Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Microsoft · Proprietary · rank 88 · bench-align-v5
MAI-Thinking-1 is a general-purpose language model. It ranks in the top quarter for instruction following (top 2% of 159 scored models) and knowledge (top 12% of 284 scored models), by BenchLM's published scores.
MAI-Thinking-1 by Microsoft scores 52.91 overall and carries a context window of 256K tokens — context window observed 2026-11-21, overall score last good 2026-10-23.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Every published price component, including cache reads and writes.
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: ObservedLast goodUnavailable
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | Unavailable | Unavailable | Unavailable | |
| Throughput | Unavailable | Unavailable | Unavailable |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 84.2 | #60 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| GPQA-D GPQA Diamond | 84.2 | #66 | Graduate-level science questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| MMLU-Pro Massive Multitask Language Understanding Professional | 85 | #21 | Multiple subjects | Professional level | MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark |
| SimpleQA Measuring Short-Form Factuality in Large Language Models | 31 | #6 | Factual questions | Factual accuracy focused | Measuring short-form factuality in large language models |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 46.0 | #57 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| SWE-bench Verified Software Engineering Benchmark Verified | 73.5 | #55 | 500 verified issues | Professional software engineering | SWE-bench: Can Language Models Resolve Real-World GitHub Issues? |
| LiveCodeBench v6 LiveCodeBench v6 | 87.7 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AIME 2025 American Invitational Mathematics Examination 2025 | 97 | #4 | 15 problems | High school olympiad level | American Invitational Mathematics Examination |
| AIME26 AIME 2026 | 94.5 | #19 | Competition math problems | Olympiad-style mathematics | Qwen3.6 launch benchmarks |
| HMMT Feb 2026 Harvard-MIT Mathematics Tournament February 2026 | 84.9 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Graphwalks BFS 128K Graphwalks BFS 0K-128K | 90 | #2 | Graph traversal tasks | Algorithmic long-context reasoning | Introducing GPT-5.4 mini and nano |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 46 | #60 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| StealthMark StealthMark Intelligence Benchmarks (overall score) | 14.1 | #43 | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon | Chained physical reasoning, planning without tools and precise visual construction | StealthMark: The AI Benchmark Explained (Stealth Models) |
| #15 |
| Fresh programming problems |
| Competitive programming level |
| LiveCodeBench official repository and release documentation |
| SWE-bench Pro SWE-bench Pro | 52.8 | #64 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| Competition math problems |
| Olympiad-style mathematics |
| Qwen3.6 launch benchmarks |