We put Kimi K3, GLM 5.3, Qwen3.8 Max and DeepSeek V4 Pro 0813 against each other across four one-shot coding tests, all run on EmpirioLabs. Same prompt each, one attempt, no edits or retries, and every result rendered live in a real browser.
Watch the four way comparison
Specs at a glance
| Kimi K3 | GLM 5.3 | Qwen3.8 Max | DeepSeek V4 Pro 0813 | |
|---|---|---|---|---|
| Maker | Moonshot AI | Z.ai | Alibaba | DeepSeek |
| Context window | 1,000,000 tokens | 1,000,000 tokens | 1,000,000 tokens | 1,000,000 tokens |
| Input | Text, images and video | Text | Text, images and video | Text |
| Reasoning control | reasoning_effort, low to max | reasoning_effort, low to max | reasoning_effort, none to max | reasoning_effort, none to max |
| Structured output | Strict JSON Schema | JSON mode | Strict JSON Schema | Strict JSON Schema |
| Input price | $3.00 per 1M tokens | $1.40 per 1M tokens | $2.00 per 1M tokens | $1.32 per 1M tokens |
| Output price | $15.00 per 1M tokens | $4.40 per 1M tokens | $6.00 per 1M tokens | $3.96 per 1M tokens |
How we ran it
Each model received the identical prompt for four tasks: a maze that generates and then solves itself with an animated A* search, a falling-sand simulation, an ocean sunset with a sailboat riding the waves, and rain running down a window at night. Every task asked for a single self-contained HTML file with no external libraries. All four models ran at reasoning_effort: "max" with a 65,536 token output budget, one shot, no retries. The line counts and tokens-per-second readouts on each panel are measured from the real API calls, and each result is the file the model returned, rendered as-is.
What to look for
DeepSeek V4 Pro 0813 returned its files fastest, at about 100 tokens per second. Qwen3.8 Max wrote the longest files, about 540 lines on average, and Kimi K3 the most compact, about 360. GLM 5.3 used the most output tokens, about 47,000 per task including its reasoning. Watch how each model animates the maze search, piles the sand, moves the waves and merges the raindrops. We are not declaring a winner. Run the clip and judge the outputs for your own use case.
Run the same test on EmpirioLabs
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3",
"reasoning_effort": "max",
"messages": [{"role": "user", "content": "Build a maze that generates and solves itself in a single HTML file."}]
}'Swap model to glm-5-3, qwen3-8-max or deepseek-v4-pro-0813 to run the same request against the others, or try them interactively in the playground.
Frequently asked questions
Were the results edited or retried?
No. Each model got one attempt per task with the identical prompt, and the rendered result is exactly the file it returned.
Why max reasoning?
A fair head to head shows each model at its best. All four expose a reasoning_effort control on EmpirioLabs, so all four ran at the highest setting.
Which model should I use?
DeepSeek V4 Pro 0813 has the lowest per-token price of the four and answered the quickest here. Kimi K3 and Qwen3.8 Max accept images and video as well as text. GLM 5.3 sits close to DeepSeek on price. Run your own workload against each before deciding.
