Model comparison

Gemma 4 31B vs Qwen3.5-122B-A10B

Data verified July 23, 2026

Head-to-head evidence from 18 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Gemma 4 31B

Google

61.08/100

Margin

0.5pts

← winning

Qwen3.5-122B-A10B

Alibaba

60.56/100

0 category wins3 category wins

Public leaderboard positions: Gemma 4 31B #43 (Supported); Qwen3.5-122B-A10B #47 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemma 4 31B and Qwen3.5-122B-A10B share 18 comparable benchmark results. 3 of 8 categories are comparable. 11 results are unique to Gemma 4 31B; 13 to Qwen3.5-122B-A10B.

Updated July 23, 2026

Shared results: 18
Gemma 4 31B only: 11
Qwen3.5-122B-A10B only: 13
Comparable categories: 3 / 8

Pick Gemma 4 31B if you want the stronger benchmark profile. Qwen3.5-122B-A10B only becomes the better choice if knowledge is the priority or you need the larger 262K context window.

Confidence note. This is a partial-evidence comparison with 18 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 BenchAlign overall profile here, landing at 61.08 versus 60.56. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Qwen3.5-122B-A10B 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 scores and score margins for Gemma 4 31B and Qwen3.5-122B-A10B
Category	Gemma 4 31B	Δ	Qwen3.5-122B-A10B
Knowledge	Gemma 4 31B52.9	Margin→ 30.7	Qwen3.5-122B-A10B83.6
Coding	Gemma 4 31B41.6	Margin→ 30.4	Qwen3.5-122B-A10B72.0
Multimodal	Gemma 4 31B76.9	Margin→ 0.3	Qwen3.5-122B-A10B77.2
Agentic	Gemma 4 31BNot measured	MarginNo overlap	Qwen3.5-122B-A10B56.4
Reasoning	Gemma 4 31BNot measured	MarginNo overlap	Qwen3.5-122B-A10B60.2
Multilingual	Gemma 4 31BNot measured	MarginNo overlap	Qwen3.5-122B-A10B82.2
Inst. Following	Gemma 4 31BNot measured	MarginNo overlap	Qwen3.5-122B-A10B93.4

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

A · Gemma 4 31BB · Qwen3.5-122B-A10B

GPQA
Knowledge
Source ↗
A 84.3%B 86.6%
Winner: Qwen3.5-122B-A10BΔ 2.3
GPQA: Gemma 4 31B scored 84.3%; Qwen3.5-122B-A10B scored 86.6%. Qwen3.5-122B-A10B wins this benchmark.
MMLU-Pro
Knowledge
Source ↗
A 85.2%B 86.7%
Winner: Qwen3.5-122B-A10BΔ 1.5
MMLU-Pro: Gemma 4 31B scored 85.2%; Qwen3.5-122B-A10B scored 86.7%. Qwen3.5-122B-A10B wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

Metric	Gemma 4 31B	Qwen3.5-122B-A10B	Comparison
Input / output priceUSD per 1M tokens	Gemma 4 31B$0 input / $0 output	Qwen3.5-122B-A10B$0 input / $0 output	Listed prices are equal.
Generation speedtokens per second	Gemma 4 31BNot available	Qwen3.5-122B-A10BNot available	A complete speed comparison is not available.
First-answer latencyseconds to first token	Gemma 4 31BNot available	Qwen3.5-122B-A10BNot available	A complete latency comparison is not available.
Context windowmaximum listed tokens	Gemma 4 31B256K	Qwen3.5-122B-A10B262K	Qwen3.5-122B-A10B lists the larger context window.

Benchmark Deep Dive

Agentic

12 benchmarks

Benchmark	Gemma 4 31B	Qwen3.5-122B-A10B	Result
AA Agentic IndexSource	14.4%	20.7%	Qwen3.5-122B-A10B leads
τ²-bench resultsSource	59.9%	93.6%	Qwen3.5-122B-A10B leads
GDPval-AASource	15.2%	23.9%	Qwen3.5-122B-A10B leads
GDPval-AASource	804	978	Qwen3.5-122B-A10B leads
Gert LabsSource	35.26%	—	Not comparable
AA EnterpriseOps-GymSource	28.3%	—	Not comparable
AA ITBenchSource	37.3%	—	Not comparable
AA Tau3 BankingSource	15.1%	—	Not comparable
terminalBenchHardSource	36.4%	—	Not comparable
Terminal-Bench 2.0Source	—	49.4%	Not comparable
BrowseCompSource	—	63.8%	Not comparable
OSWorld-VerifiedSource	—	58%	Not comparable

CodingQwen3.5-122B-A10B wins

5 benchmarks

Benchmark	Gemma 4 31B	Qwen3.5-122B-A10B	Result
SWE-RebenchSource	41.6%	—	Not comparable
React Native EvalsSource	75.2%	—	Not comparable
AA Coding IndexSource	43.4%	45.7%	Qwen3.5-122B-A10B leads
AA-SciCodeSource	43.4%	42.0%	Gemma 4 31B leads
SWE-bench VerifiedSource	—	72%	Not comparable

Reasoning

3 benchmarks

Benchmark	Gemma 4 31B	Qwen3.5-122B-A10B	Result
AA-LCRSource	62.0%	66.7%	Qwen3.5-122B-A10B leads
CritPtSource	1.4%	0.6%	Gemma 4 31B leads
LongBench v2Source	—	60.2%	Not comparable

KnowledgeQwen3.5-122B-A10B wins

12 benchmarks

Benchmark	Gemma 4 31B	Qwen3.5-122B-A10B	Result
GPQASource	84.3%	86.6%	Qwen3.5-122B-A10B leads
MMLU-ProSource	85.2%	86.7%	Qwen3.5-122B-A10B leads
HLESource	26.5%	—	Not comparable
HLE w/o toolsSource	19.5%	—	Not comparable
Artificial Analysis Intelligence IndexSource	29.4%	32.3%	Qwen3.5-122B-A10B leads
AA-GPQA DiamondSource	85.7%	85.7%	Tie
AA-HLESource	22.7%	23.4%	Qwen3.5-122B-A10B leads
AA-Omniscience IndexSource	-45.4%	-39.6%	Qwen3.5-122B-A10B leads
AA-Omniscience AccuracySource	19.9%	24.7%	Qwen3.5-122B-A10B leads
AA-Omniscience Hallucination RateSource	81.6%	85.5%	Gemma 4 31B leads
AA Openness IndexSource	38.9%	—	Not comparable
SuperGPQASource	—	67.1%	Not comparable

Multilingual

1 benchmarks

Benchmark	Gemma 4 31B	Qwen3.5-122B-A10B	Result
MMLU-ProXSource	—	82.2%	Not comparable

MultimodalQwen3.5-122B-A10B wins

7 benchmarks

Benchmark	Gemma 4 31B	Qwen3.5-122B-A10B	Result
MMMU-ProSource	76.9%	—	Not comparable
AA-MMMU-ProSource	73.4%	75.0%	Qwen3.5-122B-A10B leads
MMMUSource	—	83.9%	Not comparable
MMVUSource	—	74.7%	Not comparable
MathVisionSource	—	86.2%	Not comparable
CharXivSource	—	77.2%	Not comparable
V*Source	—	93.2%	Not comparable

Inst. Following

2 benchmarks

Benchmark	Gemma 4 31B	Qwen3.5-122B-A10B	Result
AA-IFBenchSource	75.6%	75.7%	Qwen3.5-122B-A10B leads
IFEvalSource	—	93.4%	Not comparable

Frequently Asked Questions (4)

Which is better, Gemma 4 31B or Qwen3.5-122B-A10B?

Gemma 4 31B is ahead on BenchLM's BenchAlign leaderboard, 61.08 to 60.56. The biggest single separator in this matchup is GPQA, where the scores are 84.3% and 86.6%.

Which is better for knowledge tasks, Gemma 4 31B or Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 83.6 versus 52.9. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Which is better for coding, Gemma 4 31B or Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B has the edge for coding in this comparison, averaging 72 versus 41.6. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Gemma 4 31B or Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B has the edge for multimodal and grounded tasks in this comparison, averaging 77.2 versus 76.9. Inside this category, AA-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.

Gemma 4 31B

API / mo$0

Self-host / mo$429

Break-even—

Qwen3.5-122B-A10B

API / mo$0

Self-host / moNot listed

Break-even—

Proprietary model — self-hosting not applicable.

Model the full break-even

Related Comparisons

Explore More

Google Compare Pricing Methodology Find Your Best LLM Overall Rankings

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.