MiniMax M2.7 vs Qwen3.6 Plus

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

Agentic
Coding
Multimodal & Grounded
Reasoning
Knowledge
Instruction Following
Multilingual
Mathematics

MiniMax M2.7· Qwen3.6 Plus

Quick Verdict

Pick Qwen3.6 Plus if you want the stronger benchmark profile. MiniMax M2.7 only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.

Qwen3.6 Plus has the cleaner overall profile here, landing at 69 versus 66. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Qwen3.6 Plus's sharpest advantage is in coding, where it averages 64.9 against 56.2. The single biggest benchmark swing on the page is Claw-Eval, 51.9% to 58.7%.

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 Plus. That is roughly Infinityx on output cost alone. Qwen3.6 Plus 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 Plus gives you the larger context window at 1M, compared with 200K for MiniMax M2.7.

Operational tradeoffs

Price$0.30 / $1.20Free*
Speed45 t/sN/A
TTFT2.53sN/A
Context200K1M

Decision framing

BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.

Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.

BenchmarkMiniMax M2.7Qwen3.6 Plus
AgenticQwen3.6 Plus wins
Terminal-Bench 2.057%61.6%
Tau2-Airline80.0%
Tau2-Telecom84.8%
PinchBench89.8%
BFCL v470.6%
Toolathlon46.3%39.8%
MLE-Bench Lite66.6%
MM-ClawBench62.7%
Claw-Eval51.9%58.7%
QwenClawBench57.2%
QwenWebBench1502
TAU3-Bench70.7%
VITA-Bench44.3%
DeepPlanning41.5%
MCP Atlas48.2%
MCP-Tasks74.1%
WideResearch74.3%
OSWorld-Verified62.5%
CodingQwen3.6 Plus wins
SWE-bench Verified*75.4%
SWE-bench Pro56.2%56.6%
SWE Multilingual76.5%73.8%
Multi-SWE Bench52.7%
VIBE-Pro55.6%
NL2Repo39.8%37.9%
SWE-bench Verified78.8%
LiveCodeBench v687.1%
Multimodal & Grounded
GDPval-AA1495
MMMU86.0%
MMMU-Pro78.8%
RealWorldQA85.4%
OmniDocBench 1.591.2%
Video-MME (with subtitle)87.8%
Video-MME (w/o subtitle)84.2%
MathVision88.0%
We-Math89.0%
DynaMath88.0%
MStar83.3%
SimpleVQA67.3%
ChatCVQA81.5%
MMLongBench-Doc62.0%
CC-OCR83.4%
AI2D_TEST94.4%
CountBench97.6%
RefCOCO (avg)93.5%
ODINW1351.8%
ERQA65.7%
VideoMMMU84.0%
MLVU (M-Avg)86.7%
ScreenSpot Pro68.2%
Reasoning
AI-Needle68.3%
LongBench v262%
Knowledge
GPQA-D86.2%
MMLU-Pro (Arcee)80.8%
GPQA90.4%
SuperGPQA71.6%
MMLU-Pro88.5%
MMLU-Redux94.5%
C-Eval93.3%
HLE28.8%
Instruction Following
IFBench75.7%74.2%
IFEval94.3%
Multilingual
MMLU-ProX84.7%
NOVA-6357.9%
INCLUDE85.1%
PolyMath77.4%
VWT2k-lite84.3%
MAXIFE88.2%
Mathematics
AIME25 (Arcee)80.0%
AIME2695.3%
HMMT Feb 202596.7%
HMMT Nov 202594.6%
HMMT Feb 202687.8%
MMAnswerBench83.8%
Frequently Asked Questions (3)

Which is better, MiniMax M2.7 or Qwen3.6 Plus?

Qwen3.6 Plus is ahead overall, 69 to 66. The biggest single separator in this matchup is Claw-Eval, where the scores are 51.9% and 58.7%.

Which is better for coding, MiniMax M2.7 or Qwen3.6 Plus?

Qwen3.6 Plus has the edge for coding in this comparison, averaging 64.9 versus 56.2. Inside this category, SWE Multilingual is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, MiniMax M2.7 or Qwen3.6 Plus?

Qwen3.6 Plus has the edge for agentic tasks in this comparison, averaging 62 versus 57. Inside this category, Claw-Eval is the benchmark that creates the most daylight between them.

Last updated: April 2, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.