Terminal-Bench 2.1 ↗87.27 %
GPT-6 Astra (Terminus 2) · Terminal-Bench 2.1 · Score ↗
OpenAI / MODEL EVIDENCE
GPT-6 Astra (Terminus 2)
1 benchmarks · 1 observations · 1 sources
Scores at a glance
1 benchmarks · large dot: GPT-6 Astra (Terminus 2); small dots: closest models where reported
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Claude Opus 5.5 (Terminus 2) →Anthropic
1 of 1 shared benchmark comparisons
1 of 1 shared benchmark comparisons
Claude Fable 5.1 (Terminus 2) →Anthropic
1 of 1 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
POST-TRAINING / SOURCE DISCLOSURE
What the GPT-6 Astra report says
The system card discusses reinforcement-learning grading, alignment improvements and safety behavior integrated into post-training. It reports how these changes are evaluated rather than providing the full production training recipe.
- Reinforcement learning with alignment-focused grading
- Safety behavior integrated into post-training
A specific optimizer, training-data mixture and complete compute ledger are not given in the reviewed system card. Evaluation scores do not identify those missing details.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
Names used in source tables
GPT-6 Astra (Terminus 2)