Qwen 3.6 Plus PreviewvsMiniMax-M2.7
Across 8 shared benchmarks, Qwen 3.6 Plus Preview leads overall: Qwen 3.6 Plus Preview wins 8, MiniMax-M2.7 wins 0, with 0 ties and an average score difference of +6.32.
Qwen 3.6 Plus Preview
阿里巴巴 · 2026-03-31 · Chat model
MiniMax-M2.7
MiniMaxAI · 2026-03-18 · Reasoning model
Qwen 3.6 Plus Preview8 wins(100%)(0%)0 winsMiniMax-M2.7
Benchmark scores
Grouped by capability, sorted by largest gap within each. 8 shared benchmarks.
Agent Level Benchmark
Qwen 3.6 Plus Preview 3/3| Benchmark | Qwen 3.6 Plus Preview | MiniMax-M2.7 | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 97.7013 / 264Thinking (With Tools) | 8589 / 264Thinking (With Tools) | +12.70 |
| τ³-Banking | 20.8088 / 164Thinking (With Tools) | 9.90129 / 164Thinking (With Tools) | +10.90 |
| Terminal Bench Hard | 43.9037 / 244Thinking (With Tools) | 3955 / 244Thinking (With Tools) | +4.90 |
AI Agent - Tool Usage
Qwen 3.6 Plus Preview 2/2| Benchmark | Qwen 3.6 Plus Preview | MiniMax-M2.7 | Diff |
|---|---|---|---|
| Terminal-Bench 2.1 | 61.40107 / 192Thinking (With Tools) | 55.40121 / 192Thinking (With Tools) | +6 |
| Terminal Bench 2.0 | 61.6016 / 48Thinking (With Tools) | 5725 / 48Thinking (With Tools) | +4.60 |
Claw-style Agent Evaluation
Qwen 3.6 Plus Preview 1/1| Benchmark | Qwen 3.6 Plus Preview | MiniMax-M2.7 | Diff |
|---|---|---|---|
| PinchBench v2 | 72.5023 / 45Reported best (effort unspecified) | 66.7530 / 45Reported best (effort unspecified) | +5.75 |
General Evaluation
Qwen 3.6 Plus Preview 1/1| Benchmark | Qwen 3.6 Plus Preview | MiniMax-M2.7 | Diff |
|---|---|---|---|
| GPQA Diamond | 90.4076 / 462Thinking (No Tools) | 87133 / 462Thinking (No Tools) | +3.40 |
General Knowledge
Qwen 3.6 Plus Preview 1/1| Benchmark | Qwen 3.6 Plus Preview | MiniMax-M2.7 | Diff |
|---|---|---|---|
| CritPt | 2.90115 / 200Thinking (No Tools) | 0.60168 / 200Thinking (No Tools) | +2.30 |
Specs
| Field | Qwen 3.6 Plus Preview | MiniMax-M2.7 |
|---|---|---|
| Publisher | 阿里巴巴 | MiniMaxAI |
| Release date | 2026-03-31 | 2026-03-18 |
| Model type | Chat model | Reasoning model |
| Architecture | Dense | MoE |
| Parameters | Not available | 229B |
| Context length | 1M | 200K |
| Max output | 64K | 200K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Qwen 3.6 Plus Preview | MiniMax-M2.7 |
|---|---|---|
| Text input | $0.5 / 1M tokens | $0.3 / 1M tokens |
| Text output | $3 / 1M tokens | $1.2 / 1M tokens |
| Cache read | $0.05 / 1M tokens | $0.06 / 1M tokens |
| Cache write | $0.625 / 1M tokens | $0.375 / 1M tokens |
Summary
- Qwen 3.6 Plus Previewleads in:Agent Level Benchmark (3/3), AI Agent - Tool Usage (2/2), Claw-style Agent Evaluation (1/1), General Evaluation (1/1), General Knowledge (1/1)
On average across the 8 shared benchmarks, Qwen 3.6 Plus Preview scores 6.32 higher.
Largest single-benchmark gap: τ²-Bench - Telecom — Qwen 3.6 Plus Preview 97.70 vs MiniMax-M2.7 85 (+12.70).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.