Codex + GPT-6 Luna: benchmark scores, price and ranking

Codex + GPT-6 Luna ranks #391 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.0), based on 1 benchmark results captured up to 2026-10-13.

Type
Frontier model
Open weights
No
Aggregate rank
#391 of 743 (score 48.0)

Across the 1 benchmark where at least ten models are scored, Codex + GPT-6 Luna is in the top 10% on 0 and in the top half on 0.

Codex + GPT-6 Luna benchmark results

Codex + GPT-6 Luna benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
Terminal-Bench 4.016.4%#19 of 23Terminal-Bench 4.0 official leaderboard2026-10-13

About Codex + GPT-6 Luna

Codex + GPT-6 Luna 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 Luna stands

On our aggregate score, Codex + GPT-6 Luna is #391 of 743 ranked models, around the middle of the table. Its score is 48.0; the scale is centred on 50, so it sits 2.0 points below the typical model. That beats 47% of the ranked field.

Codex + GPT-6 Luna, benchmark by benchmark

Terminal-Bench 4.0 is a weak spot. Codex + GPT-6 Luna scores 16.4%, #19 of 23, behind 78% of the models measured. The leader, Claude Code + Opus 5.5, reaches 64.8%. It covers real terminal tasks, agent+model config. The board median is 35.8%, so Codex + GPT-6 Luna is 19.4 points below it. Source: Terminal-Bench 4.0 official leaderboard, captured 2026-10-13.

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