Codex + GPT-6 Sol: benchmark scores, price and ranking
Codex + GPT-6 Sol ranks #106 of 743 LLMs on the LLMs Tiger aggregate benchmark score (51.6), based on 1 benchmark results captured up to 2026-10-13.
- Type
- Frontier model
- Open weights
- No
- Aggregate rank
- #106 of 743 (score 51.6)
Across the 1 benchmark where at least ten models are scored, Codex + GPT-6 Sol is in the top 10% on 0 and in the top half on 1.
Codex + GPT-6 Sol benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Terminal-Bench 4.0 | 49.4% | #7 of 23 | Terminal-Bench 4.0 official leaderboard | 2026-10-13 |
About Codex + GPT-6 Sol
Codex + GPT-6 Sol 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 Sol stands
On our aggregate score, Codex + GPT-6 Sol is #106 of 743 ranked models, in the top quarter. Its score is 51.6; the scale is centred on 50, so it sits 1.6 points above the typical model. That beats 86% of the ranked field.
Codex + GPT-6 Sol, benchmark by benchmark
Terminal-Bench 4.0 puts Codex + GPT-6 Sol at 49.4%, #7 of 23. That beats 70% of the models tested, but 15.5 points short of Claude Code + Opus 5.5 (64.8%). The results either side are Claude Code + Opus 5 (53.9%) and Claude Code + Fable 5 (44.5%). It covers real terminal tasks, agent+model config. The board median is 35.8%, so Codex + GPT-6 Sol is 13.6 points above 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
- #103 Darwin-36B-Opus (51.7)
- #104 Intern-S1 (51.7)
- #105 GLM-4.7-FP8 (51.6)
- #107 o1-2024-12-17 (51.6)
- #108 DeepSeek v4 Pro (max) (51.6)
- #109 GLM-5.2 (high) (51.6)
Compare it on the live leaderboard → · How the aggregate score works