Model comparison
Gemma 4 31B IT vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 19× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
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 0 categories and Qwen3.6 Max Preview in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Max Preview leads 57.6 to 37.9.
- The biggest single-benchmark swing is SimpleQA Verified: 10.4% for Gemma 4 31B IT and 52% for Qwen3.6 Max Preview.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 43.2 | 51.1 |
| Released | 2026-04-02 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 262K |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.09 | $1.30 |
| Output $ / M tokens | $0.34 | $7.80 |
| Results tracked | 35 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Gemma 4 31B IT: 41.9 (#98), Qwen3.6 Max Preview: 48.6 (#50)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1364 | 1482 |
| LMArena Coding | 1459 | 1472 |
| SWE-bench Verified | — | 76.7% |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Qwen3.6 Max Preview: —
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Gemma 4 31B IT: 26.4 (#119), Qwen3.6 Max Preview: 40.8 (#47)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| NYT Connections (extended) | 70.6% | 74.1% |
| Chess Puzzles | 5% | 20% |
| LMArena Hard Prompts | 1448 | 1457 |
| DTBench | 82.7% | 87.2% |
| LMCA | 39.3% | 42.5% |
| Epoch Capabilities Index | 142.74 | 149.27 |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 63.5% | — |
| CritPt | 1.4% | — |
| Thematic Generalization | 53% | — |
| Mystery Game Puzzles | — | 19% |
| Surface Evolver Bench | 30.6% | — |
Math Qwen3.6 Max Preview leads
Gemma 4 31B IT: 41.3 (#72), Qwen3.6 Max Preview: 52.2 (#40)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 91.1% |
| LMArena Math | 1464 | 1465 |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Gemma 4 31B IT: 37.9 (#141), Qwen3.6 Max Preview: 57.6 (#35)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 75.8% | 87.4% |
| SimpleQA Verified | 10.4% | 52% |
| LMArena Expert | 1465 | 1476 |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.0 (#32), Qwen3.6 Max Preview: —
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |
Multilingual Too close to call
Gemma 4 31B IT: 54.0 (#52), Qwen3.6 Max Preview: 54.3 (#46)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1431 | 1436 |
| LMArena Chinese | 1478 | 1487 |
| LMArena French | 1436 | 1449 |
| LMArena Russian | 1462 | 1444 |
| LMArena Spanish | 1443 | 1452 |
Instruction Following Too close to call
Gemma 4 31B IT: 75.6 (#58), Qwen3.6 Max Preview: 75.8 (#51)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1433 | 1437 |
Long Context Too close to call
Gemma 4 31B IT: 44.2 (#67), Qwen3.6 Max Preview: 44.6 (#59)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1446 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
Gemma 4 31B IT: 60.7 (#92), Qwen3.6 Max Preview: 64.0 (#58)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1443 | 1447 |
| LMArena Creative Writing | 1416 | 1435 |
| LMArena Multi-Turn | 1452 | 1456 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 19× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or Qwen3.6 Max Preview?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Gemma 4 31B IT or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 41.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Gemma 4 31B IT and Qwen3.6 Max Preview share?
23 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen3.6 Max Preview has 29.