Sign in

Vals Index

As of Nov 3, 2026, Vals Index (v2.2) is maintained by Vals AI. Metric accuracy (%). Ceiling 100. Saturation unknown. Contamination risk low.

Maintainer
Vals AI
Metric
accuracy (%)
Ceiling
100
Saturation
unknown
Contamination
low
Cadence
Declared cadence: as Vals updates (checked daily). Catalog snapshots: 1, latest Nov 3, 2026.
Source
Vals AI · this benchmark on Vals AI
Grading
Composite of Vals benchmarks (mixed grading) — GDP-weighted composite of Vals tasks. Its coding bucket includes Terminal-Bench and its legal bucket includes Harvey's Legal Agent Benchmark, so it is not purely proprietary.

Source: Vals AI. A proprietary private test set run by Vals; scores are republished with permission. Rows are dated the day isitsota first saw them, and only the benchmark's standard harness counts.

Categories

Where it counts

Top 5

Current top scores

  1. Claude Sonnet 5.5 · 70.854 · Nov 3, 2026
  2. Gemini 4 Carbon · 70.45 · Nov 3, 2026
  3. Claude Opus 5.5 · 70.177 · Nov 3, 2026
  4. Gemini 4 Argon · 69.237 · Nov 3, 2026
  5. Muse Wonder Full · 66.787 · Nov 3, 2026
ModelScoreDateKind
Claude Sonnet 5.570.8542026-11-03snapshot
Claude Opus 5.570.1772026-11-03snapshot
Gemini 4 Argon69.2372026-11-03snapshot
Muse Wonder Full66.7872026-11-03snapshot
GPT-6 Astra65.0232026-11-03snapshot
Muse Wonder64.8772026-11-03snapshot
GPT-6.1 Sol63.9442026-11-03snapshot
DeepSeek V4.1 Flash 101761.2572026-11-03snapshot
GLM 5.359.7292026-11-03snapshot
Claude Haiku 5.558.7272026-11-03snapshot
Grok 4.758.5642026-11-03snapshot
Mimo V2.6 Pro57.8132026-11-03snapshot
Gemini 3.8 Flash55.9512026-11-03snapshot
Mimo V2.6 Flash54.8262026-11-03snapshot
MiniMax M3.1 Flash53.7812026-11-03snapshot
Hy4 Preview53.2092026-11-03snapshot
DeepSeek V4 Pro 081352.9742026-11-03snapshot
Kimi K352.9552026-11-03snapshot
GPT-6 Luna52.3222026-11-03snapshot
GLM 5.3 Flash50.8612026-11-03snapshot
Inkling28.9612026-11-03snapshot
Inkling Small27.5882026-11-03snapshot
Muse Spark Open48.5672026-11-03snapshot
Mercury 343.6592026-11-03snapshot
Kimi K3.1 Pro62.522026-11-03snapshot
GPT-6.1 Terra60.5362026-11-03snapshot
Gemini 4 Carbon70.452026-11-03snapshot
Step 5 Preview54.7622026-11-03snapshot