Model comparison
Gemma 4 31B IT vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 20× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. Gemma 4 31B IT scores higher in 1 category and Qwen3.8 Max in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 43.2.
- The biggest single-benchmark swing is SimpleQA Verified: 10.4% for Gemma 4 31B IT and 47.3% for Qwen3.8 Max.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | Qwen3.8 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 43.5 | 56.8 |
| Released | 2026-04-02 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.09 | $2 |
| Output $ / M tokens | $0.34 | $6 |
| Results tracked | 35 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Gemma 4 31B IT: 42.3 (#108), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| LMArena WebDev | 1366 | 1674 |
| SciCode | 43.4% | 53.2% |
| LMArena Coding | 1459 | 1502 |
| DeepSWE | — | 57.5% |
| FrontierSWE | — | 17.8% |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Gemma 4 31B IT: 27.2 (#122), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| NYT Connections (extended) | 70.6% | 88.3% |
| CritPt | 1.4% | 20% |
| Chess Puzzles | 5% | 40% |
| LMArena Hard Prompts | 1448 | 1496 |
| DTBench | 82.7% | 92% |
| LMCA | 39.3% | 46.2% |
| Epoch Capabilities Index | 142.74 | 156.41 |
| Kagi LLM Benchmark | 63.5% | — |
| Thematic Generalization | 53% | — |
| Mystery Game Puzzles | — | 38% |
| Surface Evolver Bench | 30.6% | — |
Math Qwen3.8 Max leads
Gemma 4 31B IT: 43.2 (#81), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 100% |
| LMArena Math | 1465 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
Knowledge Qwen3.8 Max leads
Gemma 4 31B IT: 37.9 (#151), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 75.8% | 92.7% |
| SimpleQA Verified | 10.4% | 47.3% |
| LMArena Expert | 1465 | 1507 |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Gemma 4 31B IT leads
Gemma 4 31B IT: 41.6 (#34), Qwen3.8 Max: 37.2 (#75)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | 1277 | 1314 |
| Furniture Assembly | — | 20% |
| LMArena Document | 1425 | — |
Multilingual Qwen3.8 Max leads
Gemma 4 31B IT: 53.8 (#57), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1431 | 1472 |
| LMArena Chinese | 1476 | 1538 |
| LMArena French | 1435 | 1503 |
| LMArena Russian | 1460 | 1481 |
| LMArena Spanish | 1444 | 1492 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
Instruction Following Qwen3.8 Max leads
Gemma 4 31B IT: 75.5 (#61), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1433 | 1479 |
Long Context Qwen3.8 Max leads
Gemma 4 31B IT: 44.2 (#71), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1446 | 1489 |
Writing & Preference Qwen3.8 Max leads
Gemma 4 31B IT: 60.5 (#96), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Gemma 4 31B IT | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1443 | 1483 |
| LMArena Creative Writing | 1415 | 1479 |
| LMArena Multi-Turn | 1452 | 1489 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 20× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or Qwen3.8 Max?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Gemma 4 31B IT or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 262K.
How many benchmarks do Gemma 4 31B IT and Qwen3.8 Max share?
26 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen3.8 Max has 39.