BlogLLM Benchmark Scores as Published, Side by Side
Vals Index: Results as Published
Every result the catalog holds for Vals Index: 5 models from 3 developers, read from 2 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Knowledge WorkMaintainer Vals AIData version 2026103001, as of 2026-10-30
The Vals Index is a single composite score from Vals AI that averages agentic tasks in finance, coding, legal and tax work. Each sector is weighted by its share of US GDP, with finance carrying the most weight, and each sector score is the average of its benchmarks. The current version, 2.1, combines Finance Agent v2 and an Excel modeling benchmark for finance, Terminal-Bench 4.0, Vibe Code Bench and a code migration task for coding, and legal and tax benchmarks.
Vals Index
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 63.1% | Google, Gemini 4 Argonchecked 2026-10-29 | - |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 67% | Google, Gemini 4 Argonchecked 2026-10-29 | - |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 65.8% | Google, Gemini 4 Argonchecked 2026-10-29 | - |
| Gemini 4 ArgonGoogle, released 2026-09-30 | 68.9% | Google, Gemini 4 Argonchecked 2026-10-29 | - |
Vals Index v2.2
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 65% | Google, Gemini 4 Carbonchecked 2026-10-29 | - |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 70.2% | Google, Gemini 4 Carbonchecked 2026-10-29 | - |
| Gemini 4 CarbonGoogle, released 2026-10-28 | 70.4% | Google, Gemini 4 Carbonchecked 2026-10-29 | - |
| Gemini 4 ArgonGoogle, released 2026-09-30 | 69.2% | Google, Gemini 4 Carbonchecked 2026-10-29 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.