gpt-5.6-luna-xhigh (codex-harness): benchmark scores, price and ranking
gpt-5.6-luna-xhigh (codex-harness) from OpenAI ranks #453 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.2), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- OpenAI
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-07-09 (source: epoch)
- Cheapest API price
- $0.200 in / $1.20 out per million tokens (via aihubmix, observed 2026-10-13T20:47Z)
- Aggregate rank
- #453 of 743 (score 47.2)
Across the 1 benchmark where at least ten models are scored, gpt-5.6-luna-xhigh (codex-harness) is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $0.200 per million tokens, is lower than that of 67% of the 427 models with a listed price.
gpt-5.6-luna-xhigh (codex-harness) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| LMArena Code Elo | 1,518 | #27 of 30 | LMArena | 2026-10-06 |
About gpt-5.6-luna-xhigh (codex-harness)
gpt-5.6-luna-xhigh (codex-harness) is a frontier model from OpenAI. It was released on 2026-07-09, according to Epoch AI. The cheapest API listing we track charges $0.200 per million input tokens and $1.20 per million output tokens, through aihubmix. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where gpt-5.6-luna-xhigh (codex-harness) stands
On our aggregate score, gpt-5.6-luna-xhigh (codex-harness) is #453 of 743 ranked models, in the lower half. Its score is 47.2; the scale is centred on 50, so it sits 2.8 points below the typical model. That beats 39% of the ranked field. Among the 88 ranked OpenAI models it is #58. The next one up is gpt-5.6-terra-xhigh (codex-harness) at 47.3. The next one down is GPT-4o at 47.2.
gpt-5.6-luna-xhigh (codex-harness), benchmark by benchmark
LMArena Code Elo is a weak spot. gpt-5.6-luna-xhigh (codex-harness) scores 1,518, #27 of 30, behind 87% of the models measured. The leader, Claude Opus 5.5 (max), reaches 1,814. It covers crowd-voted coding answers. The board median is 1,622, so gpt-5.6-luna-xhigh (codex-harness) is 104 points below it. Source: LMArena, captured 2026-10-06.
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so gpt-5.6-luna-xhigh (codex-harness) costs less 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-5.1 Codex Mini ($0.250) and DeepSeek-V3.1 ($0.250).
Release history
The OpenAI model released before it was GPT-5.6 Luna (max) on 2026-07-09, which scores 55.1. The next one was GPT-5.6 Sol (max) on 2026-07-09, at 60.1.
Reading these numbers
The 1 score on this page comes from 1 source: LMArena (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #450 Llama-3.2-3B-Instruct (47.2)
- #451 ollama/yi-coder:9b-chat-fp16 (47.2)
- #452 Codestral 25.01 (47.2)
- #454 seed-2.1-pro-preview (47.2)
- #455 MAmmoTH2-8x7B-Plus (47.2)
- #456 qwen3-30b-a3b-thinking-2507 (47.2)
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