Skip to main content

Model comparison

MAI-Thinking-1 vs Qwen3.5-35B-A3B

Data verified

Head-to-head evidence from 4 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

N/A
No comparison
56.97/100
1 category wins3 category wins

Public leaderboard positions: MAI-Thinking-1 unranked (Not scored); Qwen3.5-35B-A3B #72 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MAI-Thinking-1 and Qwen3.5-35B-A3B share 4 comparable benchmark results. 4 of 8 categories are comparable. 9 results are unique to MAI-Thinking-1; 24 to Qwen3.5-35B-A3B.

Updated July 23, 2026
Shared results
4
MAI-Thinking-1 only
9
Qwen3.5-35B-A3B only
24
Comparable categories
4 / 8

Treat this as a split decision. MAI-Thinking-1 makes more sense if coding is the priority; Qwen3.5-35B-A3B is the better fit if knowledge is the priority or you need the larger 262K context window.

Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 3 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

MAI-Thinking-1 and Qwen3.5-35B-A3B 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.

Qwen3.5-35B-A3B gives you the larger context window at 262K, compared with 256K for MAI-Thinking-1.

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 MAI-Thinking-1 and Qwen3.5-35B-A3B
CategoryMAI-Thinking-1ΔQwen3.5-35B-A3B
KnowledgeMAI-Thinking-172.5Margin 9.1Qwen3.5-35B-A3B81.6
Inst. FollowingMAI-Thinking-185.0Margin 6.9Qwen3.5-35B-A3B91.9
AgenticMAI-Thinking-146.0Margin 5.0Qwen3.5-35B-A3B51.0
CodingMAI-Thinking-165.5Margin 4.9Qwen3.5-35B-A3B60.6
ReasoningMAI-Thinking-1Not measuredMarginNo overlapQwen3.5-35B-A3B59.0
MathMAI-Thinking-189.7MarginNo overlapQwen3.5-35B-A3BNot measured
MultilingualMAI-Thinking-1Not measuredMarginNo overlapQwen3.5-35B-A3B81.0

Decisive benchmark drivers

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

More
A · MAI-Thinking-1B · Qwen3.5-35B-A3B
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 46%B 40.5%
    Winner: MAI-Thinking-1Δ 5.5
    Terminal-Bench 2.0: MAI-Thinking-1 scored 46%; Qwen3.5-35B-A3B scored 40.5%. MAI-Thinking-1 wins this benchmark.
  2. SWE-bench Verified

    Coding
    Source ↗
    A 73.5%B 69.2%
    Winner: MAI-Thinking-1Δ 4.3
    SWE-bench Verified: MAI-Thinking-1 scored 73.5%; Qwen3.5-35B-A3B scored 69.2%. MAI-Thinking-1 wins this benchmark.
  3. MMLU-Pro

    Knowledge
    Source ↗
    A 85%B 85.3%
    Winner: Qwen3.5-35B-A3BΔ 0.3
    MMLU-Pro: MAI-Thinking-1 scored 85%; Qwen3.5-35B-A3B scored 85.3%. Qwen3.5-35B-A3B wins this benchmark.

Operational comparison

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

MetricMAI-Thinking-1Qwen3.5-35B-A3BComparison
Input / output priceUSD per 1M tokensMAI-Thinking-1Not availableQwen3.5-35B-A3B$0 input / $0 outputA complete price comparison is not available.
Generation speedtokens per secondMAI-Thinking-1Not availableQwen3.5-35B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMAI-Thinking-1Not availableQwen3.5-35B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMAI-Thinking-1256KQwen3.5-35B-A3B262KQwen3.5-35B-A3B lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.5-35B-A3B wins
BenchmarkMAI-Thinking-1Qwen3.5-35B-A3BResult
Terminal-Bench 2.0Source 46%40.5%MAI-Thinking-1 leads
BrowseCompSource 61%Not comparable
OSWorld-VerifiedSource 54.5%Not comparable
τ²-bench resultsSource 89.2%Not comparable
Gert LabsSource 28.96%Not comparable
CodingMAI-Thinking-1 wins
BenchmarkMAI-Thinking-1Qwen3.5-35B-A3BResult
SWE-bench VerifiedSource 73.5%69.2%MAI-Thinking-1 leads
SWE-bench ProSource 52.8%Not comparable
Terminal-Bench 2.0Source 46.0%Not comparable
SWE-RebenchSource 53.7%Not comparable
AA-SciCodeSource 37.7%Not comparable
Reasoning
BenchmarkMAI-Thinking-1Qwen3.5-35B-A3BResult
Graphwalks BFS 128KSource 90%Not comparable
LongBench v2Source 59%Not comparable
AA-LCRSource 62.7%Not comparable
CritPtSource 0.9%Not comparable
KnowledgeQwen3.5-35B-A3B wins
BenchmarkMAI-Thinking-1Qwen3.5-35B-A3BResult
GPQASource 84.2%84.2%Tie
GPQA-DSource 84.2%Not comparable
MMLU-ProSource 85%85.3%Qwen3.5-35B-A3B leads
SimpleQASource 31%Not comparable
SuperGPQASource 63.4%Not comparable
Artificial Analysis Intelligence IndexSource 29.3%Not comparable
AA-GPQA DiamondSource 84.5%Not comparable
AA-HLESource 19.7%Not comparable
AA-Omniscience IndexSource -46.4%Not comparable
AA-Omniscience AccuracySource 20.5%Not comparable
AA-Omniscience Hallucination RateSource 84.0%Not comparable
Math
BenchmarkMAI-Thinking-1Qwen3.5-35B-A3BResult
AIME 2025Source 97%Not comparable
AIME26Source 94.5%Not comparable
HMMT Feb 2026Source 84.9%Not comparable
Multilingual
BenchmarkMAI-Thinking-1Qwen3.5-35B-A3BResult
MMLU-ProXSource 81%Not comparable
Multimodal
BenchmarkMAI-Thinking-1Qwen3.5-35B-A3BResult
MMMUSource 81.4%Not comparable
MMVUSource 72.3%Not comparable
MathVisionSource 83.9%Not comparable
V*Source 92.7%Not comparable
AA-MMMU-ProSource 72.7%Not comparable
Inst. FollowingQwen3.5-35B-A3B wins
BenchmarkMAI-Thinking-1Qwen3.5-35B-A3BResult
IFBenchSource 85%Not comparable
IFEvalSource 91.9%Not comparable
AA-IFBenchSource 72.5%Not comparable
Frequently Asked Questions (5)

Which is better, MAI-Thinking-1 or Qwen3.5-35B-A3B?

MAI-Thinking-1 and Qwen3.5-35B-A3B 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, MAI-Thinking-1 or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 72.5. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, MAI-Thinking-1 or Qwen3.5-35B-A3B?

MAI-Thinking-1 has the edge for coding in this comparison, averaging 65.5 versus 60.6. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, MAI-Thinking-1 or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has the edge for agentic tasks in this comparison, averaging 51 versus 46. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for instruction following, MAI-Thinking-1 or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has the edge for instruction following in this comparison, averaging 91.9 versus 85. MAI-Thinking-1 stays close enough that the answer can still flip depending on your workload.

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.