Codex + GPT-6.2 Astra: benchmark scores, price and ranking

Codex + GPT-6.2 Astra ranks #65 of 827 LLMs on the LLMs Tiger aggregate benchmark score (52.7), based on 1 benchmark results captured up to 2026-11-18.

Type
Frontier model
Open weights
No
Aggregate rank
#65 of 827 (score 52.7)

Across the 1 benchmark where at least ten models are scored, Codex + GPT-6.2 Astra is in the top 10% on 0 and in the top half on 1.

Codex + GPT-6.2 Astra benchmark results

Codex + GPT-6.2 Astra benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
Terminal-Bench 4.062.1%#6 of 52Terminal-Bench 4.0 official leaderboard2026-11-18

About Codex + GPT-6.2 Astra

Codex + GPT-6.2 Astra is a frontier model. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where Codex + GPT-6.2 Astra stands

On our aggregate score, Codex + GPT-6.2 Astra is #65 of 827 ranked models, in the top quarter. Its score is 52.7; the scale is centred on 50, so it sits 2.7 points above the typical model. That beats 92% of the ranked field.

Codex + GPT-6.2 Astra, benchmark by benchmark

Terminal-Bench 4.0 puts Codex + GPT-6.2 Astra at 62.1%, #6 of 52. That beats 88% of the models tested, but 9.1 points short of GitHub Copilot + Copilot Fusion (71.2%). The results either side are Claude Code + Sonnet 5.5 (63.9%) and Codex + GPT-6.2 Sol (61.5%). It covers real terminal tasks, agent+model config. The board median is 29.1%, so Codex + GPT-6.2 Astra is 33.0 points above it. Source: Terminal-Bench 4.0 official leaderboard, captured 2026-11-18.

Reading these numbers

The 1 score on this page comes from 1 source: Terminal-Bench 4.0 official leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

Compare it on the live leaderboard → · How the aggregate score works