TutorMoments
Can the model produce useful work in a professional knowledge-work setting?
Knowledge Work7 ranked models14 reported values1 reportsHigher is better
Top rankings
One row per model, using its best reported score across effort settings.
| Rank | Model | Best score | Best reported setting |
|---|---|---|---|
| 1 | Claude Opus 4.8Anthropic | 0.831 | Reported configurationAllen AI report2 values · 1 reportAug 7, 2026 · source |
| 2 | Claude Sonnet 4.6Anthropic | 0.792 | Reported configurationAllen AI report2 values · 1 reportAug 7, 2026 · source |
| 3 | Gemini 2.5 ProGoogle | 0.712 | Reported configurationAllen AI report2 values · 1 reportAug 7, 2026 · source |
| 4 | Gemini 3.5 FlashGoogle | 0.646 | Reported configurationAllen AI report2 values · 1 reportAug 7, 2026 · source |
| 5 | GPT-5.5OpenAI | 0.531 | Reported configurationAllen AI report2 values · 1 reportAug 7, 2026 · source |
| 6 | DeepSeek V4 ProDeepSeek | 0.492 | Reported configurationAllen AI report2 values · 1 reportAug 7, 2026 · source |
| 7 | GPT 5.4 miniOpenAI | 0.404 | Reported configurationAllen AI report2 values · 1 reportAug 7, 2026 · source |
Effort curve
Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarylimited methodology
Can the model produce useful work in a professional knowledge-work setting?
Professional analysis, document, finance, office, or domain-specific tasks. Higher is better. Share of annotated moments where the model made the appropriate tutoring move.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
Evaluation-aware prompt is the first value and plain prompt the second; 260 rigor moments in the annotations.
Method / source