live
weekly refresh
basedagi.org
benchmark evidence

TutorBench

Scale Labs tutoring benchmark measuring adaptive explanations, feedback, and hint quality.

winner on TutorBench
direct benchmark result, not a broad vertical composite | source row dated 2025-09-10
scored on 2025-12-15 · stale source data (165d)
latest mapped results | top 20
#ModelScoreEvidenceTested
1OpenAI: GPT-5
Openai
77.3
model-only
independent_benchmark
2025-09-10
2OpenAI: GPT-5.2
Openai
74.7
model-only
independent_benchmark
2025-12-15
3Anthropic: Claude Opus 4.5
Anthropic
69.6
model-only
independent_benchmark
2025-09-10
4Anthropic: Claude Sonnet 4.5
Anthropic
63.8
model-only
independent_benchmark
2025-09-10
5Meta: Llama 4 Maverick
Meta Llama
56.2
model-only
independent_benchmark
2025-09-10
what this result means

Scale Labs tutoring benchmark measuring adaptive explanations, feedback, and hint quality.

This benchmark contributes direct public evidence. Read its scope before generalizing the result.

A win here is a win on TutorBench. Broad task pages require independent corroboration before naming a general winner.

source record
category: writing
metric: accuracy
matched models: 5
latest source date: 2025-12-15
direction: higher is better
inspect upstream source ->