Model comparison
Gemma 4 31B vs Qwen3.6-35B-A3B
Head-to-head evidence from 22 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: Gemma 4 31B unranked; Qwen3.6-35B-A3B #31
BenchAlign evidence: Gemma 4 31B supported; Qwen3.6-35B-A3B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Gemma 4 31B and Qwen3.6-35B-A3B share 22 comparable benchmark results. 3 of 8 categories are comparable. 8 results are unique to Gemma 4 31B; 36 to Qwen3.6-35B-A3B.
Updated July 15, 2026- Shared results
- 22
- Gemma 4 31B only
- 8
- Qwen3.6-35B-A3B only
- 36
- Comparable categories
- 3 / 8
Pick Gemma 4 31B if you want the stronger benchmark profile. Qwen3.6-35B-A3B only becomes the better choice if coding is the priority or you need the larger 262K context window.
Confidence note. This is a partial-evidence comparison with 22 shared benchmark results across 6 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Gemma 4 31B has the cleaner provisional overall profile here, landing at 62 versus 59. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Gemma 4 31B's sharpest advantage is in knowledge, where it averages 53.3 against 51.8. The single biggest benchmark swing on the page is HLE, 26.5% to 21.4%. Qwen3.6-35B-A3B does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Qwen3.6-35B-A3B gives you the larger context window at 262K, compared with 256K for Gemma 4 31B.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Gemma 4 31B | Δ | Qwen3.6-35B-A3B |
|---|---|---|---|
| Coding | Gemma 4 31B41.6 | Margin→ 32.2 | Qwen3.6-35B-A3B73.8 |
| Knowledge | Gemma 4 31B53.3 | Margin← 1.5 | Qwen3.6-35B-A3B51.8 |
| Multimodal | Gemma 4 31B76.9 | Margin← 0.6 | Qwen3.6-35B-A3B76.3 |
| Agentic | Gemma 4 31BNot measured | MarginNo overlap | Qwen3.6-35B-A3B51.5 |
| Math | Gemma 4 31BNot measured | MarginNo overlap | Qwen3.6-35B-A3B88.2 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
HLE
KnowledgeA 26.5%B 21.4%Winner: Gemma 4 31BΔ 5.1HLE: Gemma 4 31B scored 26.5%; Qwen3.6-35B-A3B scored 21.4%. Gemma 4 31B wins this benchmark. - Source ↗
GPQA
KnowledgeA 84.3%B 86%Winner: Qwen3.6-35B-A3BΔ 1.7GPQA: Gemma 4 31B scored 84.3%; Qwen3.6-35B-A3B scored 86%. Qwen3.6-35B-A3B wins this benchmark. - Source ↗
MMMU-Pro
MultimodalA 76.9%B 75.3%Winner: Gemma 4 31BΔ 1.6MMMU-Pro: Gemma 4 31B scored 76.9%; Qwen3.6-35B-A3B scored 75.3%. Gemma 4 31B wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Gemma 4 31B | Qwen3.6-35B-A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Gemma 4 31B$0 input / $0 output | Qwen3.6-35B-A3BNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Gemma 4 31BNot available | Qwen3.6-35B-A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Gemma 4 31BNot available | Qwen3.6-35B-A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Gemma 4 31B256K | Qwen3.6-35B-A3B262K | Qwen3.6-35B-A3B lists the larger context window. |
Benchmark Deep Dive
Agentic19 benchmarks
| Benchmark | Gemma 4 31B | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| AA Agentic IndexSource | 14.4% | 21.4% | Qwen3.6-35B-A3B leads |
| τ²-bench resultsSource | 59.9% | 95.3% | Qwen3.6-35B-A3B leads |
| GDPval-AASource | 15.2% | 27.4% | Qwen3.6-35B-A3B leads |
| GDPval-AASource | 804 | 1049 | Qwen3.6-35B-A3B leads |
| Gert LabsSource | 35.26% | 42.65% | Qwen3.6-35B-A3B leads |
| AA EnterpriseOps-GymSource | 28.3% | — | Not comparable |
| AA Harvey LABSource | 0.0% | — | Not comparable |
| AA ITBenchSource | 37.3% | — | Not comparable |
| AA Tau3 BankingSource | 15.1% | — | Not comparable |
| Terminal-Bench 2.0Source | — | 51.5% | Not comparable |
| Claw-EvalSource | — | 68.7% | Not comparable |
| QwenClawBenchSource | — | 52.6% | Not comparable |
| QwenWebBenchSource | — | 1397 | Not comparable |
| τ³-bench resultsSource | — | 67.2% | Not comparable |
| VITA-BenchSource | — | 35.6% | Not comparable |
| DeepPlanningSource | — | 25.9% | Not comparable |
| ToolathlonSource | — | 26.9% | Not comparable |
| MCP AtlasSource | — | 62.8% | Not comparable |
| WideResearchSource | — | 60.1% | Not comparable |
CodingQwen3.6-35B-A3B wins11 benchmarks
| Benchmark | Gemma 4 31B | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| SWE-RebenchSource | 41.6% | — | Not comparable |
| React Native EvalsSource | 75.2% | — | Not comparable |
| AA Coding IndexSource | 43.4% | 41.9% | Gemma 4 31B leads |
| Terminal-Bench HardSource | 36.4% | 34.8% | Gemma 4 31B leads |
| AA-SciCodeSource | 43.4% | 35.8% | Gemma 4 31B leads |
| SWE-bench VerifiedSource | — | 73.4% | Not comparable |
| SWE MultilingualSource | — | 67.2% | Not comparable |
| SWE-bench ProSource | — | 49.5% | Not comparable |
| Terminal-Bench 2.0Source | — | 51.5% | Not comparable |
| LiveCodeBenchSource | — | 80.4% | Not comparable |
| NL2RepoSource | — | 29.4% | Not comparable |
Reasoning2 benchmarks
KnowledgeGemma 4 31B wins13 benchmarks
| Benchmark | Gemma 4 31B | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| GPQASource | 84.3% | 86% | Qwen3.6-35B-A3B leads |
| MMLU-ProSource | 85.2% | 85.2% | Tie |
| HLESource | 26.5% | 21.4% | Gemma 4 31B leads |
| HLE w/o toolsSource | 19.5% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 29.4% | 31.6% | Qwen3.6-35B-A3B leads |
| AA-GPQA DiamondSource | 85.7% | 84.1% | Gemma 4 31B leads |
| AA-HLESource | 22.7% | 20.2% | Gemma 4 31B leads |
| AA-Omniscience IndexSource | -45.4% | -21.4% | Qwen3.6-35B-A3B leads |
| AA-Omniscience AccuracySource | 19.9% | 18.9% | Gemma 4 31B leads |
| AA-Omniscience Hallucination RateSource | 81.6% | 49.7% | Qwen3.6-35B-A3B leads |
| AA Openness IndexSource | 38.9% | — | Not comparable |
| SuperGPQASource | — | 64.7% | Not comparable |
| C-EvalSource | — | 90% | Not comparable |
Math5 benchmarks
MultimodalGemma 4 31B wins15 benchmarks
| Benchmark | Gemma 4 31B | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| MMMU-ProSource | 76.9% | 75.3% | Gemma 4 31B leads |
| AA-MMMU-ProSource | 73.4% | 75.0% | Qwen3.6-35B-A3B leads |
| MMMUSource | — | 81.7% | Not comparable |
| RealWorldQASource | — | 85.3% | Not comparable |
| OmniDocBench 1.5Source | — | 89.9% | Not comparable |
| CharXivSource | — | 78% | Not comparable |
| SimpleVQASource | — | 58.9% | Not comparable |
| CC-OCRSource | — | 81.9% | Not comparable |
| AI2D_TESTSource | — | 92.7% | Not comparable |
| RefCOCO (avg)Source | — | 92.0% | Not comparable |
| ODINW13Source | — | 50.8% | Not comparable |
| Video-MME (with subtitle)Source | — | 86.6% | Not comparable |
| Video-MME (w/o subtitle)Source | — | 82.5% | Not comparable |
| VideoMMMUSource | — | 83.7% | Not comparable |
| MLVU (M-Avg)Source | — | 86.2% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Gemma 4 31B | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| AA-IFBenchSource | 75.6% | 64.4% | Gemma 4 31B leads |
Frequently Asked Questions (4)
Which is better, Gemma 4 31B or Qwen3.6-35B-A3B?
Gemma 4 31B is ahead on BenchLM's provisional leaderboard, 62 to 59. The biggest single separator in this matchup is HLE, where the scores are 26.5% and 21.4%.
Which is better for knowledge tasks, Gemma 4 31B or Qwen3.6-35B-A3B?
Gemma 4 31B has the edge for knowledge tasks in this comparison, averaging 53.3 versus 51.8. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.
Which is better for coding, Gemma 4 31B or Qwen3.6-35B-A3B?
Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 versus 41.6. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Gemma 4 31B or Qwen3.6-35B-A3B?
Gemma 4 31B has the edge for multimodal and grounded tasks in this comparison, averaging 76.9 versus 76.3. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.