RankingHealthBench Professional · source release snapshot; version not specified
HealthBench Professional · source release snapshot; version not specified
- Bucket
- Supporting evidence
- Unit
- percent
- Direction
- Higher is better
- Version
- source release snapshot; version not specified
- Display harness
- MAI-Thinking-1 technical report
- Board
- https://microsoft.ai/pdf/mai-thinking-1.pdf
The available records have no admitted matched comparison in the capability core. Raw results remain available below.
Compare published benchmark results with category weights →
Models
| Model | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|
| Claude Sonnet 4.6Anthropic | 38%Reported settings & sourceMicrosoft own evaluation suite; Sonnet max reasoning; Tables 12/19. LongBenchV2 capped 256k,408 questions; CorpusQA GPT-5.4 high judge; 4 runs. First-party reported result; comparator results retain the source evaluation setup. MAI-Thinking-1 technical report · Tables 12 and 19 · reviewed 2026-09-06 | MAI-Thinking-1 technical report | lab self-report | 2026-09-06 |
| MAI-Thinking-1Microsoft | 35%Reported settings & sourceMicrosoft own evaluation suite; Sonnet max reasoning; Tables 12/19. LongBenchV2 capped 256k,408 questions; CorpusQA GPT-5.4 high judge; 4 runs. First-party reported result; comparator results retain the source evaluation setup. MAI-Thinking-1 technical report · Tables 12 and 19 · reviewed 2026-09-06 | MAI-Thinking-1 technical report | lab self-report | 2026-09-06 |
| Claude Opus 4.8Anthropic | 55.8%Reported settings & sourceMeta Model API xhigh; Gemini high; Opus max; GPT xhigh. Best of self-reported or Meta reproduction unless specified. OSWorld GUI only; Terminal bash only5attempts89tasks6CPU8GB; DeepSWE no internet5attempts. First-party reported result; comparator results retain the source evaluation setup. Muse Spark 1.1 evaluation report Figure44 · Figure44 physical page101; methodology pages101–105 · reviewed 2026-09-06 | Muse Spark 1.1 evaluation report Figure44 | lab self-report | 2026-09-06 |
| Gemini 3.1 ProGoogle | 41.6%Reported settings & sourceMeta Model API xhigh; Gemini high; Opus max; GPT xhigh. Best of self-reported or Meta reproduction unless specified. OSWorld GUI only; Terminal bash only5attempts89tasks6CPU8GB; DeepSWE no internet5attempts. First-party reported result; comparator results retain the source evaluation setup. Muse Spark 1.1 evaluation report Figure44 · Figure44 physical page101; methodology pages101–105 · reviewed 2026-09-06 | Muse Spark 1.1 evaluation report Figure44 | lab self-report | 2026-09-06 |
| GPT-5.5OpenAI | 51.8%Reported settings & sourceMeta Model API xhigh; Gemini high; Opus max; GPT xhigh. Best of self-reported or Meta reproduction unless specified. OSWorld GUI only; Terminal bash only5attempts89tasks6CPU8GB; DeepSWE no internet5attempts. First-party reported result; comparator results retain the source evaluation setup. Muse Spark 1.1 evaluation report Figure44 · Figure44 physical page101; methodology pages101–105 · reviewed 2026-09-06 | Muse Spark 1.1 evaluation report Figure44 | lab self-report | 2026-09-06 |
| Muse Spark 1.1Meta | 59.3%Reported settings & sourceMeta Model API xhigh; Gemini high; Opus max; GPT xhigh. Best of self-reported or Meta reproduction unless specified. OSWorld GUI only; Terminal bash only5attempts89tasks6CPU8GB; DeepSWE no internet5attempts. First-party reported result; comparator results retain the source evaluation setup. Muse Spark 1.1 evaluation report Figure44 · Figure44 physical page101; methodology pages101–105 · reviewed 2026-09-06 | Muse Spark 1.1 evaluation report Figure44 | lab self-report | 2026-09-06 |