EXdeck Back to home
Model benchmarks

Choose the AI that fits your slide

Decks are generated with our balanced default, but you can regenerate any single slide with a different model — right-click a slide in the rail, or use the Regenerate button under the preview. Here’s how each model performs on a standardized single-slide task. Measured on 2026-07-11.

Speed
Average response latency — lower is faster.
Throughput
Output tokens per second — higher is faster.
Reliability
Share of runs returning valid JSON.
ModelLatencyTokens/secJSON reliabilityContext / Max outCredit rateBest for
Llama 3.3 70BDefault
Meta
1.09s149100%131k / 33k1.1×Balanced default — reliable quality for any deck
Llama 3.1 8B Instant
Meta
0.41s253100%131k / 131k0.5×Fastest & cheapest — quick drafts
Llama 4 Scout 17B
Meta
0.64s220100%131k / 8k1.2×Fast with the most token headroom
Qwen 3 32B
Qwen
1.16s361100%131k / 41k2×Strong reasoning, high throughput
Qwen 3.6 27B
Qwen
1.87s60%131k / 33k2×Multilingual prose (less reliable for strict JSON)
GPT-OSS 20B
OpenAI
1.06s510100%131k / 66k2.2×Highest throughput — premium quality
GPT-OSS 120B
OpenAI
1.16s291100%131k / 66k2.5×Largest open model — top quality

Credit rate multiplies the token-based cost of a generation/regeneration. Regeneration is charged by tokens used × the model’s rate; a longer slide costs more than a short one. Numbers are averages and vary with load and prompt size.

New: regenerate any slide with a different model

  1. 1. Open your deck in the editor.
  2. 2. Right-click a slide in the left rail, or use the Regenerate slide button under the preview.
  3. 3. Pick a model — the slide’s text, tables, and charts are rewritten with fresh, real data.
  4. 4. Credits are charged by tokens used × the model’s rate shown above.