Model comparison
MAI-Thinking-1 vs MiniMax M3
Head-to-head evidence from 4 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: MAI-Thinking-1 unranked (Not scored); MiniMax M3 #15 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. MAI-Thinking-1 and MiniMax M3 share 4 comparable benchmark results. 3 of 8 categories are comparable. 9 results are unique to MAI-Thinking-1; 41 to MiniMax M3.
Updated July 23, 2026- Shared results
- 4
- MAI-Thinking-1 only
- 9
- MiniMax M3 only
- 41
- Comparable categories
- 3 / 8
Treat this as a split decision. MAI-Thinking-1 makes more sense if mathematics is the priority or you want the stronger reasoning-first profile; MiniMax M3 is the better fit if agentic is the priority or you need the larger 1M context window.
Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 2 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
MAI-Thinking-1 and MiniMax M3 finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
MAI-Thinking-1 is the reasoning model in the pair, while MiniMax M3 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. MiniMax M3 gives you the larger context window at 1M, compared with 256K for MAI-Thinking-1.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | MAI-Thinking-1 | Δ | MiniMax M3 |
|---|---|---|---|
| Agentic | MAI-Thinking-146.0 | Margin→ 26.3 | MiniMax M372.3 |
| Coding | MAI-Thinking-165.5 | Margin→ 6.7 | MiniMax M372.2 |
| Math | MAI-Thinking-189.7 | Margin← 4.0 | MiniMax M385.7 |
| Knowledge | MAI-Thinking-172.5 | MarginNo overlap | MiniMax M3Not measured |
| Multimodal | MAI-Thinking-1Not measured | MarginNo overlap | MiniMax M364.9 |
| Inst. Following | MAI-Thinking-185.0 | MarginNo overlap | MiniMax M3Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 46%B 66%Winner: MiniMax M3Δ 20Terminal-Bench 2.0: MAI-Thinking-1 scored 46%; MiniMax M3 scored 66%. MiniMax M3 wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 73.5%B 80.5%Winner: MiniMax M3Δ 7SWE-bench Verified: MAI-Thinking-1 scored 73.5%; MiniMax M3 scored 80.5%. MiniMax M3 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 52.8%B 59%Winner: MiniMax M3Δ 6.2SWE-bench Pro: MAI-Thinking-1 scored 52.8%; MiniMax M3 scored 59%. MiniMax M3 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | MAI-Thinking-1 | MiniMax M3 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | MAI-Thinking-1Not available | MiniMax M3$0.3 input / $1.2 output | A complete price comparison is not available. |
| Generation speedtokens per second | MAI-Thinking-1Not available | MiniMax M3Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | MAI-Thinking-1Not available | MiniMax M3Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | MAI-Thinking-1256K | MiniMax M31M | MiniMax M3 lists the larger context window. |
Benchmark Deep Dive
AgenticMiniMax M3 wins18 benchmarks
| Benchmark | MAI-Thinking-1 | MiniMax M3 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 46% | 66% | MiniMax M3 leads |
| BrowseCompSource | — | 83.5% | Not comparable |
| OSWorld-VerifiedSource | — | 70.1% | Not comparable |
| MCP AtlasSource | — | 74.2% | Not comparable |
| Claw-EvalSource | — | 74.5% | Not comparable |
| AA Agentic IndexSource | — | 35.4% | Not comparable |
| τ²-bench resultsSource | — | 88.9% | Not comparable |
| GDPval-AASource | — | 44.7% | Not comparable |
| GDPval-AASource | — | 1395 | Not comparable |
| GDPval rubricsSource | — | 74.7% | Not comparable |
| BankerToolBenchSource | — | 76.1% | Not comparable |
| ResearchClawBenchSource | — | 19.8% | Not comparable |
| OSWorld 2.0Source | — | 4.6% | Not comparable |
| AA BriefcaseSource | — | 1110 | Not comparable |
| AA EnterpriseOps-GymSource | — | 32.1% | Not comparable |
| AA Harvey LABSource | — | 88.4% | Not comparable |
| terminalBenchHardSource | — | 42.4% | Not comparable |
| aaTerminalBench21Source | — | 65.2% | Not comparable |
CodingMiniMax M3 wins9 benchmarks
| Benchmark | MAI-Thinking-1 | MiniMax M3 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 73.5% | 80.5% | MiniMax M3 leads |
| SWE-bench ProSource | 52.8% | 59% | MiniMax M3 leads |
| Terminal-Bench 2.0Source | 46.0% | 66.0% | MiniMax M3 leads |
| NL2RepoSource | — | 42.1% | Not comparable |
| AA Coding IndexSource | — | 58.6% | Not comparable |
| AA-SciCodeSource | — | 45.4% | Not comparable |
| VIBE V2Source | — | 50.1% | Not comparable |
| SVG-BenchSource | — | 63.7% | Not comparable |
| KernelBench HardSource | — | 28.8% | Not comparable |
Reasoning3 benchmarks
Knowledge11 benchmarks
| Benchmark | MAI-Thinking-1 | MiniMax M3 | Result |
|---|---|---|---|
| GPQASource | 84.2% | — | Not comparable |
| GPQA-DSource | 84.2% | — | Not comparable |
| MMLU-ProSource | 85% | — | Not comparable |
| SimpleQASource | 31% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 44.4% | Not comparable |
| AA-GPQA DiamondSource | — | 92.9% | Not comparable |
| AA-HLESource | — | 37.1% | Not comparable |
| AA-Omniscience IndexSource | — | 1.4% | Not comparable |
| AA-Omniscience AccuracySource | — | 15.0% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 16.1% | Not comparable |
| AA Openness IndexSource | — | 33.3% | Not comparable |
MathMAI-Thinking-1 wins4 benchmarks
Multimodal7 benchmarks
| Benchmark | MAI-Thinking-1 | MiniMax M3 | Result |
|---|---|---|---|
| OfficeQA ProSource | — | 45.1% | Not comparable |
| OmniDocBench 1.5Source | — | 91.6% | Not comparable |
| MMMU-ProSource | — | 78.1% | Not comparable |
| VideoMMMUSource | — | 84.6% | Not comparable |
| Video-MME (with subtitle)Source | — | 85.4% | Not comparable |
| Design Arena WebsiteSource | — | 1289 | Not comparable |
| AA-MMMU-ProSource | — | 78.6% | Not comparable |
Frequently Asked Questions (4)
Which is better, MAI-Thinking-1 or MiniMax M3?
MAI-Thinking-1 and MiniMax M3 are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for coding, MAI-Thinking-1 or MiniMax M3?
MiniMax M3 has the edge for coding in this comparison, averaging 72.2 versus 65.5. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for math, MAI-Thinking-1 or MiniMax M3?
MAI-Thinking-1 has the edge for math in this comparison, averaging 89.7 versus 85.7. MiniMax M3 stays close enough that the answer can still flip depending on your workload.
Which is better for agentic tasks, MAI-Thinking-1 or MiniMax M3?
MiniMax M3 has the edge for agentic tasks in this comparison, averaging 72.3 versus 46. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.