Skip to main content

Model comparison

MAI-Thinking-1 vs Qwen 3.6 Max (preview)

Data verified

Head-to-head evidence from 3 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

N/A
No comparison
59.72/100
2 category wins2 category wins

Public leaderboard positions: MAI-Thinking-1 unranked (Not scored); Qwen 3.6 Max (preview) #53 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MAI-Thinking-1 and Qwen 3.6 Max (preview) share 3 comparable benchmark results. 4 of 8 categories are comparable. 10 results are unique to MAI-Thinking-1; 18 to Qwen 3.6 Max (preview).

Updated July 23, 2026
Shared results
3
MAI-Thinking-1 only
10
Qwen 3.6 Max (preview) only
18
Comparable categories
4 / 8

Treat this as a split decision. MAI-Thinking-1 makes more sense if mathematics is the priority; Qwen 3.6 Max (preview) is the better fit if agentic is the priority.

Confidence note. This is a partial-evidence comparison with 3 shared benchmark results across 2 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 Qwen 3.6 Max (preview) 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 MAI-Thinking-1 and Qwen 3.6 Max (preview)
CategoryMAI-Thinking-1ΔQwen 3.6 Max (preview)
MathMAI-Thinking-189.7Margin 71.3Qwen 3.6 Max (preview)18.4
AgenticMAI-Thinking-146.0Margin 19.4Qwen 3.6 Max (preview)65.4
CodingMAI-Thinking-165.5Margin 14.5Qwen 3.6 Max (preview)51.0
KnowledgeMAI-Thinking-172.5Margin 1.4Qwen 3.6 Max (preview)73.9
Inst. FollowingMAI-Thinking-185.0MarginNo overlapQwen 3.6 Max (preview)Not measured

Decisive benchmark drivers

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

More
A · MAI-Thinking-1B · Qwen 3.6 Max (preview)
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 46%B 65.4%
    Winner: Qwen 3.6 Max (preview)Δ 19.4
    Terminal-Bench 2.0: MAI-Thinking-1 scored 46%; Qwen 3.6 Max (preview) scored 65.4%. Qwen 3.6 Max (preview) wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 52.8%B 57.3%
    Winner: Qwen 3.6 Max (preview)Δ 4.5
    SWE-bench Pro: MAI-Thinking-1 scored 52.8%; Qwen 3.6 Max (preview) scored 57.3%. Qwen 3.6 Max (preview) wins this benchmark.

Operational comparison

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

MetricMAI-Thinking-1Qwen 3.6 Max (preview)Comparison
Input / output priceUSD per 1M tokensMAI-Thinking-1Not availableQwen 3.6 Max (preview)Not availableA complete price comparison is not available.
Generation speedtokens per secondMAI-Thinking-1Not availableQwen 3.6 Max (preview)Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMAI-Thinking-1Not availableQwen 3.6 Max (preview)Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensMAI-Thinking-1256KQwen 3.6 Max (preview)256KListed context windows are equal.

Benchmark Deep Dive

AgenticQwen 3.6 Max (preview) wins
BenchmarkMAI-Thinking-1Qwen 3.6 Max (preview)Result
Terminal-Bench 2.0Source 46%65.4%Qwen 3.6 Max (preview) leads
QwenClawBenchSource 59.0%Not comparable
QwenWebBenchSource 1532Not comparable
τ²-bench resultsSource 95.9%Not comparable
CodingMAI-Thinking-1 wins
BenchmarkMAI-Thinking-1Qwen 3.6 Max (preview)Result
SWE-bench VerifiedSource 73.5%Not comparable
SWE-bench ProSource 52.8%57.3%Qwen 3.6 Max (preview) leads
Terminal-Bench 2.0Source 46.0%65.4%Qwen 3.6 Max (preview) leads
SciCodeSource 47%Not comparable
NL2RepoSource 42.9%Not comparable
AA-SciCodeSource 46.9%Not comparable
Reasoning
BenchmarkMAI-Thinking-1Qwen 3.6 Max (preview)Result
Graphwalks BFS 128KSource 90%Not comparable
AA-LCRSource 69.7%Not comparable
CritPtSource 3.7%Not comparable
KnowledgeQwen 3.6 Max (preview) wins
BenchmarkMAI-Thinking-1Qwen 3.6 Max (preview)Result
GPQASource 84.2%Not comparable
GPQA-DSource 84.2%Not comparable
MMLU-ProSource 85%Not comparable
SimpleQASource 31%Not comparable
SuperGPQASource 73.9%Not comparable
Artificial Analysis Intelligence IndexSource 40.0%Not comparable
AA-GPQA DiamondSource 88.8%Not comparable
AA-HLESource 28.9%Not comparable
AA-Omniscience IndexSource 10.2%Not comparable
AA-Omniscience AccuracySource 37.7%Not comparable
AA-Omniscience Hallucination RateSource 44.2%Not comparable
MathMAI-Thinking-1 wins
BenchmarkMAI-Thinking-1Qwen 3.6 Max (preview)Result
AIME 2025Source 97%Not comparable
AIME26Source 94.5%Not comparable
HMMT Feb 2026Source 84.9%Not comparable
FrontierMath v2 (Tiers 1-3)Source 23.103%Not comparable
FrontierMath v2 (Tier 4)Source 4.167%Not comparable
Inst. Following
BenchmarkMAI-Thinking-1Qwen 3.6 Max (preview)Result
IFBenchSource 85%Not comparable
AA-IFBenchSource 76.6%Not comparable
Frequently Asked Questions (5)

Which is better, MAI-Thinking-1 or Qwen 3.6 Max (preview)?

MAI-Thinking-1 and Qwen 3.6 Max (preview) 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 Qwen 3.6 Max (preview)?

Qwen 3.6 Max (preview) has the edge for knowledge tasks in this comparison, averaging 73.9 versus 72.5. MAI-Thinking-1 stays close enough that the answer can still flip depending on your workload.

Which is better for coding, MAI-Thinking-1 or Qwen 3.6 Max (preview)?

MAI-Thinking-1 has the edge for coding in this comparison, averaging 65.5 versus 51. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for math, MAI-Thinking-1 or Qwen 3.6 Max (preview)?

MAI-Thinking-1 has the edge for math in this comparison, averaging 89.7 versus 18.4. Qwen 3.6 Max (preview) stays close enough that the answer can still flip depending on your workload.

Which is better for agentic tasks, MAI-Thinking-1 or Qwen 3.6 Max (preview)?

Qwen 3.6 Max (preview) has the edge for agentic tasks in this comparison, averaging 65.4 versus 46. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

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.