Skip to main content

Model comparison

Gemma 4 31B vs MAI-Thinking-1

Data verified

Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.

61.08/100
No comparison
N/A
0 category wins2 category wins

Public leaderboard positions: Gemma 4 31B #43 (Supported); MAI-Thinking-1 unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemma 4 31B and MAI-Thinking-1 share 2 comparable benchmark results. 2 of 8 categories are comparable. 27 results are unique to Gemma 4 31B; 11 to MAI-Thinking-1.

Updated July 23, 2026
Shared results
2
Gemma 4 31B only
27
MAI-Thinking-1 only
11
Comparable categories
2 / 8

Treat this as a split decision. Gemma 4 31B makes more sense if its workflow fits your team better; MAI-Thinking-1 is the better fit if coding is the priority.

Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 1 evidence category; 2 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 and MAI-Thinking-1 finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

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 MAI-Thinking-1
CategoryGemma 4 31BΔMAI-Thinking-1
CodingGemma 4 31B41.6Margin 23.9MAI-Thinking-165.5
KnowledgeGemma 4 31B52.9Margin 19.6MAI-Thinking-172.5
AgenticGemma 4 31BNot measuredMarginNo overlapMAI-Thinking-146.0
MathGemma 4 31BNot measuredMarginNo overlapMAI-Thinking-189.7
MultimodalGemma 4 31B76.9MarginNo overlapMAI-Thinking-1Not measured
Inst. FollowingGemma 4 31BNot measuredMarginNo overlapMAI-Thinking-185.0

Decisive benchmark drivers

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

More
A · Gemma 4 31BB · MAI-Thinking-1
  1. MMLU-Pro

    Knowledge
    Source ↗
    A 85.2%B 85%
    Winner: Gemma 4 31BΔ 0.2
    MMLU-Pro: Gemma 4 31B scored 85.2%; MAI-Thinking-1 scored 85%. Gemma 4 31B wins this benchmark.
  2. GPQA

    Knowledge
    Source ↗
    A 84.3%B 84.2%
    Winner: Gemma 4 31BΔ 0.1
    GPQA: Gemma 4 31B scored 84.3%; MAI-Thinking-1 scored 84.2%. Gemma 4 31B wins this benchmark.

Operational comparison

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

MetricGemma 4 31BMAI-Thinking-1Comparison
Input / output priceUSD per 1M tokensGemma 4 31B$0 input / $0 outputMAI-Thinking-1Not availableA complete price comparison is not available.
Generation speedtokens per secondGemma 4 31BNot availableMAI-Thinking-1Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemma 4 31BNot availableMAI-Thinking-1Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemma 4 31B256KMAI-Thinking-1256KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGemma 4 31BMAI-Thinking-1Result
AA Agentic IndexSource 14.4%Not comparable
τ²-bench resultsSource 59.9%Not comparable
GDPval-AASource 15.2%Not comparable
GDPval-AASource 804Not comparable
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 46%Not comparable
CodingMAI-Thinking-1 wins
BenchmarkGemma 4 31BMAI-Thinking-1Result
SWE-RebenchSource 41.6%Not comparable
React Native EvalsSource 75.2%Not comparable
AA Coding IndexSource 43.4%Not comparable
AA-SciCodeSource 43.4%Not comparable
SWE-bench VerifiedSource 73.5%Not comparable
SWE-bench ProSource 52.8%Not comparable
Terminal-Bench 2.0Source 46.0%Not comparable
Reasoning
BenchmarkGemma 4 31BMAI-Thinking-1Result
AA-LCRSource 62.0%Not comparable
CritPtSource 1.4%Not comparable
Graphwalks BFS 128KSource 90%Not comparable
KnowledgeMAI-Thinking-1 wins
BenchmarkGemma 4 31BMAI-Thinking-1Result
GPQASource 84.3%84.2%Gemma 4 31B leads
MMLU-ProSource 85.2%85%Gemma 4 31B leads
HLESource 26.5%Not comparable
HLE w/o toolsSource 19.5%Not comparable
Artificial Analysis Intelligence IndexSource 29.4%Not comparable
AA-GPQA DiamondSource 85.7%Not comparable
AA-HLESource 22.7%Not comparable
AA-Omniscience IndexSource -45.4%Not comparable
AA-Omniscience AccuracySource 19.9%Not comparable
AA-Omniscience Hallucination RateSource 81.6%Not comparable
AA Openness IndexSource 38.9%Not comparable
GPQA-DSource 84.2%Not comparable
SimpleQASource 31%Not comparable
Math
BenchmarkGemma 4 31BMAI-Thinking-1Result
AIME 2025Source 97%Not comparable
AIME26Source 94.5%Not comparable
HMMT Feb 2026Source 84.9%Not comparable
Multimodal
BenchmarkGemma 4 31BMAI-Thinking-1Result
MMMU-ProSource 76.9%Not comparable
AA-MMMU-ProSource 73.4%Not comparable
Inst. Following
BenchmarkGemma 4 31BMAI-Thinking-1Result
AA-IFBenchSource 75.6%Not comparable
IFBenchSource 85%Not comparable
Frequently Asked Questions (3)

Which is better, Gemma 4 31B or MAI-Thinking-1?

Gemma 4 31B and MAI-Thinking-1 are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for knowledge tasks, Gemma 4 31B or MAI-Thinking-1?

MAI-Thinking-1 has the edge for knowledge tasks in this comparison, averaging 72.5 versus 52.9. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, Gemma 4 31B or MAI-Thinking-1?

MAI-Thinking-1 has the edge for coding in this comparison, averaging 65.5 versus 41.6. Gemma 4 31B stays close enough that the answer can still flip depending on your workload.

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
MAI-Thinking-1
API / mo$0
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Model the full break-even

Related Comparisons

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.