MAI-Thinking-1
MAI-Thinking-1MicrosoftProprietaryReasoningProvisionalReleased Jun 2, 2026
Overall score
53.3
Rank 83 of 222 · 38.9–67.6
Context window
256K
256,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Instruction following#394.7
- 2Math81.1
- 3Knowledge78.1
- 4Coding42.5
- 5Agentic & tool use30.2
Benchmark results (11)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Coding
| SWE-bench Verified | 73.5 | #46 of 98 |
| SWE-bench Pro | 52.8 | #54 of 69 |
| LiveCodeBench v6 | 87.7 | #12 of 46 |
Math
| AIME 2025 | 97.0 | #3 of 38 |
| AIME26 | 94.5 | #16 of 29 |
| HMMT Feb 2026 | 84.9 | #15 of 24 |
Knowledge
| GPQA | 84.2 | #51 of 117 |
| MMLU-Pro | 85.0 | #20 of 67 |
Agentic & tool use
| Terminal-Bench 2.0 | 46.0 | #34 of 39 |
Reasoning
| Graphwalks BFS 128K | 90.0 | #2 of 2 |
Instruction following
| IFBench | 85.0 | #1 of 42 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price | — | — | — |
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.
Related models
Similar score
- GLM-5-Turbo53.2 · $1.90
- GPT-5.4 mini53.4 · $1.69
- Grok 4.353.1 · $1.56
- Kimi K2.553.0 · $1.20
- MiMo-V2.5-Pro53.0 · $0.54