Model comparison
Gemma 4 31B IT vs Qwen3.5 27B
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 41.9 on the Noometry Index.
Last verified . 23 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Gemma 4 31B IT scores higher in 7 categories and Qwen3.5 27B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 43.2 to 38.8.
- The biggest single-benchmark swing is NYT Connections (extended): 70.6% for Gemma 4 31B IT and 47.9% for Qwen3.5 27B.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.30 / $2.40 for Qwen3.5 27B.
Side by side
| Gemma 4 31B IT | Qwen3.5 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 43.5 | 41.9 |
| Released | 2026-04-02 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.09 | $0.30 |
| Output $ / M tokens | $0.34 | $2.40 |
| 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 27B: 38.9 (#168)
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| LMArena WebDev | 1366 | 1358 |
| WeirdML | 52.3% | 39.5% |
| LMArena Coding | 1459 | 1427 |
| ALE-Bench | 925.5 | 349.45 |
| SciCode | 43.4% | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Qwen3.5 27B: —
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| Vending-Bench 2 | — | 201.98 |
Reasoning Too close to call
Gemma 4 31B IT: 27.2 (#122), Qwen3.5 27B: 27.5 (#117)
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| NYT Connections (extended) | 70.6% | 47.9% |
| Thematic Generalization | 53% | 45.5% |
| LMArena Hard Prompts | 1448 | 1414 |
| DTBench | 82.7% | 82.4% |
| LMCA | 39.3% | 34% |
| Kagi LLM Benchmark | 63.5% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Qwen3.5 27B: 38.8 (#127)
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| LMArena Math | 1465 | 1429 |
| MathArena Final-Answer Competitions | — | 56.7% |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
Knowledge Too close to call
Gemma 4 31B IT: 37.9 (#151), Qwen3.5 27B: 38.0 (#150)
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 12.1% |
| LMArena Expert | 1465 | 1428 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
Multimodal Gemma 4 31B IT leads
Gemma 4 31B IT: 41.6 (#34), Qwen3.5 27B: 39.4 (#59)
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | 1277 | 1241 |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Qwen3.5 27B: 50.8 (#115)
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1431 | 1390 |
| LMArena Chinese | 1476 | 1478 |
| LMArena French | 1435 | 1410 |
| LMArena Russian | 1460 | 1390 |
| LMArena Spanish | 1444 | 1407 |
| LMArena German | — | 1393 |
| LMArena Japanese | — | 1345 |
| LMArena Korean | — | 1358 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Qwen3.5 27B: 73.5 (#119)
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1393 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Qwen3.5 27B: 43.1 (#106)
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | 1446 | 1413 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Qwen3.5 27B: 59.3 (#111)
| Benchmark | Gemma 4 31B IT | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1443 | 1409 |
| LMArena Creative Writing | 1415 | 1362 |
| LMArena Multi-Turn | 1452 | 1410 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Qwen3.5 27B?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 41.9 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or Qwen3.5 27B?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Qwen3.5 27B lists at $0.30 and $2.40.
Is Gemma 4 31B IT or Qwen3.5 27B better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 38.9 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 27B share?
23 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen3.5 27B has 28.