Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | zoomzoom/scribe_v2_proRemove × | ideogramIdeogram V4.5 Text to ImageRemove × | abr-aiabr-ai/niagara-84m-batch.enRemove × |
|---|---|---|---|
| What’s different | 11 languages | Generate high-quality images, posters, and logos with Ideogram 4.5, with accurate text rendering and low, medium, or high quality tiers. | 0.084B parameters · 1 language · Encoder: State-space model · Decoder: CTC |
| Date | Oct 17, 2026Discovered | Sep 30, 2026Released | Oct 17, 2026Discovered |
API prices USD · provider configuration shown below | |||
| Listed rate | See provider quotes | See provider quotes | See provider quotes |
| Provider endpoints | 0 endpoints → | 1 endpoint → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Image ↗2.1 | Not reported | 1,015.07 ↗Text-to-image · all categories · quality=highIndependent result95% CI 1,000.07–1,030.07 · n=2,888 | Not reported |
| AMI-Cleaned WER ↗English short-form; normalization unversioned | 6.08% WER ↗zoom/scribe_v2_proLeaderboard entry | Not reported | 12.01% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | 4.12% WER ↗zoom/scribe_v2_proLeaderboard entry | Not reported | 10.83% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | 7.75% WER ↗zoom/scribe_v2_proLeaderboard entry | Not reported | 10.41% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | 1.11% WER ↗zoom/scribe_v2_proLeaderboard entry | Not reported | 3.09% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | 2.24% WER ↗zoom/scribe_v2_proLeaderboard entry | Not reported | 7.6% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | 1.36% WER ↗zoom/scribe_v2_proLeaderboard entry | Not reported | 2.61% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | 7.99% WER ↗zoom/scribe_v2_proLeaderboard entry | Not reported | 20.16% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | 3% WER ↗zoom/scribe_v2_proLeaderboard entry | Not reported | 8.82% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | 3.08% WER ↗zoom/scribe_v2_proLeaderboard entry | Not reported | 4.33% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
Specifications | |||
| Context window | — | — | — |
| Max output | — | — | — |
| Parameters | — | — | 0.084B |
| Audio input | Supported | Not reported | Supported |
| Transcription | Supported | Not reported | Supported |