Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | minimaxMiniMax: MiniMax M2.7Remove × | zai-orgGLM-5.3-FlashRemove × | googleGoogle: Gemini 4 ArgonRemove × |
|---|---|---|---|
| What’s different | MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates… | GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context… | Long decode can use the unified 1M-token budget for output; reads video, audio and PDFs, with implicit-only caching. |
| Date | Mar 18, 2026Listed | Aug 26, 2026Released | Sep 30, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.21 in / $0.84 out/ 1M tokensGMICloud · via OpenRouter · all routes ↗gmicloud/fp8 · quantization=fp8 | $0.048 in / $0.16 out/ 1M tokensOpenInference · via OpenRouter · all routes ↗open-inference/fp4 · quantization=fp4 | $1.00 in / $5.00 out/ 1M tokensGoogle AI Studio · via OpenRouter · all routes ↗google-ai-studio/flex · tier=flex |
| Provider endpoints | 10 endpoints → | 46 endpoints → | 8 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Intelligence ↗4.3.2 | Not reported | 41.81 ↗Effort: maxIndependent result | 52.56 ↗Effort: high · HighIndependent result |
| AA-Briefcase ↗1.1 | Not reported | 1,452.63 ↗Effort: maxIndependent result | 1,485.76 ↗Effort: high · HighIndependent result |
| GDPval-AA ↗2.1 | Not reported | 1,642.18 ↗Effort: maxIndependent result | 1,623.11 ↗Effort: high · HighIndependent result |
| AutomationBench-AA ↗AA Index 4.3.2 collection | Not reported | 60.37% ↗Effort: maxIndependent result | 77.51% ↗Effort: high · HighIndependent result |
| Terminal-Bench 4.0 · AA ↗ | Not reported | 32.83% ↗Effort: maxHarness unreportedIndependent result | 57.07% ↗Effort: high · HighHarness unreportedIndependent result |
| SciCode ↗AA Index 4.3.2 collection | Not reported | 51.62% ↗AA · Under reviewEffort: maxIndependent result | 61.81% ↗AA · Under reviewEffort: high · HighIndependent result |
| Humanity’s Last Exam ↗AA Index 4.3.2 collection | Not reported | 39.85% ↗Effort: maxIndependent result | 57.09% ↗Effort: high · HighIndependent result |
| GDP.pdf ↗AA Index 4.3.2 collection | Not reported | 15.4% ↗Effort: maxIndependent result | 21.8% ↗Effort: high · HighIndependent result |
| CritPt ↗AA Index 4.3.2 collection | Not reported | 15.43% ↗AA · Under reviewEffort: maxIndependent result | 27.14% ↗AA · Under reviewEffort: high · HighIndependent result |
| AA-Omniscience ↗AA Index 4.3.2 collection | Not reported | 7.47 ↗Effort: maxIndependent result | 42.35 ↗Effort: high · HighIndependent result |
| AA-LCR ↗1.1 | Not reported | 80% ↗Effort: maxIndependent result | 79.67% ↗Effort: high · HighIndependent result |
| LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 70.61% ↗Effort: max · single run · equal mean of 7 suitesIndependent result | 84.1% ↗Effort: high · single run · equal mean of 7 suitesIndependent result |
| LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 77.2% ↗Effort: max · single runIndependent result | 73.7% ↗Effort: high · single runIndependent result |
| LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 70.1% ↗Effort: max · single runIndependent result | 83.1% ↗Effort: high · single runIndependent result |
| LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 84% ↗Effort: max · single runIndependent result | 92% ↗Effort: high · single runIndependent result |
| LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 80.6% ↗Effort: max · single runIndependent result | 89.7% ↗Effort: high · single runIndependent result |
| LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 28.4% ↗Effort: max · single runIndependent result | 69.9% ↗Effort: high · single runIndependent result |
| LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 76.4% ↗Effort: max · single runIndependent result | 85.2% ↗Effort: high · single runIndependent result |
| LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 77.6% ↗Effort: max · single runIndependent result | 95.1% ↗Effort: high · single runIndependent result |
Specifications | |||
| Context window | 204.8K | 1M | 1M |
| Max output | 131.1K | 943.7K | 943.7K |
| Parameters | — | — | — |
| Tool calling | Supported | Supported | Supported |
| Structured output | Supported | Supported | Supported |
| Image input | Not reported | Supported | Supported |
| Audio input | Not reported | Not reported | Supported |
| Video input | Not reported | Supported | Supported |
| Reasoning | Supported | Supported | Supported |
| Prompt caching | Supported | Supported | Supported |
| Open weights | Supported | Supported | Not reported |