Skip to main content

Model comparison

MiniMax M2.7 vs Qwen3.6-27B

Data verified

Head-to-head evidence from 21 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

64.11/100
Margin
10.3pts
← winning
53.82/100
0 category wins2 category wins

Public leaderboard positions: MiniMax M2.7 #36 (Supported); Qwen3.6-27B #93 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M2.7 and Qwen3.6-27B share 21 comparable benchmark results. 2 of 8 categories are comparable. 14 results are unique to MiniMax M2.7; 33 to Qwen3.6-27B.

Updated July 21, 2026
Shared results
21
MiniMax M2.7 only
14
Qwen3.6-27B only
33
Comparable categories
2 / 8

Pick MiniMax M2.7 if you want the stronger benchmark profile. Qwen3.6-27B only becomes the better choice if coding is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 21 shared benchmark results across 5 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

MiniMax M2.7 is clearly ahead on the BenchAlign aggregate, 64.11 to 53.82. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

MiniMax M2.7 is also the more expensive model on tokens at $0.30 input / $1.20 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.6-27B. That is roughly Infinityx on output cost alone. Qwen3.6-27B is the reasoning model in the pair, while MiniMax M2.7 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Qwen3.6-27B gives you the larger context window at 262K, compared with 200K for MiniMax M2.7.

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 MiniMax M2.7 and Qwen3.6-27B
CategoryMiniMax M2.7ΔQwen3.6-27B
CodingMiniMax M2.753.3Margin 24.2Qwen3.6-27B77.5
AgenticMiniMax M2.757.0Margin 2.3Qwen3.6-27B59.3
KnowledgeMiniMax M2.7Not measuredMarginNo overlapQwen3.6-27B53.3
MathMiniMax M2.7Not measuredMarginNo overlapQwen3.6-27B89.2
MultimodalMiniMax M2.7Not measuredMarginNo overlapQwen3.6-27B76.7

Decisive benchmark drivers

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

More
A · MiniMax M2.7B · Qwen3.6-27B
  1. SWE-bench Pro

    Coding
    Source ↗
    A 56.2%B 53.5%
    Winner: MiniMax M2.7Δ 2.7
    SWE-bench Pro: MiniMax M2.7 scored 56.2%; Qwen3.6-27B scored 53.5%. MiniMax M2.7 wins this benchmark.
  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 57%B 59.3%
    Winner: Qwen3.6-27BΔ 2.3
    Terminal-Bench 2.0: MiniMax M2.7 scored 57%; Qwen3.6-27B scored 59.3%. Qwen3.6-27B wins this benchmark.

Operational comparison

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

MetricMiniMax M2.7Qwen3.6-27BComparison
Input / output priceUSD per 1M tokensMiniMax M2.7$0.3 input / $1.2 outputQwen3.6-27B$0 input / $0 outputQwen3.6-27B has the lower combined listed price.
Generation speedtokens per secondMiniMax M2.745 tok/sQwen3.6-27BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M2.72.53 sQwen3.6-27BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M2.7200KQwen3.6-27B262KQwen3.6-27B lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.6-27B wins
BenchmarkMiniMax M2.7Qwen3.6-27BResult
Terminal-Bench 2.0Source 57%59.3%Qwen3.6-27B leads
τ²-bench resultsSource 84.8%94.2%Qwen3.6-27B leads
ToolathlonSource 46.3%Not comparable
MLE-Bench LiteSource 66.6%Not comparable
MM-ClawBenchSource 62.7%Not comparable
Claw-EvalSource 48.7%72.4%Qwen3.6-27B leads
AA Agentic IndexSource 25.6%27.0%Qwen3.6-27B leads
APEX-Agents-AASource 10.6%Not comparable
GDPval-AASource 32.9%32.0%MiniMax M2.7 leads
GDPval-AASource 11581140MiniMax M2.7 leads
Gert LabsSource 40.40%54.84%Qwen3.6-27B leads
QwenClawBenchSource 53.4%Not comparable
QwenWebBenchSource 1487Not comparable
AndroidWorldSource 70.3%Not comparable
CodingQwen3.6-27B wins
BenchmarkMiniMax M2.7Qwen3.6-27BResult
SWE-bench Verified*Source 75.4%Not comparable
SWE-bench ProSource 56.2%53.5%MiniMax M2.7 leads
SWE-RebenchSource 51.9%Not comparable
SWE MultilingualSource 76.5%71.3%MiniMax M2.7 leads
Multi-SWE BenchSource 52.7%Not comparable
VIBE-ProSource 55.6%Not comparable
NL2RepoSource 39.8%36.2%MiniMax M2.7 leads
Vibe Code BenchSource 27.04%Not comparable
React Native EvalsSource 71.4%Not comparable
AA Coding IndexSource 52.6%53.7%Qwen3.6-27B leads
AA-SciCodeSource 47.0%39.8%MiniMax M2.7 leads
SWE-bench VerifiedSource 77.2%Not comparable
Terminal-Bench 2.0Source 59.3%Not comparable
LiveCodeBenchSource 83.9%Not comparable
Reasoning
BenchmarkMiniMax M2.7Qwen3.6-27BResult
AA-LCRSource 68.7%68.7%Tie
CritPtSource 0.6%1.1%Qwen3.6-27B leads
Knowledge
BenchmarkMiniMax M2.7Qwen3.6-27BResult
GPQA-DSource 87.0%Not comparable
MMLU-Pro (Arcee)Source 80.8%Not comparable
Artificial Analysis Intelligence IndexSource 38.1%37.0%MiniMax M2.7 leads
AA-GPQA DiamondSource 87.4%84.2%MiniMax M2.7 leads
AA-HLESource 28.1%21.6%MiniMax M2.7 leads
AA-Omniscience IndexSource 0.7%-19.8%MiniMax M2.7 leads
AA-Omniscience AccuracySource 26.1%19.2%MiniMax M2.7 leads
AA-Omniscience Hallucination RateSource 34.4%48.3%MiniMax M2.7 leads
MMLU-ProSource 86.2%Not comparable
MMLU-ReduxSource 93.5%Not comparable
SuperGPQASource 66%Not comparable
C-EvalSource 91.4%Not comparable
GPQASource 87.8%Not comparable
HLESource 24%Not comparable
Math
BenchmarkMiniMax M2.7Qwen3.6-27BResult
AIME25 (Arcee)Source 80.0%Not comparable
HMMT Feb 2025Source 93.8%Not comparable
HMMT Nov 2025Source 90.7%Not comparable
HMMT Feb 2026Source 84.3%Not comparable
MMAnswerBenchSource 80.8%Not comparable
AIME26Source 94.1%Not comparable
Multimodal
BenchmarkMiniMax M2.7Qwen3.6-27BResult
Design Arena WebsiteSource 1275Not comparable
MMMUSource 82.9%Not comparable
MMMU-ProSource 75.8%Not comparable
RealWorldQASource 84.1%Not comparable
DynaMathSource 85.6%Not comparable
MStarSource 81.4%Not comparable
SimpleVQASource 56.1%Not comparable
CharXivSource 78.4%Not comparable
CC-OCRSource 81.2%Not comparable
CountBenchSource 97.8%Not comparable
RefCOCO (avg)Source 92.5%Not comparable
ERQASource 62.5%Not comparable
Video-MME (with subtitle)Source 87.7%Not comparable
VideoMMMUSource 84.4%Not comparable
MLVU (M-Avg)Source 86.6%Not comparable
V*Source 94.7%Not comparable
AA-MMMU-ProSource 74.6%Not comparable
Inst. Following
BenchmarkMiniMax M2.7Qwen3.6-27BResult
AA-IFBenchSource 75.7%67.6%MiniMax M2.7 leads
Frequently Asked Questions (3)

Which is better, MiniMax M2.7 or Qwen3.6-27B?

MiniMax M2.7 is ahead on BenchLM's BenchAlign leaderboard, 64.11 to 53.82. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 56.2% and 53.5%.

Which is better for coding, MiniMax M2.7 or Qwen3.6-27B?

Qwen3.6-27B has the edge for coding in this comparison, averaging 77.5 versus 53.3. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, MiniMax M2.7 or Qwen3.6-27B?

Qwen3.6-27B has the edge for agentic tasks in this comparison, averaging 59.3 versus 57. Inside this category, Claw-Eval 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.

MiniMax M2.7
API / mo$1,125
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Qwen3.6-27B
API / mo$0
Self-host / mo$429
Break-even
Model the full break-even

Related Comparisons

Last updated: July 21, 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.