BlogLLM Benchmark Scores as Published, Side by Side
MAI-Thinking-1: Benchmark Scores as Published
Every result the catalog holds for MAI-Thinking-1: 24 tests in 10 areas, from 3 pages. All were printed by Microsoft itself. Each number is as printed; nothing is ranked or rescored.
Developer MicrosoftReleased 2026-08-12Context window 256KData version 2026103001, as of 2026-10-30
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 73.5% | Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19 | - |
| SWE-Bench Pro | 52.8% | Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19 | - |
| Terminal-Bench 2.0 | 46% | Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19 | - |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 84.2% | Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19; printed on 1 more page | - |
| AIME 2025 | 97% | Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19; printed on 1 more page | - |
| AIME 2026 | 94.5% | Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19; printed on 1 more page | - |
| HMMT February 2026 | 84.9% | Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19; printed on 1 more page | - |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LongBench v2 | 61% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | Effort: max |
| CorpusQA (AI-judge score)AI-judge score | 82 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | Effort: max |
| GraphWalks up to 128k (overall F1) (GraphWalks overall F1, up to 128k)GraphWalks overall F1, up to 128k | 90% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
Cybersecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CyberSecEval 4 Autocomplete (score)score | 63 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
| CyberSecEval 4 Instruct (score)score | 63 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMLU-Pro | 85% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
| SimpleQA Verified | 31% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
| LongFact claim precision (LongFact claim-level precision)LongFact claim-level precision | 98% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
| TruthfulQA (accuracy)accuracy | 88% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveCodeBench v6 | 87.7% | Microsoft, Microsoft AI: Introducing MAI-Thinking-1checked 2026-10-19; printed on 1 more page | - |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BFCL v3 (accuracy)accuracy | 72% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| IFBench | 69 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
| MultiChallenge | 53% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
| AdvancedIF (rubric-level score)rubric-level score | 85 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
Healthcare
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| HealthBench Professional | 35% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
| MedXpertQA Text (accuracy)accuracy | 43% | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
Safety and Alignment
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AIR-Bench 2024 (aggregate score)aggregate score | 88 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $2 | Microsoft, Microsoft Foundry Models pricing, Microsoft modelschecked 2026-10-19 | - |
| Cached input | $0.2 | Microsoft, Microsoft Foundry Models pricing, Microsoft modelschecked 2026-10-19 | - |
| Output | $8 | Microsoft, Microsoft Foundry Models pricing, Microsoft modelschecked 2026-10-19 | - |
More from Microsoft
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.