Vals AI private benchmark for understanding long-context credit agreements.
BenchLM mirrors the public Vals AI CorpFin v2 leaderboard captured from https://www.vals.ai/benchmarks/corp_fin_v2 and updated by Vals on May 16, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.
CorpFin v2 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.
BenchLM mirrors the published corpfin v2 score view for CorpFin v2. Grok 4.3 leads the public snapshot at 68.53% , followed by GPT-5.5 (68.42%) and Kimi K2.5 Thinking (68.26%). BenchLM does not use these results to rank models overall.
Grok 4.3
xAI
grok/grok-4.3
GPT-5.5
OpenAI
openai/gpt-5.5
Kimi K2.5 Thinking
Moonshot AI
kimi/kimi-k2.5-thinking
The published CorpFin v2 snapshot is tightly clustered at the top: Grok 4.3 sits at 68.53%, while the third row is only 0.27 points behind. The broader top-10 spread is 2.45 points, so many of the published scores sit in a relatively narrow band.
105 models have been evaluated on CorpFin v2. 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. CorpFin v2 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Credit-agreement understanding tasks
Format
Accuracy score
Difficulty
Professional finance document reasoning
The Vals CorpFin v2 page reports overall, exact-page, max-fitting-context, and shared-max-context task views. BenchLM keeps it display only.
Version
CorpFin v2 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
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 AI private benchmark for understanding long-context credit agreements.
Grok 4.3 currently leads the published CorpFin v2 snapshot with 68.53% corpfin v2 score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
105 AI models are included in BenchLM's mirrored CorpFin v2 snapshot, based on the public leaderboard captured on May 16, 2026.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.