Vals AI launches multi-model cross-industry benchmark comparison platform
Understand this story
Vals AI launches a model comparison platform where users can select up to 7 models at once, aggregating scores on finance, coding, legal, tax, and other tasks into a GDP-weighted Vals Index. The leaderboard shows the highest Vals Index at 71.31%±0.96; model scores on Legal Research Bench range from 46.15% to 56.25%, and Terminal-Bench 4.0 ranges from 61.62% to 65.15%. These figures reflect each model's performance on the tasks set by the platform.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIVals AI – Compare AI models across real-world benchmarks
Vals AI presents a comparison of up to seven models across real-world benchmarks, including a GDP-weighted Vals Index spanning finance, coding, legal and tax, with per-benchmark scores and confidence intervals. The page also breaks down performance by industry, per-task and per-token pricing, and model metadata such as provider, latency, context window and input modality.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 10Nov 19 14:00
- Change in the past 24 hours
- -49%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.