Skip to main content
BenchLM

Vals Public Benefits Bench v1.1 (Public Benefits Bench v1.1)

We show this table for reference; we do not rank on it.

Data verified 36 confirmed releases in the last 30 daysFollow model changes

Can AI help people navigate SNAP benefits?

Public Benefits Bench v1.1 score on Public Benefits Bench v1.1 — September 27, 2026

We mirror the published public benefits bench v1.1 score view for Public Benefits Bench v1.1. Claude Opus 5 leads the public snapshot at 76.93%, followed by Claude Fable 5.1 (74.90%) and Claude Opus 5.5 (70.64%). We do not use these results to rank models overall.

1Proprietary

Claude Opus 5

Anthropic

76.93%
Overall 79.24
2Proprietary

Claude Fable 5.1

Anthropic

74.90%
Overall 82.5Context 1M
3Proprietary

Claude Opus 5.5

Anthropic

70.64%
Overall 86.94Context 1M

43 modelsAgenticCurrentDisplay onlyUpdated September 27, 2026

Public Benefits Bench v1.1 score table (43 models)

Score
1
Claude Opus 5Anthropic · Closed
76.93%
2
Claude Fable 5.1Anthropic · Closed
74.90%
3
Claude Opus 5.5Anthropic · Closed
70.64%
4
Claude Fable 5Anthropic · Closed
70.43%
5
MiMo-V2.6-ProXiaomi · Open weight
68.94%
6
Hy4 previewTencent · Open weight
68.61%
7
GLM-5.3Z.AI · Open weight
68.54%
8
Muse Spark 1.2Meta · Closed
68.47%
9
Kimi K3Moonshot AI · Closed
68.27%
10
Claude Opus 4.8Anthropic · Closed
68.13%
11
MiMo-V2.6-FlashXiaomi · Open weight
67.59%
12
Claude Sonnet 5.5Anthropic · Closed
67.19%
13
Qwen3.8 MaxAlibaba · Open weight
67.12%
14
Grok 4.6xAI · Closed
66.85%
15
GPT-5.6 SolOpenAI · Closed
66.51%
16
Claude Sonnet 5Anthropic · Closed
66.03%
17
Grok 4.7xAI · Closed
65.63%
18
Gemini 3.8 FlashGoogle · Closed
65.29%
19
DeepSeek V4.1 FlashDeepSeek · Open weight
64.28%
20
MiniMax M3MiniMax · Open weight
64.14%
21
DeepSeek V4 Pro 0813DeepSeek · Open weight
62.92%
22
Claude Sonnet 4.6Anthropic · Closed
62.45%
23
GPT-5.6 TerraOpenAI · Closed
62.38%
24
GLM-5.1Z.AI · Open weight
61.84%
25
Muse Spark 1.1Meta · Closed
61.30%
26
GPT-5.6 LunaOpenAI · Closed
61.16%
27
GPT-5.5OpenAI · Closed
60.89%
28
Gemini 3.5 FlashGoogle · Closed
59.47%
29
Inkling-SmallThinking Machines Lab · Open weight
59.41%
30
InklingThinking Machines Lab · Open weight
58.46%
31
GPT-6 LunaOpenAI · Closed
57.65%
32
Kimi K2.6Moonshot AI · Open weight
56.63%
33
GPT-6 SolOpenAI · Closed
56.63%
34
Gemini 3.6 FlashGoogle · Closed
56.56%
35
Claude Haiku 4.5Anthropic · Closed
54.26%
36
Gemini 3.1 Pro PreviewGoogle
53.79%
37
Gemini 3.5 Flash-LiteGoogle · Closed
51.83%
38
Grok 4.3xAI · Closed
51.69%
39
Ling 3.0 Flash 2607ant
50.74%
40
Mercury 2.5Inception · Closed
45.26%
41
Grok 4.1 Fast (Reasoning)xAI · Closed
44.79%
42
Laguna M.1Poolside · Closed
43.84%
43
Laguna XS.2Poolside · Open weight
41.41%

How Public Benefits Bench v1.1 is shown here

BenchLM mirrors the public Vals AI Public Benefits Bench v1.1 leaderboard captured from https://www.vals.ai/benchmarks/snap and updated by Vals on September 27, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Public Benefits Bench v1.1 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.

Snapshot

43 Vals rows1 task viewsprivate datasetTasks: OverallDisplay only
Public Benefits Bench v1.1 on Vals AIVals methodologyVals home

The published Public Benefits Bench v1.1 snapshot places Claude Opus 5 first at 76.93%. The third row is 6.29 points behind. The broader top-10 range is 8.80 points, so many of the published results sit in a relatively narrow band.

43 models have been evaluated on Public Benefits Bench v1.1. The benchmark falls in the Agentic category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. Public Benefits Bench v1.1 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Public Benefits Bench v1.1

Year

2026

Tasks

SNAP public-benefits navigation tasks

Format

Accuracy score

Difficulty

Public-benefits policy navigation

BenchLM mirrors the public Vals AI Public Benefits Bench v1.1 leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

Public Benefits Bench v1.1Public benchmark source

Freshness and provenance

Version

Public Benefits Bench v1.1 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.

Questions

What does Public Benefits Bench v1.1 measure?

Can AI help people navigate SNAP benefits?

Which model leads the published Public Benefits Bench v1.1 snapshot?

Claude Opus 5 currently leads the published Public Benefits Bench v1.1 snapshot with 76.93% public benefits bench v1.1 score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Public Benefits Bench v1.1?

The September 27, 2026 snapshot contains 43 AI models.

Last updated: September 27, 2026 · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.