Model comparison
Gemma 3n E4b IT vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 16× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 48.5 to 32.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 31.5% for Gemma 3n E4b IT and 69.4% for Qwen3 235B-A22B.
- Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Qwen3 235B-A22B accepts more context: 131K tokens versus 33K.
Side by side
| Gemma 3n E4b IT | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 36.7 | 43.2 |
| Released | 2025-05-20 | 2025-04 |
| Weights | Open | Open |
| Context window | 33K | 131K |
| Max output | 33K | 16K |
| Input $ / M tokens | $0.06 | $0.70 |
| Output $ / M tokens | $0.12 | $2.80 |
| Results tracked | 18 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Gemma 3n E4b IT: 36.4 (#193), Qwen3 235B-A22B: 43.8 (#72)
| Benchmark | Gemma 3n E4b IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1269 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, Qwen3 235B-A22B: 33.7 (#48)
| Benchmark | Gemma 3n E4b IT | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Gemma 3n E4b IT leads
Gemma 3n E4b IT: 19.2 (#239), Qwen3 235B-A22B: 15.8 (#302)
| Benchmark | Gemma 3n E4b IT | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | 69.4% |
| LMArena Hard Prompts | 1284 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.87 |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
Gemma 3n E4b IT: 32.5 (#186), Qwen3 235B-A22B: 48.5 (#51)
| Benchmark | Gemma 3n E4b IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Math | 1251 | 1431 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Gemma 3n E4b IT: 33.6 (#193), Qwen3 235B-A22B: 49.5 (#67)
| Benchmark | Gemma 3n E4b IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Expert | 1245 | 1460 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
Multilingual Qwen3 235B-A22B leads
Gemma 3n E4b IT: 43.5 (#179), Qwen3 235B-A22B: 52.5 (#84)
| Benchmark | Gemma 3n E4b IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1285 | 1410 |
| LMArena Chinese | 1310 | 1481 |
| LMArena French | 1330 | 1445 |
| LMArena German | 1312 | 1432 |
| LMArena Japanese | 1274 | 1400 |
| LMArena Korean | 1259 | 1391 |
| LMArena Russian | 1288 | 1411 |
| LMArena Spanish | 1305 | 1429 |
Instruction Following Qwen3 235B-A22B leads
Gemma 3n E4b IT: 66.3 (#205), Qwen3 235B-A22B: 72.8 (#132)
| Benchmark | Gemma 3n E4b IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1255 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Gemma 3n E4b IT: 38.8 (#185), Qwen3 235B-A22B: 46.1 (#25)
| Benchmark | Gemma 3n E4b IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1277 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Gemma 3n E4b IT: 50.3 (#181), Qwen3 235B-A22B: 59.8 (#103)
| Benchmark | Gemma 3n E4b IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1306 | 1419 |
| LMArena Creative Writing | 1287 | 1384 |
| LMArena Multi-Turn | 1276 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
Frequently asked questions
Is Gemma 3n E4b IT better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 16× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, Gemma 3n E4b IT or Qwen3 235B-A22B?
Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is Gemma 3n E4b IT or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 36.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3 235B-A22B does, with 131K tokens against 33K.
How many benchmarks do Gemma 3n E4b IT and Qwen3 235B-A22B share?
18 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Qwen3 235B-A22B has 49.