Skip to main content

Benchmark profile

Vals Index v1.2 (Vals Index)

Vals AI composite benchmark across finance and coding tasks, including Finance Agent v2, CorpFin v2, SWE-bench, Terminal-Bench 2.1, and Vibe Code Bench.

Data verified

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 July 16, 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.

37 Vals rows6 task viewsprivate datasetTasks: Overall, Finance Agent v2, CorpFin v2, SWE-bench, Terminal-Bench 2.1Display only

Vals Index score on Vals Index — July 16, 2026

BenchLM mirrors the published vals index score view for Vals Index. Claude Fable 5 leads the public snapshot at 75.14% , followed by Kimi K3 (74.70%) and GPT-5.6 Sol (73.12%). BenchLM does not use these results to rank models overall.

37 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 16, 2026

Vals Index score table (37 models)

Score
1
75.14%
2
Kimi K3Moonshot AI
74.70%
3
73.12%
4
70.36%
5
69.88%
6
68.61%
7
68.41%
8
GPT-5.5OpenAI
67.95%
9
66.10%
10
Grok 4.5SpaceXAI
65.30%
11
65.14%
12
GLM 5.2Zhipu AI
65.02%
13
62.75%
14
60.06%
15
MiniMax M3MiniMax
58.94%
16
57.49%
17
55.62%
18
Kimi K2.6Moonshot AI
55.17%
20
GLM 5.1Zhipu AI
52.45%
21
52.42%
22
52.33%
23
Mimo V2.5Xiaomi
51.57%
24
50.74%
26
InklingThinkingmachines
49.28%
27
48.89%
28
46.63%
29
Grok 4.3SpaceXAI
46.48%
31
41.56%
33
39.50%
34
37.81%
36
Laguna M.1Poolside
33.33%
37
Laguna Xs.2Poolside
30.04%

The published Vals Index snapshot places Claude Fable 5 first at 75.14%. The third row is 2.03 points behind. The broader top-10 range is 9.85 points, so many of the published results sit in a relatively narrow band.

37 models have been evaluated on Vals Index. The benchmark falls in the External benchmark mirrors category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. 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 v1.2 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.

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 2.1, and Vibe Code Bench.

Which model leads the published Vals Index snapshot?

Claude Fable 5 currently leads the published Vals Index snapshot with 75.14% 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?

37 AI models are included in BenchLM's mirrored Vals Index snapshot, based on the public leaderboard captured on July 16, 2026.

Last updated: July 16, 2026 · mirrored from the public benchmark leaderboard

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.