Model comparison
MiniMax M3 vs Qwen3.7 Plus
Head-to-head evidence from 30 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: MiniMax M3 #15 (Supported); Qwen3.7 Plus #21 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. MiniMax M3 and Qwen3.7 Plus share 30 comparable benchmark results. 4 of 8 categories are comparable. 15 results are unique to MiniMax M3; 39 to Qwen3.7 Plus.
Updated July 23, 2026- Shared results
- 30
- MiniMax M3 only
- 15
- Qwen3.7 Plus only
- 39
- Comparable categories
- 4 / 8
Pick MiniMax M3 if you want the stronger benchmark profile. Qwen3.7 Plus only becomes the better choice if multimodal & grounded is the priority or you want the stronger reasoning-first profile.
Confidence note. This is a partial-evidence comparison with 30 shared benchmark results across 6 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
MiniMax M3 has the cleaner BenchAlign overall profile here, landing at 69.75 versus 67.22. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
MiniMax M3's sharpest advantage is in agentic, where it averages 72.3 against 71.7. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 66% to 70.3%. Qwen3.7 Plus does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
Qwen3.7 Plus is the reasoning model in the pair, while MiniMax M3 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.
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 | MiniMax M3 | Δ | Qwen3.7 Plus |
|---|---|---|---|
| Multimodal | MiniMax M364.9 | Margin→ 16.6 | Qwen3.7 Plus81.5 |
| Math | MiniMax M385.7 | Margin→ 7.2 | Qwen3.7 Plus92.9 |
| Coding | MiniMax M372.2 | Margin→ 3.4 | Qwen3.7 Plus75.6 |
| Agentic | MiniMax M372.3 | Margin← 0.6 | Qwen3.7 Plus71.7 |
| Reasoning | MiniMax M3Not measured | MarginNo overlap | Qwen3.7 Plus91.7 |
| Knowledge | MiniMax M3Not measured | MarginNo overlap | Qwen3.7 Plus60.1 |
| Multilingual | MiniMax M3Not measured | MarginNo overlap | Qwen3.7 Plus85.4 |
| Inst. Following | MiniMax M3Not measured | MarginNo overlap | Qwen3.7 Plus84.5 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 66%B 70.3%Winner: Qwen3.7 PlusΔ 4.3Terminal-Bench 2.0: MiniMax M3 scored 66%; Qwen3.7 Plus scored 70.3%. Qwen3.7 Plus wins this benchmark. - Source ↗
OSWorld-Verified
AgenticA 70.1%B 73.3%Winner: Qwen3.7 PlusΔ 3.2OSWorld-Verified: MiniMax M3 scored 70.1%; Qwen3.7 Plus scored 73.3%. Qwen3.7 Plus wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 80.5%B 77.7%Winner: MiniMax M3Δ 2.8SWE-bench Verified: MiniMax M3 scored 80.5%; Qwen3.7 Plus scored 77.7%. MiniMax M3 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 59%B 57.6%Winner: MiniMax M3Δ 1.4SWE-bench Pro: MiniMax M3 scored 59%; Qwen3.7 Plus scored 57.6%. MiniMax M3 wins this benchmark. - Source ↗
MMMU-Pro
MultimodalA 78.1%B 79%Winner: Qwen3.7 PlusΔ 0.9MMMU-Pro: MiniMax M3 scored 78.1%; Qwen3.7 Plus scored 79%. Qwen3.7 Plus wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | MiniMax M3 | Qwen3.7 Plus | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | MiniMax M3$0.3 input / $1.2 output | Qwen3.7 PlusNot available | A complete price comparison is not available. |
| Generation speedtokens per second | MiniMax M3Not available | Qwen3.7 PlusNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | MiniMax M3Not available | Qwen3.7 PlusNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | MiniMax M31M | Qwen3.7 Plus1M | Listed context windows are equal. |
Benchmark Deep Dive
AgenticMiniMax M3 wins25 benchmarks
| Benchmark | MiniMax M3 | Qwen3.7 Plus | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 66% | 70.3% | Qwen3.7 Plus leads |
| BrowseCompSource | 83.5% | — | Not comparable |
| OSWorld-VerifiedSource | 70.1% | 73.3% | Qwen3.7 Plus leads |
| MCP AtlasSource | 74.2% | 73.2% | MiniMax M3 leads |
| Claw-EvalSource | 74.5% | 62.7% | MiniMax M3 leads |
| AA Agentic IndexSource | 35.4% | 20.8% | MiniMax M3 leads |
| τ²-bench resultsSource | 88.9% | 93% | Qwen3.7 Plus leads |
| GDPval-AASource | 44.7% | 21.8% | MiniMax M3 leads |
| GDPval-AASource | 1395 | 936 | MiniMax M3 leads |
| GDPval rubricsSource | 74.7% | — | Not comparable |
| BankerToolBenchSource | 76.1% | — | Not comparable |
| ResearchClawBenchSource | 19.8% | — | Not comparable |
| OSWorld 2.0Source | 4.6% | 2.8% | MiniMax M3 leads |
| AA BriefcaseSource | 1110 | — | Not comparable |
| AA EnterpriseOps-GymSource | 32.1% | — | Not comparable |
| AA Harvey LABSource | 88.4% | — | Not comparable |
| terminalBenchHardSource | 42.4% | — | Not comparable |
| aaTerminalBench21Source | 65.2% | — | Not comparable |
| QwenClawBenchSource | — | 61.8% | Not comparable |
| QwenWebBenchSource | — | 1536 | Not comparable |
| BFCL v4Source | — | 72.9% | Not comparable |
| VITA-BenchSource | — | 45.6% | Not comparable |
| DeepPlanningSource | — | 62.3% | Not comparable |
| AndroidWorldSource | — | 81.0% | Not comparable |
| APEX-Agents-AASource | — | 22.4% | Not comparable |
CodingQwen3.7 Plus wins12 benchmarks
| Benchmark | MiniMax M3 | Qwen3.7 Plus | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 80.5% | 77.7% | MiniMax M3 leads |
| SWE-bench ProSource | 59% | 57.6% | MiniMax M3 leads |
| Terminal-Bench 2.0Source | 66.0% | 70.3% | Qwen3.7 Plus leads |
| NL2RepoSource | 42.1% | 41.1% | MiniMax M3 leads |
| AA Coding IndexSource | 58.6% | 55.9% | MiniMax M3 leads |
| AA-SciCodeSource | 45.4% | 45.5% | Qwen3.7 Plus leads |
| VIBE V2Source | 50.1% | — | Not comparable |
| SVG-BenchSource | 63.7% | — | Not comparable |
| KernelBench HardSource | 28.8% | — | Not comparable |
| SWE MultilingualSource | — | 75.8% | Not comparable |
| SciCodeSource | — | 51.3% | Not comparable |
| LiveCodeBenchSource | — | 89.6% | Not comparable |
Reasoning3 benchmarks
Knowledge14 benchmarks
| Benchmark | MiniMax M3 | Qwen3.7 Plus | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 44.4% | 39.0% | MiniMax M3 leads |
| AA-GPQA DiamondSource | 92.9% | 90.0% | MiniMax M3 leads |
| AA-HLESource | 37.1% | 33.4% | MiniMax M3 leads |
| AA-Omniscience IndexSource | 1.4% | 2.4% | Qwen3.7 Plus leads |
| AA-Omniscience AccuracySource | 15.0% | 22.2% | Qwen3.7 Plus leads |
| AA-Omniscience Hallucination RateSource | 16.1% | 25.5% | MiniMax M3 leads |
| AA Openness IndexSource | 33.3% | — | Not comparable |
| GPQASource | — | 90.3% | Not comparable |
| GPQA-DSource | — | 90.3% | Not comparable |
| HLESource | — | 34.7% | Not comparable |
| MMLU-ProSource | — | 88.5% | Not comparable |
| MMLU-ReduxSource | — | 94.5% | Not comparable |
| SuperGPQASource | — | 71.4% | Not comparable |
| MMMLUSource | — | 89.0% | Not comparable |
MathQwen3.7 Plus wins4 benchmarks
Multilingual5 benchmarks
MultimodalQwen3.7 Plus wins18 benchmarks
| Benchmark | MiniMax M3 | Qwen3.7 Plus | Result |
|---|---|---|---|
| OfficeQA ProSource | 45.1% | — | Not comparable |
| OmniDocBench 1.5Source | 91.6% | 91.4% | MiniMax M3 leads |
| MMMU-ProSource | 78.1% | 79% | Qwen3.7 Plus leads |
| VideoMMMUSource | 84.6% | 85.4% | Qwen3.7 Plus leads |
| Video-MME (with subtitle)Source | 85.4% | 88.0% | Qwen3.7 Plus leads |
| Design Arena WebsiteSource | 1289 | 1288 | MiniMax M3 leads |
| AA-MMMU-ProSource | 78.6% | 80.5% | Qwen3.7 Plus leads |
| MathVisionSource | — | 90.3% | Not comparable |
| CharXivSource | — | 85.9% | Not comparable |
| ERQASource | — | 69.8% | Not comparable |
| MedXpertQA (MM)Source | — | 71.0% | Not comparable |
| ScreenSpot ProSource | — | 79.0% | Not comparable |
| SimpleVQASource | — | 81.7% | Not comparable |
| MMSearch-PlusSource | — | 41.4% | Not comparable |
| RealWorldQASource | — | 86.9% | Not comparable |
| OCRBench V2Source | — | 70.7% | Not comparable |
| ODINW13Source | — | 51.1% | Not comparable |
| MLVU (M-Avg)Source | — | 87.4% | Not comparable |
Frequently Asked Questions (5)
Which is better, MiniMax M3 or Qwen3.7 Plus?
MiniMax M3 is ahead on BenchLM's BenchAlign leaderboard, 69.75 to 67.22. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 66% and 70.3%.
Which is better for coding, MiniMax M3 or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for coding in this comparison, averaging 75.6 versus 72.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for math, MiniMax M3 or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for math in this comparison, averaging 92.9 versus 85.7. MiniMax M3 stays close enough that the answer can still flip depending on your workload.
Which is better for agentic tasks, MiniMax M3 or Qwen3.7 Plus?
MiniMax M3 has the edge for agentic tasks in this comparison, averaging 72.3 versus 71.7. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, MiniMax M3 or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for multimodal and grounded tasks in this comparison, averaging 81.5 versus 64.9. Inside this category, Video-MME (with subtitle) is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
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.