live
weekly refresh
basedagi.org
benchmark evidence

HiL-Bench Pass@3

HiL-Bench selective escalation benchmark from Scale Labs, using Pass@3 as the outcome metric.

winner on HiL-Bench Pass@3
direct benchmark result, not a broad vertical composite | source row dated 2026-04-29
scored on 2026-04-29
latest mapped results | top 20
#ModelScoreEvidenceTested
1OpenAI: GPT-5.5
Openai
29.1
model-only
independent_benchmark
2026-04-29
2Anthropic: Claude Opus 4.7
Anthropic
27.7
model-only
independent_benchmark
2026-04-17
3Anthropic: Claude Opus 4.6
Anthropic
24.3
model-only
independent_benchmark
2026-04-16
4OpenAI: GPT-5.4
Openai
9.3
model-only
independent_benchmark
2026-04-16
what this result means

HiL-Bench selective escalation benchmark from Scale Labs, using Pass@3 as the outcome metric.

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

A win here is a win on HiL-Bench Pass@3. Broad task pages require independent corroboration before naming a general winner.

source record
category: agentic
metric: accuracy
matched models: 4
latest source date: 2026-04-29
direction: higher is better
inspect upstream source ->