GPT-6-Luna Coding Benchmark
How GPT-6-Luna ranks on the LLM Coding Leaderboard, shown next to the three models directly above and below it, with the top three models included for reference. GPT-6-Luna was tested at 4 effort levels, each ranked separately.
Last evaluated: 1 month ago (October 1, 2026), with Codex CLI.
| # | Model | Total points (max 70) |
Avg cost per prompt |
Avg time per prompt |
Video | Tested with | Points per project | Consistency penalty | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
Laravel Code Quality
(max 20) |
React-TS Code Quality
(max 20) |
Bug Finding Test
(max 10) |
Edge-case Testing (4 projects, max 20) |
||||||||
| 1 | Opus 5.5 (High) | 67.26 | $0.83 | 03:42 |
Claude Code |
18.68 | 19 | 9.58 | 20 | 0 | |
| 2 | GPT-6-Astra (High) | 66.35 | $0.96 | 04:34 |
Codex CLI |
18.6 | 18.17 | 9.58 | 20 | 0 | |
| 3 | GPT-6-Astra (Medium) | 66.03 | $0.69 | 03:08 |
Codex CLI |
18.2 | 17.83 | 10 | 20 | 0 | |
| ⋯ 13 places not shown ⋯ | |||||||||||
| 17 | Haiku 5.5 (High) | 59.03 | $0.05 | 03:37 |
Claude Code |
17.3 | 18 | 7.08 | 17.25 | −0.60 | |
| 18 | Kimi K3.1 Pro (High) | 58.46 | $0.25 | 05:23 |
OpenCode |
17.7 | 17.33 | 7.71 | 17.25 | −1.53 | |
| 19 | Haiku 5.5 (Medium) | 58.2 | $0.03 | 02:37 |
Claude Code |
17.32 | 17 | 6.88 | 17 | 0 | |
| 20 | GPT-6-Luna (Max) | 57.57 | $0.03 | 11:03 |
Codex CLI |
18.12 | 17.17 | 7.08 | 16.7 | −1.50 | |
| 21 | Gemini 4 Argon (High) | 57.09 | N/A | 09:41 |
Devin |
17.15 | 18.5 | 7.19 | 14.25 | 0 | |
| 22 | GPT-6.1-Terra (Xhigh) | 57.01 | $0.07 | 01:29 |
Codex CLI |
16.23 | 17.5 | 8.96 | 14.4 | −0.08 | |
| 23 | Grok 4.6 (High) | 56.71 | $0.77 | 09:19 |
Cursor |
17.4 | 18 | 6.56 | 14.75 | 0 | |
| 24 | SWE-2 (Max) | 56.57 | N/A | 11:59 |
Devin |
17.5 | 17.83 | 7.29 | 14.45 | −0.50 | |
| 25 | GPT-6-Luna (Xhigh) | 54.9 | $0.03 | 10:08 |
Codex CLI |
17.02 | 17.17 | 6.46 | 15.75 | −1.50 | |
| 26 | GPT-6.1-Terra (High) | 54.82 | $0.05 | 00:46 |
Codex CLI |
16.12 | 16.17 | 8.13 | 14.4 | 0 | |
| 27 | Deepseek-V4.1-Flash-1017 (High) | 54.71 | $0.03 | 03:13 |
OpenCode |
17.98 | 16.83 | 6.15 | 14.25 | −0.50 | |
| 28 | GLM-5.3 (High) | 54.32 | $0.19 | 04:58 |
OpenCode |
17.55 | 17.67 | 4.9 | 14.7 | −0.50 | |
| ⋯ 2 places not shown ⋯ | |||||||||||
| 31 | MiMo-V2.6 Pro (High) | 53.31 | $0.09 | 15:04 |
OpenCode |
17.41 | 18 | 6.25 | 12.15 | −0.50 | |
| 32 | Qwen 3.8 Max (0902) (High) | 52.89 | $0.40 | 11:49 |
OpenCode |
17.75 | 18 | 4.69 | 12.95 | −0.50 | |
| 33 | Qwen 3.8 Flash (Max) | 52.14 | $0.04 | 08:38 |
OpenCode |
16.35 | 17.67 | 5.42 | 13.2 | −0.50 | |
| 34 | GPT-6-Luna (High) | 52.04 | $0.01 | 03:51 |
Codex CLI |
16.9 | 15.83 | 5.31 | 15 | −1.00 | |
| 35 | SWE-2 Flash (High) | 51.15 | N/A | 11:29 |
Devin |
17.4 | 17.33 | 4.17 | 13 | −0.75 | |
| 36 | MiMo-V2.6 Flash (High) | 50.79 | $0.04 | 17:56 |
OpenCode |
17.83 | 17.5 | 7.81 | 10.15 | −2.50 | |
| 37 | Muse Spark 1.3 (Xhigh) | 50.37 | N/A | 06:51 |
OpenCode |
15.9 | 16.67 | 6.15 | 12.65 | −1.00 | |
| ⋯ 6 places not shown ⋯ | |||||||||||
| 44 | Qwen 3.8 27B (Xhigh) | 45.26 | $0.45 | 23:22 |
OpenCode |
17.23 | 15.67 | 2.71 | 12.15 | −2.50 | |
| 45 | GLM-5.3-Flash (Max) | 45.01 | $0.02 | 08:54 |
OpenCode |
17.2 | 17.17 | 4.69 | 8.45 | −2.50 | |
| 46 | LongCat-2.5-Preview | 44.65 | N/A | 16:50 |
OpenCode |
16.98 | 16.67 | 2.4 | 10.6 | −2.00 | |
| 47 | GPT-6-Luna (Medium) | 42.54 | $0.01 | 02:13 |
Codex CLI |
16.33 | 14.17 | 3.54 | 9.7 | −1.20 | |
| 48 | Beam (Max) | 41.76 | N/A | 01:38 |
OpenCode |
15.7 | 15.33 | 2.08 | 10.15 | −1.50 | |
| 49 | Gemini-3.1-Pro | 41.36 | $0.52 | 03:04 |
OpenCode |
12.55 | 15.33 | 4.38 | 10.1 | −1.00 | |
| 50 | Composer 2.5 | 39.89 | $0.10 | 02:41 |
Cursor |
16 | 15.83 | 3.96 | 5.6 | −1.50 | |
Videos about GPT-6-Luna
Video
· Sep 24, 2026
I Tested NEW GPT-6-Sol and GPT-6-Luna on 144 Coding Prompts
How to read this
- Each score measures a model-and-harness configuration, not the model in isolation.
- Prices are calculated with API costs. Models tested on a subscription plan show N/A.
- Full methodology and scoring formulas are explained in this article.
See every tested model side by side on the full LLM Coding Leaderboard.
