GPT-6.1-Terra Coding Benchmark
How GPT-6.1-Terra 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-6.1-Terra was tested at 4 effort levels, each ranked separately.
Last evaluated: 5 days ago (November 5, 2026), with Codex CLI.
| # | Model | Total points (max 90) |
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) |
Python Code Quality
(max 20) |
Edge-case Testing (4 projects, max 20) |
||||||||
| 1 | Opus 5.5 (High) | 85.43 | $0.83 | 03:42 |
Claude Code |
18.68 | 19 | 9.58 | 18.17 | 20 | 0 | |
| 2 | GPT-6-Astra (High) | 84.82 | $0.96 | 04:34 |
Codex CLI |
18.6 | 18.17 | 9.58 | 18.47 | 20 | 0 | |
| 3 | GPT-6-Astra (Medium) | 84.53 | $0.69 | 03:08 |
Codex CLI |
18.2 | 17.83 | 10 | 18.5 | 20 | 0 | |
| ⋯ 6 places not shown ⋯ | ||||||||||||
| 10 | Opus 5.5 (Low) | 78.2 | $0.37 | 01:21 |
Claude Code |
17.37 | 18.17 | 6.46 | 18.1 | 18.5 | −0.40 | |
| 11 | Fable 5.1 (Medium) | 77.53 | $1.53 | 03:06 |
Claude Code |
18.55 | 16.83 | 7.4 | 16.5 | 18.25 | 0 | |
| 12 | Deepseek-V4.1-Flash-1017 (Max) | 77.2 | N/A | 04:58 |
DeepSeek Harness |
18.07 | 18.67 | 8.96 | 16.5 | 15.5 | −0.50 | |
| 13 | GPT-6.1-Terra (Max) | 77.11 | $0.27 | 07:55 |
Codex CLI |
17.82 | 18.17 | 7.92 | 16.7 | 16.5 | 0 | |
| 14 | Deepseek-V4.1-Flash-1017 (Max) | 76.74 | $0.07 | 07:09 |
OpenCode |
17.42 | 18.17 | 8.13 | 16.27 | 17.25 | −0.50 | |
| 15 | Sonnet 5.5 (Medium) | 76.67 | $0.20 | 00:58 |
Claude Code |
17.88 | 18.33 | 7.08 | 16.63 | 17.25 | −0.50 | |
| 16 | Kimi K3.1 Pro (High) | 76.26 | $0.25 | 05:23 |
OpenCode |
17.7 | 17.33 | 7.71 | 17.8 | 17.25 | −1.53 | |
| ⋯ 3 places not shown ⋯ | ||||||||||||
| 20 | GPT-6-Luna (Max) | 73.6 | $0.03 | 11:03 |
Codex CLI |
18.12 | 17.17 | 7.08 | 16.03 | 16.7 | −1.50 | |
| 21 | SWE-2 (Max) | 73.3 | N/A | 11:59 |
Devin |
17.5 | 17.83 | 7.29 | 16.73 | 14.45 | −0.50 | |
| 22 | Grok 4.6 (High) | 72.28 | $0.77 | 09:19 |
Cursor |
17.4 | 18 | 6.56 | 15.57 | 14.75 | 0 | |
| 23 | GPT-6.1-Terra (Xhigh) | 72.13 | $0.07 | 01:29 |
Codex CLI |
16.23 | 17.5 | 8.96 | 15.57 | 14.4 | −0.53 | |
| 24 | Gemini 4 Argon (High) | 72.01 | N/A | 09:41 |
Devin |
17.15 | 18.5 | 7.19 | 15.17 | 14.25 | −0.25 | |
| 25 | Deepseek-V4.1-Flash-1017 (High) | 70.86 | $0.03 | 03:13 |
OpenCode |
17.98 | 16.83 | 6.15 | 16.7 | 14.25 | −1.05 | |
| 26 | GPT-6-Luna (Xhigh) | 70.85 | $0.03 | 10:08 |
Codex CLI |
17.02 | 17.17 | 6.46 | 16 | 15.75 | −1.55 | |
| 27 | MiniMax M3.1-Flash (Max) | 70.49 | N/A | 15:42 |
OpenCode |
17.44 | 17 | 4.79 | 16.9 | 15.25 | −0.89 | |
| 28 | GLM-5.3 (High) | 69.99 | $0.19 | 04:58 |
OpenCode |
17.55 | 17.67 | 4.9 | 16.27 | 14.7 | −1.10 | |
| 29 | Qwen 3.8 Max (0902) (High) | 69.99 | $0.40 | 11:49 |
OpenCode |
17.75 | 18 | 4.69 | 17.7 | 12.95 | −1.10 | |
| 30 | GPT-6.1-Terra (High) | 69.59 | $0.05 | 00:46 |
Codex CLI |
16.12 | 16.17 | 8.13 | 14.77 | 14.4 | 0 | |
| 31 | SWE-2 Flash (High) | 68.55 | N/A | 11:29 |
Devin |
17.4 | 17.33 | 4.17 | 17.4 | 13 | −0.75 | |
| 32 | GPT-6.1-Terra (Medium) | 68.5 | $0.04 | 00:31 |
Codex CLI |
16.28 | 16.17 | 7.71 | 15.67 | 14.45 | −1.78 | |
| 33 | MiMo-V2.6 Pro (High) | 68.44 | $0.09 | 15:04 |
OpenCode |
17.41 | 18 | 6.25 | 15.23 | 12.15 | −0.60 | |
| 34 | GPT-6-Luna (High) | 67.47 | $0.01 | 03:51 |
Codex CLI |
16.9 | 15.83 | 5.31 | 15.53 | 15 | −1.10 | |
| 35 | Qwen 3.8 Flash (Xhigh) | 67.47 | $0.04 | 08:38 |
OpenCode |
16.35 | 17.67 | 5.42 | 16.33 | 13.2 | −1.50 | |
Videos about GPT-6.1-Terra
I Tested NEW GPT-6.1 Terra on Coding. Better than Luna?
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.