VIALS-AA launches: Sol/Terra hit near-frontier scores at ~1/20th the cost per task of rivals
ArtificialAnlys · x · 2026-11-07
Artificial Analysis launched VIALS-AA, a leaderboard for Handshake AI's VIALS benchmark for visual reasoning in life sciences and biotech (161 tasks across 8 domains, reasoning over artifacts like gel blots). The headline finding is a massive cost spread:
- GPT-6.1 Sol scores 59% at $0.056 per task; GPT-6.1 Terra scores 60% at $0.073
- Compared with Sol, GPT-6 Astra reaches 63% at 5× the cost, Gemini 4 Carbon 64% at 23×, and Claude Opus 5.5 (max with fallback) 61% at 29×
The implication: mid-tier models now deliver near-frontier visual reasoning at a tiny fraction of the price, making cost-per-task a metric as important as raw score.
More from Models
- Inkling 2S matches Dots3 on ARC but costs roughly 3.5x more — teortaxesTex · 2026-11-07
- Open ASR Leaderboard adds private Egypt and Nigeria conversational data for accent breakdown — andimarafioti · 2026-11-07
- Users say Claude Opus 5.5 remains unmatched a month after release — prasenx · 2026-11-07
- Ripple-65B Preview: Apache 2.0 open US model tops TerminalBench 2.1 with $32M R&D — The Decoder · 2026-11-07
- Mirage: A 22MB VLM Runs Detection, OCR and Segmentation in One Pass at 74ms on Phone NPU — Henrie_the_dreamer · 2026-11-07
- 4B Nemotron 3 Nano claimed to beat frontier models on task-specific workflows — eliano · 2026-11-07