3 235B-A22B.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 34.8 | 43.2 |
| Released | 2024-12-06 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 54 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Gemini 2.0 Flash (Feb 2025): 28.2 (#308), Qwen3 235B-A22B: 43.8 (#72)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| Aider Polyglot | 38.2% | 59.6% |
| WeirdML | 25.8% | 41% |
| LMArena Coding | 1351 | 1445 |
| SWE-bench Verified (bash only) | 13.5% | — |
| SciCode | — | 42.4% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Qwen3 235B-A22B leads
Gemini 2.0 Flash (Feb 2025): 28.0 (#85), Qwen3 235B-A22B: 33.7 (#48)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| TheAgentCompany | 11.4% | — |
| Vending-Bench 2 | — | -11.34 |
Reasoning Too close to call
Gemini 2.0 Flash (Feb 2025): 15.2 (#308), Qwen3 235B-A22B: 15.8 (#302)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| ARC-AGI-2 | 1.3% | 1.3% |
| SimpleBench | 31.1% | 31% |
| Kagi LLM Benchmark | 37.8% | 69.4% |
| LMArena Hard Prompts | 1346 | 1433 |
| DTBench | 63.2% | 80.3% |
| Epoch Capabilities Index | 135.36 | 143.87 |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 9% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 29.3% |
| ForecastBench | — | 59.7 |
| LiveBench | 66.9% | — |
Math Qwen3 235B-A22B leads
Gemini 2.0 Flash (Feb 2025): 36.1 (#127), Qwen3 235B-A22B: 48.5 (#51)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 86.7% |
| Omni-MATH | 45.9% | 71.8% |
| LMArena Math | 1351 | 1431 |
| MATH Level 5 | 82.2% | 68.9% |
| FrontierMath (Feb 2025 set) | 1.7% | 8.5% |
| LiveBench Math | 75.8% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#207), Qwen3 235B-A22B: 49.5 (#67)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 64.1% | 80.1% |
| MMLU-Pro | 73.7% | 84.4% |
| Confabulations | 12.4% | 15.6% |
| GPQA (HELM) | 55.6% | 72.7% |
| LMArena Expert | 1340 | 1460 |
| Humanity's Last Exam | 6.6% | — |
| SimpleQA Verified | — | 40.4% |
| Vectara Hallucination Rate | — | 9.3% |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 35.9 (#74), Qwen3 235B-A22B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Qwen3 235B-A22B leads
Gemini 2.0 Flash (Feb 2025): 47.6 (#144), Qwen3 235B-A22B: 52.5 (#84)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1342 | 1410 |
| LMArena Chinese | 1373 | 1481 |
| LMArena French | 1390 | 1445 |
| LMArena German | 1354 | 1432 |
| LMArena Japanese | 1293 | 1400 |
| LMArena Korean | 1314 | 1391 |
| LMArena Russian | 1351 | 1411 |
| LMArena Spanish | 1363 | 1429 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.6 (#91), Qwen3 235B-A22B: 72.8 (#132)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 84.1% | 83.5% |
| LMArena Instruction Following | 1336 | 1408 |
| LiveBench Instruction Following | 85.8% | — |
Long Context Qwen3 235B-A22B leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#198), Qwen3 235B-A22B: 46.1 (#25)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| Fiction.LiveBench | 61.1% | 75% |
| LMArena Longer Query | 1345 | 1426 |
Writing & Preference Qwen3 235B-A22B leads
Gemini 2.0 Flash (Feb 2025): 49.8 (#184), Qwen3 235B-A22B: 59.8 (#103)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1354 | 1419 |
| LMArena Creative Writing | 1340 | 1384 |
| Short-Story Creative Writing | 73.8% | 83% |
| EQ-Bench Creative Writing | 1128 | 1366 |
| WildBench | 80% | 86.6% |
| LMArena Multi-Turn | 1350 | 1432 |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 34.8 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 28.2 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Qwen3 235B-A22B share?
37 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Qwen3 235B-A22B has 49.