Codex Mini (Latest): benchmark scores, price and ranking
Codex Mini (Latest) from OpenAI ranks #424 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.5), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- OpenAI
- Type
- Fast / low-cost (flash) model
- Open weights
- No
- Cheapest API price
- $1.50 in / $6.00 out per million tokens (via azure, observed 2026-10-13T20:47Z)
- Aggregate rank
- #424 of 743 (score 47.5)
Across the 1 benchmark where at least ten models are scored, Codex Mini (Latest) is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $1.50 per million tokens, is lower than that of 25% of the 427 models with a listed price.
Codex Mini (Latest) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| ARC-AGI-2 | 1.3% | #71 of 87 | ARC Prize official leaderboard | 2026-10-13 |
About Codex Mini (Latest)
Codex Mini (Latest) is a smaller, lower-cost model from OpenAI. The cheapest API listing we track charges $1.50 per million input tokens and $6.00 per million output tokens, through azure. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where Codex Mini (Latest) stands
On our aggregate score, Codex Mini (Latest) is #424 of 743 ranked models, around the middle of the table. Its score is 47.5; the scale is centred on 50, so it sits 2.5 points below the typical model. That beats 43% of the ranked field. Among the 88 ranked OpenAI models it is #53. The next one up is GPT-5.1 (Thinking, Low) at 47.5. The next one down is GPT-4.5 at 47.5.
Codex Mini (Latest), benchmark by benchmark
ARC-AGI-2 is a weak spot. Codex Mini (Latest) scores 1.3%, #71 of 87, behind 80% of the models measured. The leader, GPT-6 Astra (max), reaches 95.0%. It covers abstract reasoning, ARC Prize public eval set. The board median is 22.8%, so Codex Mini (Latest) is 21.5 points below it. Source: ARC Prize official leaderboard, captured 2026-10-13.
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Codex Mini (Latest) costs more than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on gpt-5.6-terra-xhigh (codex-harness) ($2.00) and Amazon.nova Premier v1:0 ($2.50).
Reading these numbers
The 1 score on this page comes from 1 source: ARC Prize 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
- #421 Claude Code + Sonnet 5 (47.5)
- #422 Grok Build + Grok 4.5 (47.5)
- #423 Meta-Llama-3-70B (47.5)
- #425 Qwen3-235b-a22b Instruct (25/07) (47.5)
- #426 Deepseek R1 (05/28) (47.5)
- #427 Gemini 1.5 Pro (47.5)
More from OpenAI
- GPT-6 Astra (max) (#2, 64.0)
- GPT-6.1 Sol (max) (#5, 60.6)
- GPT-5.6 Sol (max) (#6, 60.1)
- GPT-6 Sol (max) (#7, 60.0)
- GPT-5.5 (xhigh) (#11, 58.0)
- GPT-5.6 Terra (max) (#12, 57.8)
Compare it on the live leaderboard → · How the aggregate score works