Model comparison
Gemma 4 31B IT vs Qwen3 235B-A22B
Gemma 4 31B IT and Qwen3 235B-A22B score almost the same on the Noometry Index (43.5 vs 43.5), so choose on price, context window or the category you care about most.
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 4 categories and Qwen3 235B-A22B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.6 to 37.9.
- The biggest single-benchmark swing is SimpleQA Verified: 10.4% for Gemma 4 31B IT and 40.4% for Qwen3 235B-A22B.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Gemma 4 31B IT accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 4 31B IT | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 43.5 | 43.5 |
| Released | 2026-04-02 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 33K | 16K |
| Input $ / M tokens | $0.09 | $0.70 |
| Output $ / M tokens | $0.34 | $2.80 |
| Results tracked | 35 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Gemma 4 31B IT: 42.3 (#108), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 43.4% | 42.4% |
| WeirdML | 52.3% | 41% |
| LMArena Coding | 1459 | 1445 |
| Aider Polyglot | — | 59.6% |
| LMArena WebDev | 1366 | — |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 69.4% |
| CritPt | 1.4% | 0% |
| Chess Puzzles | 5% | 12% |
| LMArena Hard Prompts | 1448 | 1433 |
| DTBench | 82.7% | 80.3% |
| LMCA | 39.3% | 29.3% |
| Epoch Capabilities Index | 142.74 | 143.85 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| NYT Connections (extended) | 70.6% | — |
| ARC-AGI-1 | — | 11% |
| Thematic Generalization | 53% | — |
| Mystery Game Puzzles | — | 9% |
| Surface Evolver Bench | 30.6% | — |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
Gemma 4 31B IT: 43.2 (#81), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 86.7% |
| LMArena Math | 1465 | 1432 |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Gemma 4 31B IT: 37.9 (#151), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 75.8% | 80.1% |
| SimpleQA Verified | 10.4% | 40.4% |
| Vectara Hallucination Rate | 7.4% | 9.3% |
| LMArena Expert | 1465 | 1463 |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| GPQA (HELM) | — | 72.7% |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Qwen3 235B-A22B: —
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1431 | 1409 |
| LMArena Chinese | 1476 | 1481 |
| LMArena French | 1435 | 1445 |
| LMArena Russian | 1460 | 1411 |
| LMArena Spanish | 1444 | 1430 |
| LMArena German | — | 1433 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1391 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Gemma 4 31B IT: 44.2 (#71), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1446 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Too close to call
Gemma 4 31B IT: 60.5 (#96), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Gemma 4 31B IT | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1443 | 1419 |
| LMArena Creative Writing | 1415 | 1384 |
| EQ-Bench Creative Writing | 1368 | 1366 |
| LMArena Multi-Turn | 1452 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Qwen3 235B-A22B?
Gemma 4 31B IT and Qwen3 235B-A22B score almost the same on the Noometry Index (43.5 vs 43.5), so choose on price, context window or the category you care about most.
Which is cheaper, Gemma 4 31B IT or Qwen3 235B-A22B?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is Gemma 4 31B IT or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 131K.
How many benchmarks do Gemma 4 31B IT and Qwen3 235B-A22B share?
27 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen3 235B-A22B has 49.