Skip to main content

Vals Index v1.1 (Vals Index)

Vals AI composite benchmark across finance and coding tasks, including Finance Agent v2, CorpFin v2, SWE-bench, Terminal-Bench 2.0, and Vibe Code Bench.

How BenchLM shows Vals Index

BenchLM mirrors the public Vals AI Vals Index leaderboard captured from https://www.vals.ai/benchmarks/vals_index and updated by Vals on May 18, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Vals Index is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

17 Vals rows6 task viewsprivate datasetTasks: Overall, Finance Agent v2, CorpFin v2, SWE-bench, Terminal-Bench 2.0Display only

Vals Index score on Vals Index — May 18, 2026

BenchLM mirrors the published vals index score view for Vals Index. GPT-5.5 leads the public snapshot at 67.62% , followed by Claude Opus 4.7 (66.10%) and Gemini 3.5 Flash (62.05%). BenchLM does not use these results to rank models overall.

17 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated May 18, 2026

The published Vals Index snapshot is tightly clustered at the top: GPT-5.5 sits at 67.62%, while the third row is only 5.57 points behind. The broader top-10 spread is 18.31 points, so the benchmark still separates strong models even when the leaders cluster.

17 models have been evaluated on Vals Index. The benchmark falls in the External benchmark mirrors category. BenchLM tracks this category separately from its weighted global scoring system, so these results are best compared on the dedicated Korean benchmark views. Vals Index is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Vals Index

Year

2026

Tasks

Finance and coding components

Format

Composite score

Difficulty

Private economic-work benchmark composite

BenchLM mirrors Vals Index v1.1 as a display-only external composite. It is useful context for Vals' private benchmark suite, but it is not used as a BenchLM weighted ranking input.

BenchLM freshness & provenance

Version

Vals Index 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Vals Index score table (17 models)

1
GPT-5.5openai/gpt-5.5
67.62%
2
Claude Opus 4.7anthropic/claude-opus-4-7
66.10%
3
Gemini 3.5 Flashgoogle/gemini-3.5-flash
62.05%
4
Claude Sonnet 4.6anthropic/claude-sonnet-4-6
60.30%
5
DeepSeek V4 Prodeepseek/deepseek-v4-pro
56.23%
6
Kimi K2.6 Thinkingkimi/kimi-k2.6-thinking
55.55%
7
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview
53.42%
8
GLM 5.1 Thinkingzai/glm-5.1-thinking
52.14%
9
GPT-5.4 Miniopenai/gpt-5.4-mini-2026-03-17
51.42%
10
Gemini 3 Flash Previewgoogle/gemini-3-flash-preview
49.31%
11
Qwen3.6 Plusalibaba/qwen3.6-plus
48.04%
12
Grok 4.3grok/grok-4.3
46.63%
13
GPT-5.4 Nanoopenai/gpt-5.4-nano-2026-03-17
46.46%
14
MiniMax M2.7minimax/MiniMax-M2.7
41.41%
15
Claude Haiku 4.5 20251001 Thinkinganthropic/claude-haiku-4-5-20251001-thinking
40.33%
16
Grok 4.20 0309 Reasoninggrok/grok-4.20-0309-reasoning
39.11%
17
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview
35.24%

FAQ

What does Vals Index measure?

Vals AI composite benchmark across finance and coding tasks, including Finance Agent v2, CorpFin v2, SWE-bench, Terminal-Bench 2.0, and Vibe Code Bench.

Which model leads the published Vals Index snapshot?

GPT-5.5 currently leads the published Vals Index snapshot with 67.62% vals index score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Vals Index?

17 AI models are included in BenchLM's mirrored Vals Index snapshot, based on the public leaderboard captured on May 18, 2026.

Last updated: May 18, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.