ClaimBench
Judging whether a 10-K excerpt supports a claim, contradicts it or says nothing about it. Run by Vals AI.
As of 24 Oct 2026, GPT-6.1 Sol leads ClaimBench on BenchLeader with 100.0%, ahead of Claude Opus 5.5 at 100.0%, across 5 model configurations with a published result.
- Published by
- Vals AI
- Category
- Knowledge
- Index weight
- Reference only
- Models
- 5
- Data as of
- 24 Oct 2026
- Newest result
- 23 Oct 2026
Vals AI (vals.ai).
- 1GPT-6.1 Sol (max)100.0%
- 2Claude Opus 5.5100.0%
- 3Claude Haiku 5.5100.0%
- 4Claude Sonnet 5.5100.0%
- 5GPT-6 Luna (max)99.2%
5 of 5
| # | ||||
|---|---|---|---|---|
| 1 |  GPT-6.1 Solmax | 100.0% | 69.9 | 2026-10-23 |
| 2 |  Claude Opus 5.5 | 100.0% | 62.0 | 2026-10-23 |
| 3 | Claude Haiku 5.5 | 100.0% | – | 2026-10-23 |
| 4 | Claude Sonnet 5.5 | 100.0% | – | 2026-10-23 |
| 5 | GPT-6 Lunamax | 99.2% | 60.0 | 2026-10-23 |
More knowledge benchmarks · All LLM benchmarks
Cite as: BenchLeader, “ClaimBench leaderboard”, data as of 24 Oct 2026, https://www.benchleader.com/benchmarks/vals_claimbench.
ClaimBench: questions
- What does ClaimBench measure?
- Judging whether a 10-K excerpt supports a claim, contradicts it or says nothing about it. Run by Vals AI. Scores are reported in percent of tasks solved; higher is better.
- Which AI model leads ClaimBench?
- GPT-6.1 Sol leads ClaimBench with 100.0% as of 24 Oct 2026, ahead of Claude Opus 5.5 at 100.0%.
- How many models have ClaimBench results?
- 5 model configurations have a ClaimBench result on BenchLeader, all taken from Vals AI.
- Who runs ClaimBench and how often is it updated?
- ClaimBench is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does ClaimBench count toward the BenchLeader Index?
- No. ClaimBench is shown for reference but left out of the composite index.