Model comparison
Gemma 4 31B IT vs Qwen3.5 35B-A3B
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 42.0 on the Noometry Index.
Last verified . 24 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Gemma 4 31B IT scores higher in 7 categories and Qwen3.5 35B-A3B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.8 to 37.9.
- The biggest single-benchmark swing is SciCode: 43.4% for Gemma 4 31B IT and 29.3% for Qwen3.5 35B-A3B.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
Side by side
| Gemma 4 31B IT | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 43.5 | 42.0 |
| Released | 2026-04-02 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.09 | $0.25 |
| Output $ / M tokens | $0.34 | $2 |
| Results tracked | 35 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | Gemma 4 31B IT | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena WebDev | 1366 | 1254 |
| SciCode | 43.4% | 29.3% |
| LMArena Coding | 1459 | 1410 |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Gemma 4 31B IT | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 1.4% | 0.6% |
| Chess Puzzles | 5% | 10% |
| LMArena Hard Prompts | 1448 | 1400 |
| DTBench | 82.7% | 80% |
| LMCA | 39.3% | 29.5% |
| Epoch Capabilities Index | 142.74 | 142.52 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| Thematic Generalization | 53% | — |
| Surface Evolver Bench | 30.6% | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Gemma 4 31B IT | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 70% |
| LMArena Math | 1465 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
Knowledge Qwen3.5 35B-A3B leads
Gemma 4 31B IT: 37.9 (#151), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Gemma 4 31B IT | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 75.8% | 83.5% |
| Vectara Hallucination Rate | 7.4% | 10.5% |
| LMArena Expert | 1465 | 1408 |
| SimpleQA Verified | 10.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Qwen3.5 35B-A3B: —
| Benchmark | Gemma 4 31B IT | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Gemma 4 31B IT | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1431 | 1378 |
| LMArena Chinese | 1476 | 1457 |
| LMArena French | 1435 | 1412 |
| LMArena Russian | 1460 | 1376 |
| LMArena Spanish | 1444 | 1392 |
| LMArena German | — | 1367 |
| LMArena Japanese | — | 1325 |
| LMArena Korean | — | 1356 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Gemma 4 31B IT | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1379 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Gemma 4 31B IT | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1446 | 1389 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Gemma 4 31B IT | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1443 | 1395 |
| LMArena Creative Writing | 1415 | 1346 |
| LMArena Multi-Turn | 1452 | 1390 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Qwen3.5 35B-A3B?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 42.0 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or Qwen3.5 35B-A3B?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.
Is Gemma 4 31B IT or Qwen3.5 35B-A3B better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Gemma 4 31B IT and Qwen3.5 35B-A3B share?
24 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen3.5 35B-A3B has 28.