gpt-5.4-2026-03-05 (xhigh thinking) · Scale Labs · Score ↗
OpenAI / MODEL EVIDENCE
GPT-5.4-2026-03-05
3 benchmarks · 3 observations · 3 sources
Scores at a glance
3 benchmarks · large dot: GPT-5.4-2026-03-05; small dots: closest models where reported
VISTA ↗50.89%
gpt-5.4-2026-03-05 (xhigh thinking) · Scale Labs · Score ↗
ForecastBench ↗63.1 Brier index
gpt-5.4-2026-03-05† · Overall difficulty-adjusted Brier index ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
There are not enough shared scored settings to identify close comparisons reliably.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- Forecastbench — methodology and published results ↗
- Scale Labs — evaluation methodology and results ↗
- Scale Labs — evaluation methodology and results ↗
Names used in source tables
gpt-5.4-2026-03-05 (xhigh thinking) · gpt-5.4-2026-03-05†