Model comparison
Gemma 2 9B vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 25.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Gemma 2 9B scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 9.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 86.7% for Qwen3 235B-A22B.
Side by side
| Gemma 2 9B | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 25.9 | 43.5 |
| Released | 2024-06-24 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 35 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Gemma 2 9B: 29.4 (#304), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Gemma 2 9B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1173 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Gemma 2 9B | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Too close to call
Gemma 2 9B: 15.9 (#309), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Gemma 2 9B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1433 |
| Epoch Capabilities Index | 119.83 | 143.85 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 15.2% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 29.3% |
| ForecastBench | — | 59.7 |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Qwen3 235B-A22B leads
Gemma 2 9B: 9.9 (#318), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Gemma 2 9B | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 86.7% |
| LMArena Math | 1183 | 1432 |
| MATH Level 5 | 21% | 68.9% |
| Omni-MATH | — | 71.8% |
| LiveBench Math | 19.8% | — |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
| GSM8K | 84.9% | — |
Knowledge Qwen3 235B-A22B leads
Gemma 2 9B: 9.7 (#305), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Gemma 2 9B | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 27.5% | 80.1% |
| LMArena Expert | 1147 | 1463 |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual Qwen3 235B-A22B leads
Gemma 2 9B: 36.6 (#238), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Gemma 2 9B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1188 | 1409 |
| LMArena Chinese | 1185 | 1481 |
| LMArena French | 1190 | 1445 |
| LMArena German | 1186 | 1433 |
| LMArena Japanese | 1144 | 1399 |
| LMArena Korean | 1137 | 1391 |
| LMArena Russian | 1200 | 1411 |
| LMArena Spanish | 1200 | 1430 |
Instruction Following Qwen3 235B-A22B leads
Gemma 2 9B: 57.6 (#269), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Gemma 2 9B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1408 |
| LiveBench Instruction Following | 52.6% | — |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Gemma 2 9B: 36.3 (#233), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Gemma 2 9B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1197 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Gemma 2 9B: 32.1 (#281), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Gemma 2 9B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1207 | 1419 |
| LMArena Creative Writing | 1206 | 1384 |
| EQ-Bench Creative Writing | 841 | 1366 |
| LMArena Multi-Turn | 1193 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Qwen3 235B-A22B share?
22 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Qwen3 235B-A22B has 49.