MiniMax M2.5vsGLM-5
MiniMax M2.5 and GLM-5 are tied across 13 shared benchmarks: MiniMax M2.5 leads on 6, GLM-5 leads on 6, with 1 ties and an average score difference of -1.79.
MiniMax M2.5
MiniMaxAI · 2026-02-12 · Reasoning model
MiniMax M2.5 and GLM-5 are tied across 13 shared benchmarks: MiniMax M2.5 leads on 6, GLM-5 leads on 6, with 1 ties and an average score difference of -1.79.
MiniMaxAI · 2026-02-12 · Reasoning model
智谱AI · 2026-02-11 · AI model
Grouped by capability, sorted by largest gap within each. 13 shared benchmarks.
| Benchmark | MiniMax M2.5 | GLM-5 | Diff |
|---|---|---|---|
| HLE | 19.4098 / 149Thinking (No Tools) | 50.4015 / 149thinking + 使用工具 | -31 |
| ARC-AGI | 63.7032 / 65Thinking (No Tools) | 44.7044 / 65Thinking (No Tools) | +19 |
| GPQA Diamond | 85.2045 / 175Thinking (No Tools) | 8640 / 175Thinking (No Tools) | -0.80 |
| ARC-AGI-2 | 4.9043 / 58Thinking (No Tools) | 4.9043 / 58Thinking (No Tools) | — |
| Benchmark | MiniMax M2.5 | GLM-5 | Diff |
|---|---|---|---|
| Pinch Bench | 87.806 / 37Thinking (With Tools) | 86.4012 / 37Thinking (With Tools) | +1.40 |
| Claw Bench | 92.104 / 29Thinking (With Tools) | 91.705 / 29Thinking (With Tools) | +0.40 |
| Benchmark | MiniMax M2.5 | GLM-5 | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 97.8010 / 35thinking + 使用工具 | 985 / 35thinking + 使用工具 | -0.20 |
| Benchmark | MiniMax M2.5 | GLM-5 | Diff |
|---|---|---|---|
| BrowseComp | 76.3016 / 43thinking + 使用工具 | 75.9017 / 43thinking + 使用工具 | +0.40 |
| Benchmark | MiniMax M2.5 | GLM-5 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 51.7027 / 43thinking + 使用工具 | 61.1015 / 43thinking + 使用工具 | -9.40 |
| Benchmark | MiniMax M2.5 | GLM-5 | Diff |
|---|---|---|---|
| SWE-bench Verified | 80.209 / 103thinking + 使用工具 | 77.8018 / 103Thinking (No Tools) | +2.40 |
| Benchmark | MiniMax M2.5 | GLM-5 | Diff |
|---|---|---|---|
| IF Bench | 7010 / 27thinking + 使用工具 | 728 / 27thinking + 使用工具 | -2 |
| Benchmark | MiniMax M2.5 | GLM-5 | Diff |
|---|---|---|---|
| AA-LCR | 69.503 / 13Thinking (No Tools) | 6312 / 13Thinking (No Tools) | +6.50 |
| Benchmark | MiniMax M2.5 | GLM-5 | Diff |
|---|---|---|---|
| GDPval-AA | 3616 / 20Thinking (No Tools) | 4613 / 20Thinking (No Tools) | -10 |
| Field | MiniMax M2.5 | GLM-5 |
|---|---|---|
| Publisher | MiniMaxAI | 智谱AI |
| Release date | 2026-02-12 | 2026-02-11 |
| Model type | Reasoning model | AI model |
| Architecture | MoE | MoE |
| Parameters | 2290.0 | 7440.0 |
| Context length | 128K | 200K |
| Max output | Not available | 131072 |
Prices use DataLearner records when available; missing fields are not inferred.
| Item | MiniMax M2.5 | GLM-5 |
|---|---|---|
| Text input | $0.3 / 1M tokens | $1 / 1M tokens |
| Text output | $2.4 / 1M tokens | $3.2 / 1M tokens |
| Cache write | Not public | $0.2 / 1M tokens |
On average across the 13 shared benchmarks, GLM-5 scores 1.79 higher.
Largest single-benchmark gap: HLE — MiniMax M2.5 19.40 vs GLM-5 50.40 (-31).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.
