Vals Index
A comprehensive large language model evaluation leaderboard published by Vals AI, ranking multiple models according to their measured capabilities across various benchmarks.
Core Facts
Timeline (last 90 days)
On the Vals Index, Argon ranks first and Opus ranks third.
Gemini 4 Argon ranks first on the independent Vals Index leaderboard with a composite score of 89.4%, surpassing Anthropic Claude 4.5 Opus (85.2%) and OpenAI o1 (84.1%).
Vals Index is a comprehensive index launched by the independent evaluation organization Vals AI, which weights and aggregates results from multiple task categories such as finance, programming, law and tax into a single score, without relying on vendor self-reported data.
The evaluation methods of leaderboards like Vals Index mostly focus on short outputs or medium-length outputs, with a single output rarely exceeding a few thousand tokens, so the capability for million-token outputs is hard to directly reflect in leaderboard scores.
Vals Index is a comprehensive large-model evaluation leaderboard, typically covering multi-dimensional tasks such as reasoning, knowledge, programming, and mathematics, and giving rankings in the form of weighted scores.
On the Vals Index as of October 12, Argon leads with 68.90%, ahead of Sonnet 5.5's 67.04% and Opus 5.5's 66.97%.
Gemini 4 Argon scored 91% on LV Bench (video/long-content understanding), setting a new record.
On the VALS Knowledge Task Index, Gemini 4 Argon scored 68.9%, reaching the top of SOTA and surpassing Opus 5.5's 67%.
All Facts (7)
Gemini 4 Argon scored 91% on LV Bench (video/long-content understanding), setting a new record.
70%UnverifiedOn the Vals Index, Argon ranks first and Opus ranks third.
50%UnverifiedGemini 4 Argon ranks first on the independent Vals Index leaderboard with a composite score of 89.4%, surpassing Anthropic Claude 4.5 Opus (85.2%) and OpenAI o1 (84.1%).
50%UnverifiedVals Index is a comprehensive index launched by the independent evaluation organization Vals AI, which weights and aggregates results from multiple task categories such as finance, programming, law and tax into a single score, without relying on vendor self-reported data.
50%UnverifiedThe evaluation methods of leaderboards like Vals Index mostly focus on short outputs or medium-length outputs, with a single output rarely exceeding a few thousand tokens, so the capability for million-token outputs is hard to directly reflect in leaderboard scores.
50%UnverifiedVals Index is a comprehensive large-model evaluation leaderboard, typically covering multi-dimensional tasks such as reasoning, knowledge, programming, and mathematics, and giving rankings in the form of weighted scores.
50%UnverifiedOn the Vals Index as of October 12, Argon leads with 68.90%, ahead of Sonnet 5.5's 67.04% and Opus 5.5's 66.97%.
50%