Reasoning specialists from Z.ai, MiniMax, and DeepSeek. The reasoning benchmarks lead the band; effort tiers are noted where a model exposes them.Last reviewed 2026-09-09.
Z.ai's large-scale reasoning flagship for complex software engineering and long-horizon agent tasks.
MiniMax's multimodal foundation model for long-horizon agentic work.
The GA release of DeepSeek's open 1.6T-parameter MoE flagship for advanced reasoning and long-horizon agents.
No shared demos for these models yet.
No captured outputs for these models yet.
MiniMax M3 has the lowest blended list price. Per 1M tokens: GLM 5.3 at $1.40 in / $4.40 out; MiniMax M3 at $0.30 in / $1.20 out; DeepSeek V4 Pro (0813) at $0.66 in / $1.98 out.
GLM 5.3 leads with 1M tokens. The other two: MiniMax M3 at 524K, DeepSeek V4 Pro (0813) at 1M.
MiniMax M3 accept images; the others do not.
This idapt comparison runs all three in aligned columns: the same prompt, plus benchmarks, specs, and prices per model. Open any model in chat from its column to keep working with it.