LLM Coding Leaderboard
Last update: July 8th, 2026
Results are based on 5 different PHP/Laravel/React projects from my YouTube channel over the last weeks.
| # | Model | Total points (max 25) |
Avg time per prompt |
Avg cost per prompt |
Tested with | Points per project (max 5) | ||||
|---|---|---|---|---|---|---|---|---|---|---|
| Filament | API | Fluent | React | CSV Import | ||||||
| 1 | Opus 4.8 (Medium) | 24.5 | 02:00 | $0.74 | Claude Code | 5 | 5 | 5 | 5 | 4.5 |
| 2 | GPT-5.5 (Medium) | 24.5 | 04:00 | $1.22 | Codex CLI | 5 | 5 | 5 | 5 | 4.5 |
| 3 | GPT-5.4 (Medium) | 21.5 | 03:56 | $0.47 | Codex CLI | 5 | 5 | 3 | 5 | 3.5 |
| 4 | GPT-5.4-Mini (Medium) | 20.7 | 03:58 | $0.18 | Codex CLI | 5 | 3 | 5 | 5 | 2.7 |
| 5 | Kimi K2.7 Code | 20 | 05:36 | $0.37 | OpenCode | 3 | 4 | 5 | 5 | 3 |
| 6 | Composer 2.5 | 19.2 | 01:42 | $0.17 | Cursor | 3 | 5 | 5 | 4 | 2.2 |
| 7 | Gemini-3.5-Flash (High) | 19 | 04:33 | $1.13 | OpenCode | 5 | 5 | 3 | 5 | 1 |
| 8 | Gemini-3.1-Pro | 18.9 | 02:01 | $0.35 | OpenCode | 3 | 5 | 4 | 5 | 1.9 |
| 9 | Minimax M3 | 18.5 | 08:11 | $0.31 | OpenCode | 3 | 4 | 3 | 5 | 3.5 |
| 10 | GLM-5.2 | 17.7 | 05:28 | $0.27 | OpenCode | 5 | 5 | 1 | 4 | 2.7 |
| 11 | Sonnet 5 (Medium) | 16.5 | 02:01 | $0.72 | Claude Code | 0 | 4 | 3 | 5 | 4.5 |
| 12 | Sonnet 4.6 (Medium) | 16.4 | 02:41 | $0.49 | Claude Code | 3 | 4 | 3 | 5 | 1.4 |
| 13 | MiMo 2.5 Pro | 15.4 | 03:53 | $0.16 | OpenCode | 3 | 2 | 4 | 4 | 2.4 |
| 14 | Kimi K2.6 | 15.1 | 04:22 | $0.18 | OpenCode | 4 | 3 | 3 | 4 | 1.1 |
| 15 | Deepseek-V4-Flash (High) | 13.9 | 01:54 | $0.01 | OpenCode | 1 | 4 | 2 | 4 | 2.9 |
| 16 | Qwen 3.7 Max | 11.7 | 06:38 | $0.40 | OpenCode | 0 | 4 | 2 | 3 | 2.7 |
| 17 | Deepseek-V4-Pro (High) | 11.2 | 03:35 | $0.09 | OpenCode | 0 | 4 | 3 | 2 | 2.2 |
| 18 | Tencent Hy3 (High) | 10.4 | 01:54 | $0.00 | OpenCode | 0 | 3 | 2 | 4 | 1.4 |
| 19 | Qwen 3.7 Plus | 8.3 | 03:41 | $0.06 | OpenCode | 2 | 4 | 1 | 0 | 1.3 |
Support Leaderboard Updates
Running dozens of prompts on multiple projects with different LLMs is costly.
So, if you want to support my mission and help keep the leaderboard updated with new models/variants, subscribe to Premium membership of AI Coding Daily.
Explanations
- Prices are calculated with API costs
- GPT/Opus were tested only on Medium effort: it was enough to get top spots, High effort wasn't needed
Updates
- July 8th: added Tencent Hy3
- July 1st: added Sonnet 5
- June 24th: added GPT-5.4-Mini and Gemini-3.5-Flash
- June 23rd: added 5th benchmark project, removed Opus 4.7 and GLM-5.1, added GPT-5.4
- June 17th: added GLM-5.2
- June 13th: added Kimi-K2.7-Code
- June 5th: added Deepseek v4 Flash and removed Minimax M2.7
- June 4th: added Qwen 3.7 Plus
- June 2nd: added Qwen 3.7 Max and "Tested with" column
- June 2nd: added Minimax M3
- May 30th: added Avg Cost for all LLMs (based on API pricing)
- May 29th: added Claude Opus 4.8
- May 24th: added 4th benchmark project - for React/TypeScript
- May 20th: added Composer 2.5
Explanation / Methodology
Each prompt was launched 5 times on the same project, making it total of 25 points max.
For all evaluation tests passing, LLM got 1 point for the task. If at least one test failed, LLM got 0 points for that task.
So this above is the summary table.
I will continue testing models constantly - will come up with new tasks for evaluation, and will update when new LLMs are released.
