GLM 5.1vsMiniMax-M2.7
Across 8 shared benchmarks, GLM 5.1 leads overall: GLM 5.1 wins 6, MiniMax-M2.7 wins 2, with 0 ties and an average score difference of +1.64.
GLM 5.1
智谱AI · 2026-03-27 · Reasoning model
MiniMax-M2.7
MiniMaxAI · 2026-03-18 · Reasoning model
GLM 5.16 wins(75%)(25%)2 winsMiniMax-M2.7
Benchmark scores
Grouped by capability, sorted by largest gap within each. 8 shared benchmarks.
AI Agent - Tool Usage
GLM 5.1 2/2| Benchmark | GLM 5.1 | MiniMax-M2.7 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 63.5013 / 48Thinking (With Tools) | 5725 / 48Thinking (With Tools) | +6.50 |
| Terminal-Bench 2.1 | 61.80105 / 192Thinking (With Tools) | 55.40121 / 192Thinking (With Tools) | +6.40 |
Coding and Software Engineer
Even 2/2| Benchmark | GLM 5.1 | MiniMax-M2.7 | Diff |
|---|---|---|---|
| SciCode | 44.8090 / 130Thinking (No Tools) | 50.1068 / 130Thinking (No Tools) | -5.30 |
| SWE-Bench Pro - Public | 58.4020 / 62Thinking (With Tools) | 56.2029 / 62Thinking (With Tools) | +2.20 |
Agent Level Benchmark
GLM 5.1 1/1| Benchmark | GLM 5.1 | MiniMax-M2.7 | Diff |
|---|---|---|---|
| τ³-Banking | 13.60115 / 164Thinking (With Tools) | 9.90129 / 164Thinking (With Tools) | +3.70 |
Claw-style Agent Evaluation
MiniMax-M2.7 1/1| Benchmark | GLM 5.1 | MiniMax-M2.7 | Diff |
|---|---|---|---|
| PinchBench v2 | 59.9533 / 45Reported best (effort unspecified) | 66.7530 / 45Reported best (effort unspecified) | -6.80 |
General Knowledge
GLM 5.1 1/1| Benchmark | GLM 5.1 | MiniMax-M2.7 | Diff |
|---|---|---|---|
| CritPt | 4.60102 / 200Thinking (No Tools) | 0.60168 / 200Thinking (No Tools) | +4 |
Multimodal Understanding
GLM 5.1 1/1| Benchmark | GLM 5.1 | MiniMax-M2.7 | Diff |
|---|---|---|---|
| GDP.pdf | 8.4086 / 118Thinking (No Tools) | 691 / 118Thinking (No Tools) | +2.40 |
Specs
| Field | GLM 5.1 | MiniMax-M2.7 |
|---|---|---|
| Publisher | 智谱AI | MiniMaxAI |
| Release date | 2026-03-27 | 2026-03-18 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | MoE |
| Parameters | 754B | 229B |
| Context length | 200K | 200K |
| Max output | 125K | 200K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GLM 5.1 | MiniMax-M2.7 |
|---|---|---|
| Text input | $1.4 / 1M tokens | $0.3 / 1M tokens |
| Text output | $4.4 / 1M tokens | $1.2 / 1M tokens |
| Cache read | $4.4 / 1M tokens | $0.06 / 1M tokens |
| Cache write | $0.26 / 1M tokens | $0.375 / 1M tokens |
Summary
- GLM 5.1leads in:AI Agent - Tool Usage (2/2), Agent Level Benchmark (1/1), General Knowledge (1/1), Multimodal Understanding (1/1)
- MiniMax-M2.7leads in:Claw-style Agent Evaluation (1/1)
- Tied in:Coding and Software Engineer
On average across the 8 shared benchmarks, GLM 5.1 scores 1.64 higher.
Largest single-benchmark gap: PinchBench v2 — GLM 5.1 59.95 vs MiniMax-M2.7 66.75 (-6.80).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.