Model rankings
What models real apps run in production. Measured from every metered run across hosted SkillSafe apps over the last 30 days — 394 runs — not benchmarks. Updated several times a day.
| # | Model | Provider | Runs (30d) | Apps | Success | Share |
|---|---|---|---|---|---|---|
| 1 | Gemma 4 26B (Workers AI) @cf/google/gemma-4-26b-a4b-it | Workers AI | 197 | 2 | 100.0% | |
| 2 | Qwen 3.8 27B (Workers AI) @cf/qwen/qwen3.8-27b | Workers AI | 51 | 1 | 100.0% | |
| 3 | GPT-6 Sol gpt-6-sol | OpenAI | 44 | 1 | 100.0% | |
| 4 | FLUX.2 Klein 4B (Workers AI) @cf/black-forest-labs/flux-2-klein-4b | Workers AI | 34 | 2 | 79.4% | |
| 5 | Deepgram Aura 2 English (Workers AI) @cf/deepgram/aura-2-en | Workers AI | 26 | 1 | 100.0% | |
| 6 | workflow workflow | Anthropic | 12 | 5 | 91.7% | |
| 7 | GPT Image 2.5 Flare gpt-image-2.5-flare | OpenAI | 11 | 1 | 54.5% | |
| 8 | GPT-5.6 Terra gpt-5.6-terra | OpenAI | 8 | 4 | 100.0% | |
| 9 | MeloTTS (Workers AI) @cf/myshell-ai/melotts | Workers AI | 6 | 1 | 100.0% | |
| 10 | FLUX.1 Schnell (Workers AI) @cf/black-forest-labs/flux-1-schnell | Workers AI | 2 | 1 | 100.0% | |
| 11 | Kimi K2.6 (Workers AI) @cf/moonshotai/kimi-k2.6 | Workers AI | 1 | 1 | 100.0% | |
| 12 | FLUX.2 Klein 9B (Workers AI) @cf/black-forest-labs/flux-2-klein-9b | Workers AI | 1 | 1 | 100.0% | |
| 13 | Llama 3.3 70B fp8-fast (Workers AI) @cf/meta/llama-3.3-70b-instruct-fp8-fast | Workers AI | 1 | 1 | 100.0% |
Aggregates only — no per-app or per-user figures. Data as of 2026-10-08.
How this is measured
- Production runs, not benchmarks. Every row is built from metered runs that real apps executed and real users paid for over a trailing 30-day window.
- Runs count toward the model that actually executed them. An app's configured model gets the credit unless the user overrode it — model aliases resolve to the concrete model that ran.
- Success rate is the share of terminal runs that completed rather than failed (timeouts and provider errors count as failures; in-flight runs are excluded).