Model comparison
Gemma 4 31B IT vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 7.4× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Gemma 4 31B IT scores higher in 3 categories and Qwen3.6 Plus in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 37.9.
- The biggest single-benchmark swing is SimpleQA Verified: 10.4% for Gemma 4 31B IT and 44.1% for Qwen3.6 Plus.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus 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 | Qwen3.6 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 43.5 | 47.5 |
| Released | 2026-04-02 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.09 | $0.50 |
| Output $ / M tokens | $0.34 | $3 |
| Results tracked | 35 | 37 |
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), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1366 | 1461 |
| SciCode | 43.4% | 40.7% |
| LMArena Coding | 1459 | 1467 |
| ALE-Bench | 925.5 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| WeirdML | 52.3% | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Qwen3.6 Plus: —
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
Gemma 4 31B IT: 27.2 (#122), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 70.6% | 60.3% |
| CritPt | 1.4% | 2.9% |
| Chess Puzzles | 5% | 17% |
| Thematic Generalization | 53% | 59.5% |
| LMArena Hard Prompts | 1448 | 1449 |
| DTBench | 82.7% | 81.9% |
| LMCA | 39.3% | 33.1% |
| Epoch Capabilities Index | 142.74 | 147.65 |
| Kagi LLM Benchmark | 63.5% | — |
| Mystery Game Puzzles | — | 12% |
| Surface Evolver Bench | 30.6% | — |
Math Qwen3.6 Plus leads
Gemma 4 31B IT: 43.2 (#81), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 93.3% |
| LMArena Math | 1465 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
Gemma 4 31B IT: 37.9 (#151), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 75.8% | 88.4% |
| SimpleQA Verified | 10.4% | 44.1% |
| LMArena Expert | 1465 | 1454 |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Qwen3.6 Plus: —
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Too close to call
Gemma 4 31B IT: 53.8 (#57), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1431 | 1424 |
| LMArena Chinese | 1476 | 1477 |
| LMArena French | 1435 | 1455 |
| LMArena Russian | 1460 | 1434 |
| LMArena Spanish | 1444 | 1432 |
| LMArena German | — | 1452 |
| LMArena Japanese | — | 1389 |
| LMArena Korean | — | 1379 |
Instruction Following Too close to call
Gemma 4 31B IT: 75.5 (#61), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1433 | 1425 |
Long Context Too close to call
Gemma 4 31B IT: 44.2 (#71), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1446 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
Gemma 4 31B IT: 60.5 (#96), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Gemma 4 31B IT | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1443 | 1437 |
| LMArena Creative Writing | 1415 | 1404 |
| LMArena Multi-Turn | 1452 | 1438 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 7.4× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or Qwen3.6 Plus?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is Gemma 4 31B IT or Qwen3.6 Plus better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 262K.
How many benchmarks do Gemma 4 31B IT and Qwen3.6 Plus share?
27 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen3.6 Plus has 37.