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。
GLM-5
智谱AI
MiniMax-M2.7
MiniMaxAI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: Agent能力评测 +8.5 / Relative gap: 长上下文能力 -6.0
Relative edge: 长上下文能力 +6.0 / Relative gap: Agent能力评测 -8.5
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 · 70.53
Best single
GLM-5 · τ²-Bench - Telecom 98.00
Modality coverage
GLM-5 · 1 modalities
Head to head
10
Benchmarks
4
Wins
5
Losses
+2.91
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.
10 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GLM-5 | MiniMax-M2.7 |
|---|---|---|
GPQA Diamond 综合评估 | 86.00Thinking Enabled | 87.00Thinking Enabled |
HLE 综合评估 | 50.40Thinking Enabled ｜ Tools | 28.00Thinking Enabled |
LiveBench 综合评估 | 68.85Standard Mode | 63.49Deep Thinking Mode |
Terminal Bench Hard Agent能力评测 | 43.00Thinking Enabled ｜ Tools | 39.00Thinking Enabled ｜ Tools |
τ²-Bench - Telecom Agent能力评测 | 98.00Thinking Enabled ｜ Tools | 85.00Thinking Enabled ｜ Tools |
IF Bench 指令跟随 | 72.00Thinking Enabled ｜ Tools | 76.00Thinking Enabled ｜ Tools |
GDPval-AA 生产力知识 | 46.00Thinking Enabled | 50.00Thinking Enabled |
AA-LCR 长上下文能力 | 63.00Thinking Enabled | 69.00Thinking Enabled ｜ Tools |
Claw Bench OpenClaw智能体能力综合测评 | 91.70Thinking Enabled ｜ Tools | 91.70Thinking Enabled ｜ Tools |
Pinch Bench OpenClaw智能体能力综合测评 | 86.40Thinking Enabled ｜ Tools | 87.10Thinking Enabled ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | GLM-5智谱AI | MiniMax-M2.7MiniMaxAI |
|---|---|---|
Core specsRelease | 2026-02-11 | 2026-03-18 |
Context length | 200K | 200K |
Parameters | 7440 | 2290 |
Active parameters | 400 | 100 |
Max output | 131072 | 204800 |
MoE | Yes | Yes |
LicenseCode Open Source | Not provided | Not provided |
Weights Open Source | Closed Source | Not provided |
Commercial use | 免费商用授权 | 不可以商用 |
Modality supportText Input/Output | / | / |
ResourcesPaper / report | GLM-5: From Vibe Coding to Agentic Engineering | MiniMax M2.7: Early Echoes of Self-Evolution |
DataLearner blog | Not provided | MiniMax M2.7 发布：模型开始帮自己训练自己 |
