# MAI-Thinking-1 vs MiniMax M3 > Side-by-side benchmark comparison for MAI-Thinking-1 and MiniMax M3 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks. - Canonical page: https://benchlm.ai/compare/mai-thinking-1-vs-minimax-m3 - Last updated: September 4, 2026 - Shared sourced benchmarks: 4 - HTML indexing: indexable - Ranking lane: BenchAlign v5 ## Quick Verdict Pick MiniMax M3 if you want the stronger benchmark profile. MAI-Thinking-1 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score. ## Summary - MiniMax M3 leads overall 63.91 to 52.27. - The clearest category separation is in agentic, where the averages are 51.7 for MAI-Thinking-1 and 43.2 for MiniMax M3. - The biggest single benchmark swing is Terminal-Bench 2.0 in Agentic, with scores of 46% and 66%. - MiniMax M3 also has the larger context window at 1M. ## Model Snapshot | Property | MAI-Thinking-1 | MiniMax M3 | |----------|----------|----------| | Creator | Microsoft | MiniMax | | Type | Proprietary | Open Weight | | Reasoning | Reasoning | Non-Reasoning | | Context | 256K | 1M | | Overall Score | 52.27 | 63.91 | | Benchmarks Covered | 14 | 27 | | Pricing (input/output) | N/A | $0.30 / $1.20 | ## Category Breakdown ### Agentic - Winner: Coming soon - MAI-Thinking-1 public-lane score: 51.7 (Estimated · #53/151) - MiniMax M3 public-lane score: 43.2 (Supported · #106/151) | Benchmark | MAI-Thinking-1 | MiniMax M3 | Winner | |-----------|-----------|-----------|--------| | Terminal-Bench 2.0 | 46% | 66% | MiniMax M3 | | BrowseComp | Coming soon | 83.5% | Coming soon | | OSWorld-Verified | Coming soon | 70.1% | Coming soon | | MCP Atlas | Coming soon | 74.2% | Coming soon | | Claw-Eval | Coming soon | 74.5% | Coming soon | | BankerToolBench | Coming soon | 76.1% | Coming soon | | ResearchClawBench | Coming soon | 19.8% | Coming soon | | OSWorld 2.0 | Coming soon | 4.6% | Coming soon | | Terminal-Bench 2.1 (Vals) | Coming soon | 53.6% | Coming soon | ### Coding - Winner: Coming soon - MAI-Thinking-1 public-lane score: 51.8 (Estimated · #60/183) - MiniMax M3 public-lane score: 50.6 (Estimated · #68/183) | Benchmark | MAI-Thinking-1 | MiniMax M3 | Winner | |-----------|-----------|-----------|--------| | LiveCodeBench v6 | 87.7% | Coming soon | Coming soon | | SWE-bench Verified | 73.5% | 80.5% | MiniMax M3 | | SWE-bench Pro | 52.8% | 59% | MiniMax M3 | | Terminal-Bench 2.0 | 46.0% | 66.0% | MiniMax M3 | | NL2Repo | Coming soon | 42.1% | Coming soon | | VIBE V2 | Coming soon | 50.1% | Coming soon | | SVG-Bench | Coming soon | 63.7% | Coming soon | | KernelBench Hard | Coming soon | 28.8% | Coming soon | | OpenHarmony Bench | Coming soon | 48.4% | Coming soon | | LiveCodeBench (Vals) | Coming soon | 82.2% | Coming soon | | SWE-bench (Vals) | Coming soon | 75.0% | Coming soon | ### Multimodal & Grounded - Winner: Coming soon - MAI-Thinking-1 public-lane score: Coming soon - MiniMax M3 public-lane score: 52 (#34/48) | Benchmark | MAI-Thinking-1 | MiniMax M3 | Winner | |-----------|-----------|-----------|--------| | OfficeQA Pro | Coming soon | 45.1% | Coming soon | | OmniDocBench 1.5 | Coming soon | 91.6% | Coming soon | | MMMU-Pro | Coming soon | 78.1% | Coming soon | | VideoMMMU | Coming soon | 84.6% | Coming soon | | Video-MME (with subtitle) | Coming soon | 85.4% | Coming soon | ### Reasoning - Winner: Coming soon - MAI-Thinking-1 public-lane score: Coming soon - MiniMax M3 public-lane score: 78.5 (#5/22) | Benchmark | MAI-Thinking-1 | MiniMax M3 | Winner | |-----------|-----------|-----------|--------| | Graphwalks BFS 128K | 90% | Coming soon | Coming soon | ### Knowledge - Winner: Coming soon - MAI-Thinking-1 public-lane score: 53.3 (Estimated · #68/181) - MiniMax M3 public-lane score: 53.9 (Supported · #65/181) | Benchmark | MAI-Thinking-1 | MiniMax M3 | Winner | |-----------|-----------|-----------|--------| | GPQA | 84.2% | Coming soon | Coming soon | | GPQA-D | 84.2% | Coming soon | Coming soon | | MMLU-Pro | 85% | Coming soon | Coming soon | | SimpleQA | 31% | Coming soon | Coming soon | | GPQA Diamond (Vals) | Coming soon | 92.7% | Coming soon | | MMLU-Pro (Vals) | Coming soon | 84.2% | Coming soon | ### Instruction Following - Winner: Coming soon - MAI-Thinking-1 public-lane score: 94.7 (#1/120) - MiniMax M3 public-lane score: 93.5 (#4/120) | Benchmark | MAI-Thinking-1 | MiniMax M3 | Winner | |-----------|-----------|-----------|--------| | IFBench | 85% | Coming soon | Coming soon | ### Mathematics - Winner: Coming soon - MAI-Thinking-1 public-lane score: 73.4 (Unranked · 3 rankable rows) - MiniMax M3 public-lane score: Coming soon | Benchmark | MAI-Thinking-1 | MiniMax M3 | Winner | |-----------|-----------|-----------|--------| | AIME 2025 | 97% | Coming soon | Coming soon | | AIME26 | 94.5% | Coming soon | Coming soon | | HMMT Feb 2026 | 84.9% | Coming soon | Coming soon | | USAMO 2026 | Coming soon | 85.7% | Coming soon | ## FAQ ### Which is better overall, MAI-Thinking-1 or MiniMax M3? MiniMax M3 is ahead overall on BenchLM right now. ### Where is the biggest gap between MAI-Thinking-1 and MiniMax M3? The widest category gap is in agentic, where the averages are 51.7 for MAI-Thinking-1 and 43.2 for MiniMax M3. ### How many benchmarks does MAI-Thinking-1 cover on BenchLM? MAI-Thinking-1 currently has 14 sourced benchmark scores on BenchLM. ### How many benchmarks does MiniMax M3 cover on BenchLM? MiniMax M3 currently has 27 sourced benchmark scores on BenchLM. ## Related Comparisons - [MAI-Thinking-1 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-mai-thinking-1) - [MiniMax M3 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-minimax-m3) - [MAI-Thinking-1 vs GPT-6 Astra](/compare/gpt-6-astra-vs-mai-thinking-1) - [MiniMax M3 vs GPT-6 Astra](/compare/gpt-6-astra-vs-minimax-m3) ## Explore More - [MAI-Thinking-1 profile](/models/mai-thinking-1) - [MiniMax M3 profile](/models/minimax-m3) - [Compare Pricing](/llm-pricing) - [Alternative Finder](/tools/alternative-finder) - [LLM Selector](/tools/llm-selector) - [Overall Rankings](/best/overall)