See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。

MiniMax M2.5
MiniMaxAI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: AI Agent - 信息收集 +7.3 / Relative gap: 指令跟随 -2.0
Relative edge: 指令跟随 +2.0 / Relative gap: AI Agent - 信息收集 -7.3
Method: for each model and benchmark, the chart first averages all scores in the current mode scope instead of taking the best score, then averages those benchmark scores within each category. Only benchmarks with at least two selected models scored are included; missing values are not counted as zero.
Best overall
GLM-5 · 65.99
Best single
GLM-5 · τ²-Bench - Telecom 98.00
Modality coverage
GLM-5 · 1 modalities
Head to head
13
Benchmarks
6
Wins
6
Losses
-1.79
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
13 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | MiniMax M2.5 | GLM-5 |
|---|---|---|
ARC-AGI 综合评估 | 63.70Thinking Enabled | 44.70Thinking Enabled |
ARC-AGI-2 综合评估 | 4.90Thinking Enabled | 4.90Thinking Enabled |
GPQA Diamond 综合评估 | 85.20Thinking Enabled | 86.00Thinking Enabled |
HLE 综合评估 | 19.40Thinking Enabled | 50.40Thinking Enabled | Tools |
SWE-bench Verified 编程与软件工程 | 80.20Thinking Enabled | Tools | 77.80Thinking Enabled |
τ²-Bench - Telecom Agent能力评测 | 97.80Thinking Enabled | Tools | 98.00Thinking Enabled | Tools |
IF Bench 指令跟随 | 70.00Thinking Enabled | Tools | 72.00Thinking Enabled | Tools |
BrowseComp AI Agent - 信息收集 | 76.30Thinking Enabled | Tools | 75.90Thinking Enabled | Tools |
Terminal Bench 2.0 AI Agent - 工具使用 | 51.70Thinking Enabled | Tools | 61.10Thinking Enabled | Tools |
GDPval-AA 生产力知识 | 36.00Thinking Enabled | 46.00Thinking Enabled |
AA-LCR 长上下文能力 | 69.50Thinking Enabled | 63.00Thinking Enabled |
Claw Bench OpenClaw智能体能力综合测评 | 92.10Thinking Enabled | Tools | 91.70Thinking Enabled | Tools |
Pinch Bench OpenClaw智能体能力综合测评 | 87.80Thinking Enabled | Tools | 86.40Thinking Enabled | Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | MiniMax M2.5MiniMaxAI | GLM-5智谱AI |
|---|---|---|
Core specsRelease | 2026-02-12 | 2026-02-11 |
Context length | 128K | 200K |
Parameters | 2290 | 7440 |
Active parameters | 100 | 400 |
Max output | Not provided | 131072 |
MoE | Yes | Yes |
LicenseCode Open Source | Closed Source | Not provided |
Weights Open Source | Not provided | Closed Source |
Commercial use | 免费商用授权 | 免费商用授权 |
Modality supportText Input/Output | Not provided | / |
ResourcesPaper / report | MiniMax M2.5: Built for Real-World Productivity. | GLM-5: From Vibe Coding to Agentic Engineering |

GLM-5
智谱AI