Model comparison
Gemma 3n E4b IT vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 18× less per token, which makes it the better buy when Qwen3.5 397B-A17B'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 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 33.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 31.5% for Gemma 3n E4b IT and 73.7% for Qwen3.5 397B-A17B.
- Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 33K.
Side by side
| Gemma 3n E4b IT | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 36.7 | 45.7 |
| Released | 2025-05-20 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 33K | 262K |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.06 | $0.60 |
| Output $ / M tokens | $0.12 | $3.60 |
| Results tracked | 18 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Gemma 3n E4b IT: 36.4 (#193), Qwen3.5 397B-A17B: 41.7 (#108)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1269 | 1464 |
| LMArena WebDev | — | 1400 |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, Qwen3.5 397B-A17B: 33.2 (#51)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Gemma 3n E4b IT: 19.2 (#239), Qwen3.5 397B-A17B: 33.6 (#62)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | 73.7% |
| LMArena Hard Prompts | 1284 | 1448 |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.64 |
Math Qwen3.5 397B-A17B leads
Gemma 3n E4b IT: 32.5 (#186), Qwen3.5 397B-A17B: 44.9 (#64)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1251 | 1455 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
Knowledge Qwen3.5 397B-A17B leads
Gemma 3n E4b IT: 33.6 (#193), Qwen3.5 397B-A17B: 53.3 (#53)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1245 | 1461 |
| GPQA Diamond | — | 86.4% |
Multimodal Not comparable
Gemma 3n E4b IT: —, Qwen3.5 397B-A17B: 40.0 (#42)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1262 |
Multilingual Qwen3.5 397B-A17B leads
Gemma 3n E4b IT: 43.5 (#179), Qwen3.5 397B-A17B: 54.0 (#56)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1285 | 1431 |
| LMArena Chinese | 1310 | 1501 |
| LMArena French | 1330 | 1461 |
| LMArena German | 1312 | 1447 |
| LMArena Japanese | 1274 | 1427 |
| LMArena Korean | 1259 | 1382 |
| LMArena Russian | 1288 | 1429 |
| LMArena Spanish | 1305 | 1443 |
Instruction Following Qwen3.5 397B-A17B leads
Gemma 3n E4b IT: 66.3 (#205), Qwen3.5 397B-A17B: 75.2 (#73)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1255 | 1424 |
Long Context Qwen3.5 397B-A17B leads
Gemma 3n E4b IT: 38.8 (#185), Qwen3.5 397B-A17B: 44.1 (#71)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1277 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Gemma 3n E4b IT: 50.3 (#181), Qwen3.5 397B-A17B: 62.5 (#74)
| Benchmark | Gemma 3n E4b IT | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1306 | 1438 |
| LMArena Creative Writing | 1287 | 1401 |
| LMArena Multi-Turn | 1276 | 1447 |
| EQ-Bench Creative Writing | — | 1478 |
Frequently asked questions
Is Gemma 3n E4b IT better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 18× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Which is cheaper, Gemma 3n E4b IT or Qwen3.5 397B-A17B?
Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is Gemma 3n E4b IT or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 41.7 versus 36.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 33K.
How many benchmarks do Gemma 3n E4b IT and Qwen3.5 397B-A17B share?
18 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Qwen3.5 397B-A17B has 36.