Noometry

Model comparison

MiniMax-M2 vs Qwen2.5-VL 72B Instruct

MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.9 on the Noometry Index.

Last verified . 1 shared benchmarks.

MiniMax-M2 MiniMax

37.4

Rank #204 Confirmed

Qwen2.5-VL 72B Instruct Alibaba (Qwen)

29.9

Rank #302 Confirmed

Summary

  • They share 1 benchmark with published results for both. MiniMax-M2 scores higher in 1 category and Qwen2.5-VL 72B Instruct in 1 category; 2 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where MiniMax-M2 leads 25.1 to 18.6.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 57.8% for MiniMax-M2 and 36% for Qwen2.5-VL 72B Instruct.
  • MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
  • MiniMax-M2 accepts more context: 205K tokens versus 131K.

Side by side

MiniMax-M2Qwen2.5-VL 72B Instruct
ProviderMiniMaxAlibaba (Qwen)
Noometry Index37.429.9
Released2025-10-272024-09
WeightsOpenOpen
Context window205K131K
Max output131K8K
Input $ / M tokens$0.30$2.80
Output $ / M tokens$1.20$8.40
Results tracked216

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

MiniMax-M2: 39.3 (#159), Qwen2.5-VL 72B Instruct: —

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
SWE-bench Verified (bash only)61%—
LMArena WebDev1297—
LMArena Coding1370—

Agentic & Tool Use MiniMax-M2 leads

MiniMax-M2: 25.1 (#109), Qwen2.5-VL 72B Instruct: 18.6 (#144)

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
Terminal-Bench30%—
OSWorld—5%
Vending-Bench 2160.6—

Reasoning Qwen2.5-VL 72B Instruct leads

MiniMax-M2: 19.4 (#258), Qwen2.5-VL 72B Instruct: 20.7 (#233)

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
Kagi LLM Benchmark57.8%36%
NYT Connections (extended)14.8%—
LMArena Hard Prompts1357—

Math Not comparable

MiniMax-M2: 37.3 (#160), Qwen2.5-VL 72B Instruct: —

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
LMArena Math1352—

Knowledge Not comparable

MiniMax-M2: 37.0 (#163), Qwen2.5-VL 72B Instruct: —

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
LMArena Expert1337—

Multimodal Not comparable

MiniMax-M2: —, Qwen2.5-VL 72B Instruct: 33.5 (#97)

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
LMArena Vision—1107
Video-MME—73.5%
GeoBench—62%
SpatialViz-Bench—33.3%

Multilingual Not comparable

MiniMax-M2: 45.3 (#171), Qwen2.5-VL 72B Instruct: —

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
LMArena Non-English1313—
LMArena Chinese1366—
LMArena French1335—
LMArena German1355—
LMArena Russian1331—
LMArena Spanish1326—

Instruction Following Not comparable

MiniMax-M2: 70.2 (#166), Qwen2.5-VL 72B Instruct: —

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
LMArena Instruction Following1328—

Long Context Not comparable

MiniMax-M2: 40.5 (#153), Qwen2.5-VL 72B Instruct: —

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
LMArena Longer Query1331—

Writing & Preference Not comparable

MiniMax-M2: 53.0 (#162), Qwen2.5-VL 72B Instruct: —

BenchmarkMiniMax-M2Qwen2.5-VL 72B Instruct
LMArena Text1340—
LMArena Creative Writing1286—
LMArena Multi-Turn1361—

Frequently asked questions

Is MiniMax-M2 better than Qwen2.5-VL 72B Instruct?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.9 on the Noometry Index.

Which is cheaper, MiniMax-M2 or Qwen2.5-VL 72B Instruct?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.

Which has the bigger context window?

MiniMax-M2 does, with 205K tokens against 131K.

How many benchmarks do MiniMax-M2 and Qwen2.5-VL 72B Instruct share?

1 benchmark has published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.

Related comparisons

Go deeper