TEACHARENA benchmark¶
Product or Programme · All products and programmes
Evidence · 4 claims (4 for) · 1 study (1 design),q2· 0 of 1 report an effect size · 4 claims rest on one study
Description¶
A source-grounded benchmark and evaluation harness created by Zixin Chen et al. containing 354 audited teacher-task instances with matched verifiers for evaluating tutor agents' pedagogical judgment, adaptive tutoring, and institutional workflow execution.
Components¶
Claims¶
- Across 17 frontier models, Stage 1 pedagogical-judgment scores are high (mean 0.893) while rank correlations with Stage 2 (ρ=0.24) and Stage 3 (ρ=0.21) are weak, with workflow scores topping out at 0.704 [+M]
- The strategic surface learner is the lowest-scoring Stage 2 profile for 15 of 17 models, averaging 0.702 versus 0.757 across the other profiles [+M]
- The six long-chain Stage 3 workflows average 0.321 versus 0.559 across all other Stage 3 tasks and are the lowest-scoring family for 15 of 17 models [+M]
- Claude Opus 4.8 has the highest overall score (0.803) and is the only model ranking in the top three on all three stages, yet does not saturate situated tutoring (0.773) or workflows (0.704) [+W]
Related Products and Programmes¶
Key Sources¶
- Zixin Chen, Peng Liu, Rui Sheng, Haobo Li, Jianhong Tu, Xiaodong Deng, Kashun Shum, Dayiheng Liu, Huamin Qu. (2026). Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows. Preprint. https://arxiv.org/abs/2605.14322
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
teacharena-benchmark |
title |
TEACHARENA benchmark |
description |
A source-grounded benchmark and evaluation harness created by Zixin Chen et al. |
status |
review |
product_kind |
dataset |
generated |
by process:settle-candidates on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.