All documented models
11 public models with source-linked specifications, provider pricing, and benchmark records.
Ranked by raw score for OSWorld-Verified · v. Versions are kept separate.
| Model | Creator | Raw benchmark score | Modalities | Context | Input / 1M | Output / 1M | Released | |
|---|---|---|---|---|---|---|---|---|
| Claude Fable 5anthropic/claude-fable-5 | 85.0 | Image, Pdf, Text | 1M | $3.000 | $18.000 | 2026-06-09 | ||
| Claude Opus 4.8anthropic/claude-opus-4-8 | 83.4 | Image, Pdf, Text | 1M | $0.425 | $2.125 | 2026-05-28 | ||
| Claude Sonnet 5anthropic/claude-sonnet-5 | 81.2 | Image, Pdf, Text | 1M | $1.440 | $7.200 | 2026-06-30 | ||
| Muse Spark 1.1meta/muse-spark-1.1 | 80.8 | Image, Pdf, Text, Video | 1M | $1.250 | $4.250 | 2026-04-08 | ||
| GPT-5.5openai/gpt-5.5 | 78.7 | Image, Pdf, Text | 1.05M | $0.188 | $1.125 | 2026-04-23 | ||
| Claude Sonnet 4.6anthropic/claude-sonnet-4-6 | 78.5 | Image, Pdf, Text | 1M | $2.992 | $14.994 | 2026-02-17 | ||
| Gemini 3.5 Flashgoogle/gemini-3.5-flash | 78.4 | Audio, Image, Pdf, Text, Video | 1.04858M | $0.186 | $1.114 | 2026-05-19 | ||
| Claude Opus 4.7anthropic/claude-opus-4-7 | 78.0 | Image, Pdf, Text | 1M | $4.500 | $22.500 | 2026-04-16 | ||
| Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | 76.2 | Audio, Image, Pdf, Text, Video | 1.04858M | $2.000 | $12.000 | 2026-02-19 | ||
| GPT-5.4openai/gpt-5.4 | 75.0 | Image, Pdf, Text | 1.05M | $1.800 | $10.800 | 2026-03-05 | ||
| MiniMax-M3minimax/MiniMax-M3 | 70.06 | Image, Text, Video | 512K | $0.300 | $1.200 | 2026-06-01 |
Page 1 of 1