MiniMax-M2.7 Benchmark Details
MiniMax-M2.7 currently shows benchmark results led by Claw Bench (5 / 29, score 91.70), Pinch Bench (10 / 38, score 87.10), IF Bench (9 / 34, score 76). This page also compares it with 2 competitor models and 2 predecessor or same-series models, including performance and pricing views when available. 2 source links are attached for reference.
Benchmark Results
Benchmark Results
Coding and Software Engineer
3 evaluationsAgent Level Benchmark
2 evaluationsProductivity Knowledge
2 evaluationsClaw-style Agent Evaluation
2 evaluationsCompetitor Comparison
Benchmark scores for MiniMax-M2.7 compared against top models in its class
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | MiniMax-M2.7Current | Kimi K2.5 | GLM-5 |
|---|---|---|---|
HLE 综合评估 | 28.00Thinking Enabled | 50.20Thinking Enabled ｜ Tools | 50.40Thinking Enabled ｜ Tools |
LiveBench 综合评估 | 63.49Deep Thinking Mode | 69.07Thinking Enabled | 68.85Standard Mode |
GPQA Diamond 科学与综合推理 | 87.00Thinking Enabled | 87.60Thinking Enabled | 86.00Thinking Enabled |
SWE-bench Multilingual 编程与软件工程 | 76.50Thinking Enabled ｜ Tools | 73.00Thinking Enabled | -- |
SWE-Bench Pro - Public 编程与软件工程 | 56.20Thinking Enabled ｜ Tools | 50.70Thinking Enabled ｜ Tools | -- |
Terminal Bench Hard Agent能力评测 | 39.00Thinking Enabled ｜ Tools | -- | 43.00Thinking Enabled ｜ Tools |
τ²-Bench - Telecom Agent能力评测 | 85.00Thinking Enabled ｜ Tools | -- | 98.00Thinking Enabled ｜ Tools |
IF Bench 指令跟随 | 76.00Thinking Enabled ｜ Tools | -- | 72.00Thinking Enabled ｜ Tools |
Terminal Bench 2.0 AI Agent - 工具使用 | 57.00Thinking Enabled ｜ Tools | 50.80Thinking Enabled ｜ Tools | 61.10Thinking Enabled ｜ Tools |
Context Arena 文本向量检索 | 33.29Thinking Enabled | 59.22Thinking Enabled | -- |
GDPval-AA 生产力知识 | 50.00Thinking Enabled | 40.00Thinking Enabled | 46.00Thinking Enabled |
AA-LCR 长上下文能力 | 69.00Thinking Enabled ｜ Tools | 65.00Thinking Enabled | 63.00Thinking Enabled |
Standard API Pricing: MiniMax-M2.7 vs. Peer Models
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
MiniMax-M2.7 | MiniMaxAI | $0.3 / 1M tokens | $1.2 / 1M tokens | — |
Kimi K2.5 | Moonshot AI | $0.6 / 1M tokens | $3 / 1M tokens | — |
GLM-5 | 智谱AI | $1 / 1M tokens | $3.2 / 1M tokens | — |
Version History
How each version of the MiniMax-M2.7 series stacks up on benchmark tests
11 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.
| Benchmark | MiniMax-M2.7Current | MiniMax M2.5 | M2.1 |
|---|---|---|---|
HLE 综合评估 | 28.00Thinking Enabled | 19.40Thinking Enabled | 22.00Thinking Enabled |
LiveBench 综合评估 | 63.49Deep Thinking Mode | 60.14Deep Thinking Mode | -- |
GPQA Diamond 科学与综合推理 | 87.00Thinking Enabled | 85.20Thinking Enabled | 81.00Thinking Enabled |
SWE-Bench Pro - Public 编程与软件工程 | 56.20Thinking Enabled ｜ Tools | 55.40Thinking Enabled ｜ Tools | 32.60Thinking Enabled ｜ Tools |
τ²-Bench - Telecom Agent能力评测 | 85.00Thinking Enabled ｜ Tools | 97.80Thinking Enabled ｜ Tools | 87.00Thinking Enabled ｜ Tools |
IF Bench 指令跟随 | 76.00Thinking Enabled ｜ Tools | 70.00Thinking Enabled ｜ Tools | 70.00Thinking Enabled ｜ Tools |
Terminal Bench 2.0 AI Agent - 工具使用 | 57.00Thinking Enabled ｜ Tools | 51.70Thinking Enabled ｜ Tools | 47.90Thinking Enabled ｜ Tools |
GDPval-AA 生产力知识 | 50.00Thinking Enabled | 36.00Thinking Enabled | -- |
AA-LCR 长上下文能力 | 69.00Thinking Enabled ｜ Tools | 69.50Thinking Enabled | -- |
Claw Bench OpenClaw智能体能力综合测评 | 91.70Thinking Enabled ｜ Tools | 92.10Thinking Enabled ｜ Tools | -- |
Pinch Bench OpenClaw智能体能力综合测评 | 87.10Thinking Enabled ｜ Tools | 87.80Thinking Enabled ｜ Tools | 84.30Thinking Enabled ｜ Tools |
Single-Benchmark Version Trend
Viewing: HLE · 综合评估
Standard API Pricing Across the MiniMax-M2.7 Series
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier.
These models use different currencies or billing units, so the page falls back to raw price values instead of a shared bar chart.
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
MiniMax-M2.7 | MiniMaxAI | $0.3 / 1M tokens | $1.2 / 1M tokens | — |
MiniMax M2.5 | MiniMaxAI | $0.3 / 1M tokens | $2.4 / 1M tokens | — |
M2.1 | MiniMaxAI | ¥2.1 / 1M tokens | ¥8.4 / 1M tokens | — |