Skip to main content

Vals Multimodal Index v1.1 (Vals Multimodal Index)

Vals AI multimodal composite across finance, coding, education, and mortgage-tax task families.

How BenchLM shows Vals Multimodal Index

BenchLM mirrors the public Vals AI Vals Multimodal Index leaderboard captured from https://www.vals.ai/benchmarks/vals_multimodal_index and updated by Vals on May 19, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Vals Multimodal 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.

14 Vals rows8 task viewsprivate datasetTasks: Overall, Finance Agent v2, CorpFin v2, SWE-bench, Terminal-Bench 2.0Display only

Vals Multimodal Index score on Vals Multimodal Index — May 19, 2026

BenchLM mirrors the published vals multimodal index score view for Vals Multimodal Index. GPT-5.5 leads the public snapshot at 67.77% , followed by Claude Opus 4.7 (67.36%) and Gemini 3.5 Flash (62.29%). BenchLM does not use these results to rank models overall.

14 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated May 19, 2026

The published Vals Multimodal Index snapshot is tightly clustered at the top: GPT-5.5 sits at 67.77%, while the third row is only 5.48 points behind. The broader top-10 spread is 20.28 points, so the benchmark still separates strong models even when the leaders cluster.

14 models have been evaluated on Vals Multimodal 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 Multimodal Index is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Vals Multimodal Index

Year

2026

Tasks

Finance, coding, education, and mortgage-tax components

Format

Composite score

Difficulty

Private multimodal economic-work benchmark composite

BenchLM mirrors the Vals Multimodal Index as a display-only external composite with task-level component scores preserved in the Vals snapshot.

BenchLM freshness & provenance

Version

Vals Multimodal 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 Multimodal Index score table (14 models)

1
GPT-5.5openai/gpt-5.5
67.77%
2
Claude Opus 4.7anthropic/claude-opus-4-7
67.36%
3
Gemini 3.5 Flashgoogle/gemini-3.5-flash
62.29%
4
Claude Sonnet 4.6anthropic/claude-sonnet-4-6
60.78%
5
Kimi K2.6 Thinkingkimi/kimi-k2.6-thinking
56.79%
6
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview
55.75%
7
GPT-5.4 Miniopenai/gpt-5.4-mini-2026-03-17
53.30%
8
Gemini 3 Flash Previewgoogle/gemini-3-flash-preview
51.98%
9
Qwen3.6 Plusalibaba/qwen3.6-plus
50.74%
10
GPT-5.4 Nanoopenai/gpt-5.4-nano-2026-03-17
47.48%
11
Grok 4.3grok/grok-4.3
43.44%
12
Claude Haiku 4.5 20251001 Thinkinganthropic/claude-haiku-4-5-20251001-thinking
42.35%
13
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview
40.47%
14
Grok 4.20 0309 Reasoninggrok/grok-4.20-0309-reasoning
38.70%

FAQ

What does Vals Multimodal Index measure?

Vals AI multimodal composite across finance, coding, education, and mortgage-tax task families.

Which model leads the published Vals Multimodal Index snapshot?

GPT-5.5 currently leads the published Vals Multimodal Index snapshot with 67.77% vals multimodal index score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Vals Multimodal Index?

14 AI models are included in BenchLM's mirrored Vals Multimodal Index snapshot, based on the public leaderboard captured on May 19, 2026.

Last updated: May 19, 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.