Model comparison
Gemma 4 31B IT vs Qwen3-Coder 480B-A35B Instruct
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 38.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and Qwen3-Coder 480B-A35B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemma 4 31B IT leads 42.3 to 35.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 63.5% for Gemma 4 31B IT and 49.5% for Qwen3-Coder 480B-A35B Instruct.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
Side by side
| Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 43.5 | 38.1 |
| Released | 2026-04-02 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.09 | $1.50 |
| Output $ / M tokens | $0.34 | $7.50 |
| Results tracked | 35 | 25 |
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-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena WebDev | 1366 | 1275 |
| WeirdML | 52.3% | 41.2% |
| LMArena Coding | 1459 | 1412 |
| ALE-Bench | 925.5 | 461.45 |
| SWE-bench Verified (bash only) | — | 55.4% |
| SciCode | 43.4% | — |
| GSO | — | 4.9% |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 49.5% |
| LMArena Hard Prompts | 1448 | 1372 |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1465 | 1365 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
Knowledge Too close to call
Gemma 4 31B IT: 37.9 (#151), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1465 | 1338 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Qwen3-Coder 480B-A35B Instruct: —
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1431 | 1346 |
| LMArena Chinese | 1476 | 1357 |
| LMArena French | 1435 | 1398 |
| LMArena Russian | 1460 | 1366 |
| LMArena Spanish | 1444 | 1360 |
| LMArena German | — | 1325 |
| LMArena Japanese | — | 1310 |
| LMArena Korean | — | 1305 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1433 | 1355 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1446 | 1378 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Gemma 4 31B IT | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1443 | 1357 |
| LMArena Creative Writing | 1415 | 1333 |
| LMArena Multi-Turn | 1452 | 1365 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Qwen3-Coder 480B-A35B Instruct?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 38.1 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or Qwen3-Coder 480B-A35B Instruct?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Gemma 4 31B IT or Qwen3-Coder 480B-A35B Instruct better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 35.5 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-Coder 480B-A35B Instruct share?
18 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.