Model comparison
Gemma 4 31B IT vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 4.6× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Gemma 4 31B IT scores higher in 1 category and Qwen3.7 Plus in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 37.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.3% for Gemma 4 31B IT and 93.3% for Qwen3.7 Plus.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 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 | Qwen3.7 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 43.2 | 45.0 |
| Released | 2026-04-02 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.09 | $0.40 |
| Output $ / M tokens | $0.34 | $1.60 |
| Results tracked | 35 | 32 |
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: 41.9 (#98), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| SciCode | 43.4% | 45.5% |
| LMArena Coding | 1459 | 1473 |
| FrontierCode | — | 10.2% |
| LMArena WebDev | 1364 | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Qwen3.7 Plus: 21.2 (#130)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
Gemma 4 31B IT: 26.4 (#119), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 70.6% | 74.8% |
| CritPt | 1.4% | 9.1% |
| Chess Puzzles | 5% | 24% |
| LMArena Hard Prompts | 1448 | 1460 |
| DTBench | 82.7% | 84% |
| LMCA | 39.3% | 37.6% |
| Epoch Capabilities Index | 142.74 | 147.39 |
| Kagi LLM Benchmark | 63.5% | — |
| Thematic Generalization | 53% | — |
| Mystery Game Puzzles | — | 17% |
| Surface Evolver Bench | 30.6% | — |
Math Qwen3.7 Plus leads
Gemma 4 31B IT: 41.3 (#72), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 93.3% |
| LMArena Math | 1464 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
Knowledge Qwen3.7 Plus leads
Gemma 4 31B IT: 37.9 (#141), Qwen3.7 Plus: 54.9 (#46)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 75.8% | 87.9% |
| LMArena Expert | 1465 | 1467 |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Too close to call
Gemma 4 31B IT: 41.0 (#32), Qwen3.7 Plus: 41.2 (#30)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1278 | 1281 |
| LMArena Document | 1425 | 1444 |
Multilingual Too close to call
Gemma 4 31B IT: 54.0 (#52), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1431 | 1445 |
| LMArena Chinese | 1478 | 1510 |
| LMArena French | 1436 | 1471 |
| LMArena Russian | 1462 | 1457 |
| LMArena Spanish | 1443 | 1453 |
| LMArena German | — | 1471 |
| LMArena Japanese | — | 1411 |
| LMArena Korean | — | 1416 |
Instruction Following Too close to call
Gemma 4 31B IT: 75.6 (#58), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1433 | 1439 |
Long Context Too close to call
Gemma 4 31B IT: 44.2 (#67), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1446 | 1454 |
Writing & Preference Qwen3.7 Plus leads
Gemma 4 31B IT: 60.7 (#92), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | Gemma 4 31B IT | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1443 | 1454 |
| LMArena Creative Writing | 1416 | 1439 |
| LMArena Multi-Turn | 1452 | 1459 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 4.6× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or Qwen3.7 Plus?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is Gemma 4 31B IT or Qwen3.7 Plus better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 262K.
How many benchmarks do Gemma 4 31B IT and Qwen3.7 Plus share?
25 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen3.7 Plus has 32.